id
stringlengths
1
3
all_gold
stringlengths
2
376
raw_text
stringlengths
20
472
messages
listlengths
3
3
200
{"ORGANISATION": ["Big Brother Watch", "South Wales Police", "Metropolitan Police", "South Wales Police"], "COUNTRY": ["United Kingdom"], "TASK": ["facial recognition", "facial recognition"]}
In 2018, a report by the civil liberties and rights campaigning organisation Big Brother Watch revealed that two United Kingdom police forces, South Wales Police and the Metropolitan Police, were using live facial recognition at public events and in public spaces, in September 2019, South Wales Police use of facial rec...
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
201
{"PRODUCT": ["ANIMAL"], "PROGRAMMING_LANGUAGE": ["R"], "FIELD": ["statistical computing", "graphics"]}
ANIMAL has been ported to R, a freely available language and environment for statistical computing and graphics.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
202
{"ALGORITHM": ["Time-inhomogeneous hidden Bernoulli model", "TI-HBM", "hidden Markov model", "HMM"], "TASK": ["automatic speech recognition"]}
Time-inhomogeneous hidden Bernoulli model (TI-HBM) is an alternative to hidden Markov model (HMM) for automatic speech recognition.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
203
{"ORGANISATION": ["Nvidia"], "CONFERENCE": ["SIGGRAPH"]}
In July 2016, Nvidia demonstrated during SIGGRAPH a new method of foveated rendering claimed to be invisible to users.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
204
{"MISC": ["speech act theory"], "RESEARCHER": ["John Searle", "Terry Winograd", "Flores"]}
Both rely on speech act theory developed by John Searle in the 1960s and enhanced by Terry Winograd and Flores in the 1970s.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
205
{"ALGORITHM": ["Neural network models"], "RESEARCHER": ["George Miller"], "PRODUCT": ["Wordnet"]}
Neural network models of concept formation and the structure of knowledge have opened powerful hierarchical models of knowledge organization such as George Miller 's Wordnet.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
206
{"ALGORITHM": ["Template matching"], "TASK": ["face recognition", "medical image processing"], "PRODUCT": ["facial recognition system"]}
Template matching has various applications and is used in such fields as face recognition (see facial recognition system) and medical image processing.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
207
{"RESEARCHER": ["Navneet Dalal", "Bill Triggs"], "ORGANISATION": ["French National Institute for Research in Computer Science and Automation", "INRIA"], "ALGORITHM": ["HOG descriptors"], "CONFERENCE": ["Conference on Computer Vision and Pattern Recognition", "CVPR"]}
However, usage only became widespread in 2005 when Navneet Dalal and Bill Triggs, researchers for the French National Institute for Research in Computer Science and Automation (INRIA), presented their supplementary work on HOG descriptors at the Conference on Computer Vision and Pattern Recognition (CVPR).
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
208
{"UNIVERSITY": ["Penn"], "ORGANISATION": ["AT & T Labs", "Bell Labs", "Secure Systems Research department"], "FIELD": ["AI", "Machine Learning"], "RESEARCHER": ["Michael L. Littman", "David A. McAllester", "Richard S. Sutton", "Michael Collins"]}
Prior to joining the Penn faculty in 2002, he spent a decade (1991-2001) in AT & T Labs and Bell Labs, including as head of the AI department with colleagues including Michael L. Littman, David A. McAllester, and Richard S. Sutton; Secure Systems Research department; and Machine Learning department with members such as...
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
209
{"FIELD": ["supervised learning", "unsupervised learning"], "TASK": ["Cluster analysis"]}
When data are unlabelled, supervised learning is not possible, and an unsupervised learning approach is required which attempts to find natural Cluster analysis to groups, and then map new data to these formed groups.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
210
{"FIELD": ["computer science", "artificial intelligence", "robotics"], "ORGANISATION": ["MIT A.I. Lab"]}
This field of computer science developed in the 1950s at academic institutions such as the MIT A.I. Lab, originally as a branch of artificial intelligence and robotics.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
211
{"METRICS": ["Log loss"]}
It could also be replaced by the Log loss equation below:
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
212
{"ORGANISATION": ["Shirley Ryan AbilityLab", "Rehabilitation Institute of Chicago"], "UNIVERSITY": ["University of California at Berkeley", "MIT", "Stanford University", "University of Twente"], "COUNTRY": ["Netherlands"], "FIELD": ["biomechatronics"]}
The Shirley Ryan AbilityLab (formerly the Rehabilitation Institute of Chicago), University of California at Berkeley, MIT, Stanford University, and University of Twente in the Netherlands are the researching leaders in biomechatronics.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
213
{"METRICS": ["mean squared prediction error", "forecasting accuracy"]}
Given a set of predicted values and a corresponding set of actual values for X for various time periods, a common evaluation technique is to use the mean squared prediction error; other measures are also available (see forecasting # forecasting accuracy).
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
214
{"METRICS": ["accuracy"]}
Other measures, such as the proportion of correct predictions (also termed accuracy), are not useful when the two classes are of very different sizes.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
215
{"PRODUCT": ["OpenCV"], "CONFERENCE": ["Computer Vision and Pattern Recognition"]}
The first alpha version of OpenCV was released to the public at the Conference on Computer Vision and Pattern Recognition in 2000, and five betas were released between 2001 and 2005.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
216
{"METRICS": ["BLEU"]}
Results have been presented which give correlation of up to 0.964 with human judgement at the corpus level, compared to BLEU 's achievement of 0.817 on the same data set.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
217
{"METRICS": ["VMAF", "SSIM", "PSNR -HVS", "VQM-VFD", "accuracy"]}
An early version of VMAF has been shown to outperform other image and video quality metrics such as SSIM, PSNR -HVS and VQM-VFD on three of four datasets in terms of prediction accuracy, when compared to subjective ratings.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
218
{"TASK": ["machine translation", "information retrieval"]}
For example, the ambiguity of 'mouse' (animal or device) is not relevant in machine translation, but is relevant in information retrieval.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
219
{"ALGORITHM": ["Geometric hashing"], "FIELD": ["computer vision"], "TASK": ["object recognition"]}
Geometric hashing was originally suggested in computer vision for object recognition in 2D and 3D,
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
220
{"FIELD": ["machine learning", "supervised learning", "reinforcement learning"]}
It forms one of the three main categories of machine learning, along with supervised learning and reinforcement learning.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
221
{"FIELD": ["Reinforcement learning", "game", "control theory", "operations research", "information theory", "simulation-based optimization", "multi-agent systems", "swarm intelligence", "statistics"], "ALGORITHM": ["genetic algorithm"]}
Reinforcement learning, due to its generality, is studied in many other disciplines, such as game, control theory, operations research, information theory, simulation-based optimization, multi-agent systems, swarm intelligence, statistics and genetic algorithm s.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
222
{"FIELD": ["Pattern recognition", "artificial intelligence", "machine learning"]}
Pattern recognition is closely related to artificial intelligence and machine learning,
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
223
{"ALGORITHM": ["neural network", "multivariate regression"], "FIELD": ["supervised learning", "unsupervised learning", "data mining"], "TASK": ["classification", "function approximation", "time-series prediction"]}
The software is used to design, train and deploy neural network (supervised learning and unsupervised learning) models to perform a wide variety of tasks such as data mining, classification, function approximation, multivariate regression and time-series prediction.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
224
{"CONFERENCE": ["Association for the Advancement of Artificial Intelligence"]}
In 2016, he was elected Fellow of Association for the Advancement of Artificial Intelligence.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
225
{"ORGANISATION": ["National Academy of Sciences", "American Academy of Arts and Sciences"]}
She serves as a member of the National Academy of Sciences (since 2005), American Academy of Arts and Sciences (since 2009),
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
226
{"MISC": ["Yom Kippur War", "Israeli"], "PRODUCT": ["surface-to-air missile"], "COUNTRY": ["Egypt", "Syria"]}
During the 1973 Yom Kippur War, Soviet-supplied surface-to-air missile batteries in Egypt and Syria caused heavy damage Israeli fighter jet s.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
227
{"PRODUCT": ["HTK book", "HTK toolkit"]}
Another resource (free but copyrighted) is the HTK book (and the accompanying HTK toolkit).
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
228
{"CONFERENCE": ["2004 AAAI"]}
- were taken in the 2004 AAAI Spring Symposium where linguists, computer scientists, and other interested researchers first aligned interests and proposed shared tasks and benchmark data sets for the systematic computational research on affect, appeal, subjectivity, and sentiment in text.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
229
{"TASK": ["eyeball inspection", "cluster analysis", "principal component analysis"]}
A single grid can be analysed for both content (eyeball inspection) and structure (cluster analysis, principal component analysis, and a variety of structural indices relating to the complexity and range of the ratings being the chief techniques used).
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
230
{"ORGANISATION": ["Toyota"], "PRODUCT": ["Self-driving car"]}
In 2018 Toyota was regarded as being behind in Self-driving car and in need of innovation.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
231
{"MISC": ["ionosphere reflections", "meteor trails", "three body scatter spike"]}
Such targets include natural objects such as ground, sea, precipitation (such as rain, snow or hail), sand storm s, animals (especially birds), atmospheric turbulence, and other atmospheric effects, such as ionosphere reflections, meteor trails, and three body scatter spike.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
232
{"PRODUCT": ["industrial"], "MISC": ["biped gait"]}
In planning and control, the essential difference between humanoids and other kinds of robots (like industrial ones) is that the movement of the robot must be human-like, using legged locomotion, especially biped gait.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
233
{"ALGORITHM": ["gradient descent"], "MISC": ["local minimum", "curvature"], "METRICS": ["accuracy"]}
The gradient descent can take many iterations to compute a local minimum with a required accuracy, if the curvature in different directions is very different for the given function.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
234
{"MISC": ["1997 RoboCup 2D Soccer Simulation League", "RoboCup"], "CONFERENCE": ["International Joint Conference on Artificial Intelligence"], "LOCATION": ["Nagoya"], "COUNTRY": ["Japan"]}
The 1997 RoboCup 2D Soccer Simulation League was the first RoboCup competition promoted in conjunction with International Joint Conference on Artificial Intelligence held in Nagoya, Japan, from 23 to 29 August 1997.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
235
{"PROGRAMMING_LANGUAGE": ["Python", "R"], "PRODUCT": ["Rserve"]}
Other programming options include an embedded Python environment, and an R Console plus support for Rserve.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
236
{"RESEARCHER": ["Bonn", "Wolfram Burgard", "Dieter Fox", "Sebastian Thrun"], "FIELD": ["artificial intelligence", "robotics", "software engineering", "civil engineering", "information systems", "geosciences."], "MISC": ["AAAI Classic Paper award"]}
From Bonn he has contributed fundamentally to artificial intelligence and robotics (with Wolfram Burgard, Dieter Fox, Sebastian Thrun among his students), and to the development of software engineering, particularly in civil engineering, and information systems, particularly in the geosciences. won the AAAI Classic Pap...
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
237
{"CONFERENCE": ["USA edition of Campus Party"], "LOCATION": ["TCF Center", "Detroit", "Michigan"]}
The first USA edition of Campus Party will take place from 20 to 22 of August at TCF Center in Detroit, Michigan.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
238
{"RESEARCHER": ["Yann LeCun", "Yoshua Bengio", "Hinton"], "MISC": ["Turing Award"], "ALGORITHM": ["deep neural networks"]}
Together with Yann LeCun, and Yoshua Bengio, Hinton won the 2018 Turing Award for conceptual and engineering breakthroughs that have made deep neural networks a critical component of computing.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
239
{"PRODUCT": ["Euler Math Toolbox", "MATLAB"]}
Euler Math Toolbox uses a matrix language similar to MATLAB, a system that had been under development since the 1970s.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
240
{"PROGRAMMING_LANGUAGE": ["Scheme", "Common Lisp", "Perl", "D"]}
Some languages make it possible portably (e.g. Scheme, Common Lisp, Perl or D).
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
241
{"MISC": ["Perceptrons", "XOR function"], "RESEARCHER": ["Marvin Minsky", "Seymour Papert"]}
In 1969 a famous book entitled Perceptrons by Marvin Minsky and Seymour Papert showed that it was impossible for these classes of network to learn an XOR function.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
242
{"MISC": ["Russian"], "PRODUCT": ["SYSTRAN"], "ORGANISATION": ["USAF Foreign Technology Division", "National Air and Space Intelligence Center"], "LOCATION": ["Wright-Patterson Air Force Base", "Ohio"]}
Large numbers of Russian scientific and technical documents were translated using SYSTRAN under the auspices of the USAF Foreign Technology Division (later the National Air and Space Intelligence Center) at Wright-Patterson Air Force Base, Ohio.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
243
{"FIELD": ["Semi-supervised learning", "unsupervised learning", "supervised learning"]}
Semi-supervised learning falls between unsupervised learning (without any labeled training data) and supervised learning (with completely labeled training data).
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
244
{"ALGORITHM": ["n -gram model", "probabilistic language model", "Markov model"]}
An n -gram model is a type of probabilistic language model for predicting the next item in such a sequence in the form of a (n − 1) -order Markov model .efficiently.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
245
{"LOCATION": ["Cleveland Clinic"], "PRODUCT": ["Cyc", "natural language query interface of biomedical information"]}
The Cleveland Clinic has used Cyc to develop a natural language query interface of biomedical information, spanning decades of information on cardiothoracic surgeries.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
246
{"COUNTRY": ["United States", "Japan"]}
The incident strained relations between the United States and Japan, and resulted in the arrest and prosecution two senior executives, as well as the imposition of sanctions on the company by both countries.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
247
{"ALGORITHM": ["artificial neural network", "cross-validation"], "FIELD": ["machine learning"], "MISC": ["training", "tuning"]}
If the modeling is done by an artificial neural network or other machine learning, the optimization of parameters is called training, while the optimization of model hyperparameters is called tuning and often uses cross-validation..
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
248
{"COUNTRY": ["United Kingdom", "India", "Australia"], "ORGANISATION": ["Rotten Tomatoes", "Fandango"]}
Localized versions of the site available in the United Kingdom, India, and Australia were discontinued following the acquisition of Rotten Tomatoes by Fandango.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
249
{"TASK": ["NER", "speech recognition"], "METRICS": ["accuracy"]}
The NER model is one of a number of methods for determining the accuracy of live subtitles in television broadcasts and events that are produced using speech recognition.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
250
{"RESEARCHER": ["Atran"], "UNIVERSITY": ["Cambridge University", "Hebrew University", "École pratique des hautes études", "École Polytechnique", "John Jay College of Criminal Justice"], "LOCATION": ["Jerusalem", "Paris", "New York City"]}
Atran has taught at Cambridge University, Hebrew University in Jerusalem, the École pratique des hautes études and École Polytechnique in Paris, and John Jay College of Criminal Justice in New York City.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
251
{"PRODUCT": ["SHRDLU"], "TASK": ["natural language understanding"], "RESEARCHER": ["Terry Winograd"], "UNIVERSITY": ["MIT"]}
SHRDLU was an early natural language understanding computer program, developed by Terry Winograd at MIT in 1968-1970
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
252
{"MISC": ["B.E.", "M.S.", "M.S.", "Ph.D."], "FIELD": ["electronics engineering", "electrical and computer engineering", "computer science", "Artificial Intelligence"], "UNIVERSITY": ["B.M.S. College of Engineering", "Bangalore University", "Drexel University", "University of Wisconsin-Madison"], "LOCATION": ["Bangalore...
He received a B.E. in electronics engineering from B.M.S. College of Engineering in Bangalore, India in 1982, when it was affiliated with Bangalore University, an M.S. in electrical and computer engineering in 1984 from Drexel University, and an M.S. in computer science in 1989, and a Ph.D. in 1990, respectively, from ...
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
253
{"METRICS": ["word error rate", "WER", "real time factor"]}
Accuracy is usually rated with word error rate (WER), whereas speed is measured with the real time factor.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
254
{"RESEARCHER": ["Terry Winograd"], "FIELD": ["natural language processing"]}
In 1971 Terry Winograd developed an early natural language processing engine capable of interpreting naturally written commands within a simple rule-governed environment.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
255
{"FIELD": ["artificial intelligence"], "RESEARCHER": ["Marvin Minsky", "Herbert A. Simon", "Allen Newell"]}
In artificial intelligence, Marvin Minsky, Herbert A. Simon, and Allen Newell are prominent.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
256
{"FIELD": ["electrical engineering", "electronic engineering", "computer engineering", "design engineering"], "MISC": ["user-machine interfaces"]}
In the latter half of the 20th century, electrical engineering itself separated into several disciplines, specialising in the design and analysis of systems that manipulate physical signals; electronic engineering and computer engineering as examples; while design engineering developed to deal with functional design of...
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
257
{"METRICS": ["accuracy", "Fraction Correct", "FC", "TP + TN", "TP + TN", "TP + TN + FP + FN"]}
Perhaps the simplest statistic is accuracy or Fraction Correct (FC), which measures the fraction of all instances that are correctly categorized; it is the ratio of the number of correct classifications to the total number of correct or incorrect classifications: (TP + TN) / Total Population = (TP + TN) / (TP + TN + FP...
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
258
{"CONFERENCE": ["First International Conference Data Mining and Knowledge Discovery", "KDD-95", "AAAI"], "LOCATION": ["Montreal"]}
In the academic community, the major forums for research started in 1995 when the First International Conference Data Mining and Knowledge Discovery (KDD-95) was started in Montreal under AAAI sponsorship.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
259
{"FIELD": ["data mining", "machine learning"]}
In this approach, models are developed using different data mining, machine learning algorithms to predict users' rating of unrated items.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
260
{"ALGORITHM": ["SVM", "empirical risk", "Tikhonov regularization"], "MISC": ["loss function"], "METRICS": ["hinge loss"]}
In light of the above discussion, we see that the SVM technique is equivalent to empirical risk with Tikhonov regularization, where in this case the loss function is the hinge loss
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
261
{"PERSON": ["Molly McGrath", "Chris Rose", "Kenny Florian"], "ORGANISATION": ["UFC"]}
The 2015 edition was hosted by Molly McGrath, with Chris Rose and former UFC fighter Kenny Florian as commentators.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
262
{"PRODUCT": ["Micro-Planner", "SHRDLU"], "RESEARCHER": ["Gerald Jay Sussman", "Eugene Charniak", "Terry Winograd", "Sussman", "Winograd", "Winograd", "Eugene Charniak", "Thorne McCarty"], "TASK": ["natural-language understanding", "story understanding", "legal reasoning"]}
A subset called Micro-Planner was implemented by Gerald Jay Sussman, Eugene Charniak and Terry Winograd Sussman,, and Winograd 1971 and was used in Winograd's natural-language understanding program SHRDLU, Eugene Charniak's story understanding work, Thorne McCarty's work on legal reasoning, and some other projects.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
263
{"PRODUCT": ["WordNet", "information systems"], "TASK": ["word-sense disambiguation", "information retrieval", "automatic text classification", "Automatic summarization", "machine translation", "automatic crossword puzzle generation"]}
WordNet has been used for a number of purposes in information systems, including word-sense disambiguation, information retrieval, automatic text classification, Automatic summarization, machine translation and even automatic crossword puzzle generation.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
264
{"RESEARCHER": ["Keutzer"], "ORGANISATION": ["IEEE"]}
Keutzer was named a Fellow of the IEEE in 1996.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
265
{"ALGORITHM": ["nonlinear weighted sum", "hyperbolic tangent", "sigmoid function", "softmax function", "rectifier function"], "MISC": ["activation function"]}
A widely used type of composition is the nonlinear weighted sum, where math\ textstyle f (x) = K\ left (\ sum _ i w _ i g _ i (x)\ right) / math, where math\ textstyle K / math (commonly referred to as the activation function) is some predefined function, such as the hyperbolic tangent, sigmoid function, softmax functi...
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
266
{"MISC": ["Westworld"]}
In the film Westworld, female robots actually engaged in intercourse with human men as part of the make-believe vacation world human customers paid to attend.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
267
{"TASK": ["terminology extraction", "part-of-speech tagging", "phrase chunking"]}
Typically, the process starts by terminology extraction and concepts or noun phrase s from plain text using linguistic processors such as part-of-speech tagging and phrase chunking.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
268
{"FIELD": ["machine learning"], "TASK": ["handwriting recognition"]}
They demonstrated its performance on a number of problems of interest to the machine learning community, including handwriting recognition.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
269
{"UNIVERSITY": ["Stanford"], "RESEARCHER": ["Scheinman", "George Devol"], "PRODUCT": ["Unimate", "industrial robot"]}
While studying at Stanford, Scheinman was awarded a fellowship sponsored by George Devol, the inventor of the Unimate, the first industrial robot.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
270
{"TASK": ["machine translations"], "METRICS": ["bilingual evaluation understudy", "BLEU"], "PRODUCT": ["paraphrase generation models"]}
While originally used to evaluate machine translations, bilingual evaluation understudy (BLEU) has been used successfully to evaluate paraphrase generation models as well.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
271
{"ORGANISATION": ["Unimation", "Kawasaki Heavy Industries", "GKN"], "PRODUCT": ["Unimate"], "COUNTRY": ["Japan", "England"]}
Unimation later licensed their technology to Kawasaki Heavy Industries and GKN, manufacturing Unimate s in Japan and England respectively.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
272
{"CONFERENCE": ["ECML PKDD", "knowledge discovery and data mining", "KDD"], "FIELD": ["machine learning"]}
Much of the confusion between these two research communities (which do often have separate conferences and separate journals, ECML PKDD being a major exception) comes from the basic assumptions they work with: in machine learning, performance is usually evaluated with respect to the ability to reproduce known knowledge...
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
273
{"ALGORITHM": ["Hidden Markov model"], "PRODUCT": ["automatic speech recognition systems"]}
Hidden Markov model s are the basis for most modern automatic speech recognition systems.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
274
{"LOCATION": ["Bangalore"], "COUNTRY": ["India"], "TASK": ["handwriting recognition"]}
, a company in Bangalore, India specializing in online handwriting recognition software.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
275
{"MISC": ["canonical form"], "METRICS": ["BLEU", "BiLingual Evaluation Understudy"]}
Do repeated translations converge on a single expression in both languages? I.e. does the translation method show stationarity or produce a canonical form? Does the translation become stationary without losing the original meaning? This metric has been criticized as not being well correlated with BLEU (BiLingual Evalua...
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
276
{"CONFERENCE": ["American Association for Artificial Intelligence"], "ORGANISATION": ["Center for Advanced Study in the Behavioral Sciences", "Canadian Institute for Advanced Research", "Canadian Psychological Association", "Royal Society of Canada"], "UNIVERSITY": ["Stanford University", "MIT"], "FIELD": ["Cognitive S...
He holds fellowships in the American Association for Artificial Intelligence, the Center for Advanced Study in the Behavioral Sciences at Stanford University, the MIT Center for Cognitive Science, the Canadian Institute for Advanced Research, the Canadian Psychological Association, and was elected Fellow of the Royal S...
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
277
{"RESEARCHER": ["Hinton", "Yoshua Bengio", "Yann LeCun"], "MISC": ["Godfathers of AI", "Godfathers of Deep Learning"]}
Hinton - together with Yoshua Bengio and Yann LeCun - are referred to by some as the Godfathers of AI and Godfathers of Deep Learning.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
278
{"PRODUCT": ["eSpeak", "eSpeak", "Google Translate"], "MISC": ["Mandarin", "Cantonese."]}
The lightweight open-source speech project eSpeak, which has its own approach to synthesis, has experimented with Mandarin and Cantonese. eSpeak was used by Google Translate from May 20102010.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
279
{"PRODUCT": ["Software Automatic Mouth"], "TASK": ["synthesis program"]}
Also released in 1982, Software Automatic Mouth was the first commercial all-software voice synthesis program.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
280
{"METRICS": ["TRUE Positive Rate", "TPR", "Sensitivity", "recall", "TP / ( TP + FN )", "FALSE Negative Rate", "FNR", "FN / ( TP + FN )", "TRUE Negative Rate", "TNR", "Specificity", "SPC", "TN / ( TN + FP )", "FALSE Positive Rate", "FPR", "FP / ( TN + FP )"]}
The column ratios are TRUE Positive Rate (TPR, aka Sensitivity or recall) (TP / (TP + FN)), with complement the FALSE Negative Rate (FNR) (FN / (TP + FN)); and TRUE Negative Rate (TNR, aka Specificity, SPC) (TN / (TN + FP)), with complement FALSE Positive Rate (FPR) (FP / (TN + FP)).
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
281
{"PERSON": ["Edsinger"], "ORGANISATION": ["Weber"], "PRODUCT": ["Kismet"]}
Edsinger and Weber collaborated on many other robots as well, and their experience working with the Kismet
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
282
{"PROGRAMMING_LANGUAGE": ["R", "Python"]}
R functionality is accessible from several scripting languages such as Python, are available as well.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
283
{"PROGRAMMING_LANGUAGE": ["VAL"], "PRODUCT": ["Unimate robots"]}
VAL was one of the first robot languages and was used in Unimate robots.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
284
{"CONFERENCE": ["2009 Conference on Computer Vision and Pattern Recognition", "CVPR"], "LOCATION": ["Florida"]}
They presented their database for the first time as a poster at the 2009 Conference on Computer Vision and Pattern Recognition (CVPR) in Florida.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
285
{"MISC": ["Categorization tasks"], "TASK": ["unsupervised classification", "Cluster analysis"], "FIELD": ["unsupervised learning"]}
Categorization tasks in which no labels are supplied are referred to as unsupervised classification, unsupervised learning, Cluster analysis.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
286
{"TASK": ["Object recognition", "emotion recognition"]}
It needs to Object recognition, recognize and locate humans and further emotion recognition.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
287
{"MISC": ["encoding", "recall", "retrieval"]}
The process is complex and contains encoding and recall or retrieval.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
288
{"PRODUCT": ["Stewart platforms", "Stewart platform", "articulated robot"]}
Also known as parallel robots, or generalized Stewart platforms (in the Stewart platform, the actuators are paired together on both the basis and the platform), these systems are articulated robot s that use similar mechanisms for the movement of either the robot on its base, or one or more manipulator arms.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
289
{"FIELD": ["Machine vision", "systems engineering", "computer vision", "computer science"]}
Machine vision as a systems engineering discipline can be considered distinct from computer vision, a form of computer science.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
290
{"ALGORITHM": ["LSTM gates", "logistic sigmoid function"]}
The activation function of the LSTM gates is often the logistic sigmoid function.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
291
{"METRICS": ["sample mean", "minimum variance unbiased estimator", "MVUE", "maximum likelihood estimator"]}
In other words, the sample mean is the (necessarily unique) efficient estimator, and thus also the minimum variance unbiased estimator (MVUE), in addition to being the maximum likelihood estimator.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
292
{"MISC": ["Scientific American"], "RESEARCHER": ["Berners-Lee", "James Hendler", "Ora Lassila"], "PRODUCT": ["Web", "Semantic Web"]}
The 2001 Scientific American article by Berners-Lee, James Hendler, and Ora Lassila described an expected evolution of the existing Web to a Semantic Web.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
293
{"MISC": ["Blade Runner"], "PERSON": ["Sean Young", "Rachael", "Tyrell", "Sammon", "Nina Axelrod"]}
Blade Runner used a number of then-lesser-known actors: Sean Young portrays Rachael, an experimental replicant implanted with the memories of Tyrell's niece, causing her to believe she is human; Sammon, pp. 92-93 Nina Axelrod auditioned for the role.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
294
{"RESEARCHER": ["Gerry Sussman", "Eugene Charniak", "Seymour Papert", "Terry Winograd"], "UNIVERSITY": ["University of Edinburgh"], "PRODUCT": ["Micro-Planner", "SHRDLU"], "LOCATION": ["Edinburgh"]}
Gerry Sussman, Eugene Charniak, Seymour Papert and Terry Winograd visited the University of Edinburgh in 1971 spreading the news about Micro-Planner and SHRDLU and casting doubt on the resolution uniform proof procedure approach that had been the mainstay of the Edinburgh Logicists.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
295
{"RESEARCHER": ["Walter", "Rodney Brooks", "Hans Moravec", "Mark Tilden"], "FIELD": ["robotics"]}
Walter's work inspired subsequent generations of robotics researchers such as Rodney Brooks, Hans Moravec and Mark Tilden.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
296
{"ALGORITHM": ["CNN"], "RESEARCHER": ["Alex Krizhevsky"], "CONFERENCE": ["ImageNet Large Scale Visual Recognition Challenge 2012"]}
Subsequently, a similar GPU-based CNN by Alex Krizhevsky et al. won the ImageNet Large Scale Visual Recognition Challenge 2012.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
297
{"MISC": ["loss functions", "TRUE probability"], "METRICS": ["log loss", "Brier score"]}
Commonly used loss functions for probabilistic classification include log loss and the Brier score between the predicted and the TRUE probability distributions.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
298
{"ORGANISATION": ["NtechLab", "NIST"], "FIELD": ["biometrics"], "MISC": ["Russian"]}
In May 2016, NtechLab was admitted to the official testing of biometrics technology by NIST among the three Russian companies.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...
299
{}
However, floating-point numbers have only a certain amount of mathematical precision.
[ { "role": "system", "content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the...