Every trained head: explicit spans, relations and records; reference runtime; phone results
ff95cf8 verified | { | |
| "about": "Parity corpus for LiteRT ports of GLiNER2 checkpoints: short general-domain texts with invented people and companies, and schema templates covering every call type gliner2 2.0.0 offers (entities with and without descriptions, relations, plain structures, choice fields, natural/latent/anchorless records, entity attributes, single- and multi-label classification, mixed schemas). Only agreement with the library is measured; there are no gold labels. Each text stays under 40 words so a call fits a 128-token bucket with its schema.", | |
| "templates": { | |
| "entities": {"entities": ["person", "organization", "location", "date"]}, | |
| "entities_described": {"entities": {"person": "a named individual", "product": "a named product, device or service", "money": "an amount of money"}}, | |
| "entities_single": {"entities": ["person", "organization"], "dtype": "str"}, | |
| "relations_work": {"relations": ["works_for", "founded", "located_in"]}, | |
| "relations_family": {"relations": {"parent_of": "the head is a parent of the tail", "married_to": "the two people are married"}}, | |
| "relations_event": {"relations": ["won", "held_in"]}, | |
| "structure_event": {"structures": [{"name": "event", "fields": [{"name": "name", "dtype": "str"}, {"name": "date", "dtype": "str"}, {"name": "place", "dtype": "str"}]}]}, | |
| "structure_order": {"structures": [{"name": "order", "fields": [{"name": "item", "dtype": "str"}, {"name": "category", "dtype": "str", "choices": ["electronics", "clothing", "furniture", "food"]}, {"name": "quantity", "dtype": "str"}]}]}, | |
| "record_natural": {"structures": [{"name": "employment", "mode": "natural", "anchor": "person", "fields": [{"name": "person", "dtype": "str"}, {"name": "company", "dtype": "str"}, {"name": "role", "dtype": "str"}]}]}, | |
| "record_latent": {"structures": [{"name": "employment", "mode": "latent", "fields": [{"name": "person", "dtype": "str"}, {"name": "company", "dtype": "str"}]}]}, | |
| "record_anchorless": {"structures": [{"name": "trip", "mode": "anchorless", "fields": [{"name": "traveler", "dtype": "str"}, {"name": "destination", "dtype": "str"}]}]}, | |
| "attributes": {"entities": ["person", "organization"], "attributes": {"role": {"labels": ["founder", "employee", "customer"]}}}, | |
| "classification_topic": {"classifications": [{"task": "topic", "labels": ["business", "family", "travel", "shopping", "science", "sports"]}]}, | |
| "classification_multi": {"classifications": [{"task": "tags", "labels": ["money", "people", "places", "dates", "products"], "multi_label": true}]}, | |
| "classification_described": {"classifications": [{"task": "tone", "labels": {"positive": "good news or praise", "negative": "bad news or complaints", "neutral": "plain facts"}}]}, | |
| "mixed": {"entities": ["person", "organization"], "relations": ["works_for"], "classifications": [{"task": "sentiment", "labels": ["positive", "negative", "neutral"]}]} | |
| }, | |
| "groups": { | |
| "business": { | |
| "templates": ["entities", "entities_single", "relations_work", "record_natural", "record_latent", "attributes", "classification_topic", "mixed"], | |
| "texts": [ | |
| "Nora Lindqvist founded Brightwell Labs in Oslo in 2019 and still runs it as chief executive.", | |
| "Tomas Ferreira joined Halcyon Freight in March as head of logistics, moving from a rival in Lisbon.", | |
| "Priya Raman works at Cobalt Analytics in Pune, where she leads a team of twelve engineers.", | |
| "Marco Bellini and Ines Duarte started Verde Foods together; Marco handles sales while Ines manages the kitchen in Porto.", | |
| "Westgate Mills hired Daniel Okafor as an accountant last week, and Sara Klein left the company after ten years.", | |
| "Kwame Mensah is the founder of Sunline Solar, a startup based in Accra that installs rooftop panels.", | |
| "After the merger, Lena Hoffmann became chief financial officer of Northpeak Group in Munich.", | |
| "Ravi Shah, an engineer at Tidewater Systems, presented the new billing platform to customers in Boston on Tuesday." | |
| ] | |
| }, | |
| "family": { | |
| "templates": ["entities", "relations_family", "record_latent", "classification_topic", "classification_described"], | |
| "texts": [ | |
| "Helen Ward married Peter Ward in 1998, and their daughter Emma was born two years later in Leeds.", | |
| "Carlos Mendes is the father of Lucia and Mateo, who both moved to Madrid for university.", | |
| "My grandmother Rosa raised four children on a farm near Cork before moving to Dublin.", | |
| "Aiko Tanaka and her husband Kenji celebrated their anniversary in Kyoto with their son Haruto.", | |
| "Fatima Diallo is the mother of twins, Amina and Yusuf, who turned nine on Sunday.", | |
| "James Porter's sister, Claire, lives in Toronto with her partner Mark and their dog.", | |
| "Olga Petrova married Ivan Sokolov last spring; Ivan's brother Dmitri was the best man.", | |
| "The Nguyen family, Linh, Bao and their son Minh, spent the holidays with relatives in Hanoi." | |
| ] | |
| }, | |
| "travel": { | |
| "templates": ["entities", "relations_work", "record_anchorless", "structure_event", "classification_topic", "classification_multi"], | |
| "texts": [ | |
| "Last July, Elena flew from Rome to Reykjavik and spent a week hiking near Vik.", | |
| "Ben and Chloe drove from Denver to Santa Fe, stopping overnight in Taos on the way.", | |
| "Our tour group arrived in Marrakech on Friday and leaves for Fez on Monday morning.", | |
| "Hugo booked a train from Paris to Geneva for the conference on 14 May.", | |
| "Mia visited her cousin in Cape Town and then took a ferry to Robben Island.", | |
| "The museum in Bilbao reopened in April after a two-year renovation led by the city council.", | |
| "Sam and Priya plan to backpack through Peru, starting in Cusco and ending in Lima.", | |
| "Grace missed her connection in Frankfurt, so she reached Warsaw a day late." | |
| ] | |
| }, | |
| "shopping": { | |
| "templates": ["entities_described", "structure_order", "record_natural", "classification_multi", "classification_described", "attributes"], | |
| "texts": [ | |
| "I ordered two oak chairs from Hearthwood for 180 dollars, but only one arrived.", | |
| "Lucas bought a Zenith X2 laptop and a wireless mouse at Volt Electronics for 1,240 euros.", | |
| "Please send three boxes of green tea and a ceramic teapot to the Seattle store.", | |
| "The customer returned a wool coat to Northline Apparel and asked for a refund of 95 pounds.", | |
| "Amara paid 12 dollars for a loaf of sourdough and a jar of honey at the Saturday market.", | |
| "Our office ordered forty desk lamps from Brightspace, and the invoice came to 2,000 dollars.", | |
| "Jonah's new Aurora headphones broke after a week, and the shop offered him a replacement.", | |
| "Ten kilograms of rice and five bags of lentils were delivered to the community kitchen." | |
| ] | |
| }, | |
| "science": { | |
| "templates": ["entities", "entities_described", "relations_work", "structure_event", "classification_topic", "classification_described"], | |
| "texts": [ | |
| "Dr. Yusuf Kaya and his team at the Halden Institute published a study on coral bleaching in June.", | |
| "The Meridian telescope in Chile recorded a supernova on 3 February, according to astronomer Lucia Ortiz.", | |
| "Researchers at Brookfield University tested a new battery that charges in six minutes.", | |
| "Marta Silva, a biologist at the Lisbon Aquarium, tagged forty sea turtles last summer.", | |
| "The probe Helios-4 entered orbit around Mars after a seven-month journey from Earth.", | |
| "Engineers at Polaris Robotics in Seoul unveiled a robot that sorts recycling by material.", | |
| "A trial run by Kestrel Health in Nairobi found the vaccine safe for children over five.", | |
| "Professor Anil Mehta left Crestview College to lead the climate lab at Northgate University." | |
| ] | |
| }, | |
| "sports": { | |
| "templates": ["entities", "relations_event", "structure_event", "record_latent", "classification_topic", "mixed"], | |
| "texts": [ | |
| "Sofia Marin won the Vienna Marathon in April, finishing ahead of last year's champion Ruth Abebe.", | |
| "The Harbor City Hawks beat the Ridgeview Bears 3 to 1 in the final held in Glasgow.", | |
| "Coach Andre Lopes signed a new contract with Atletico Verde until 2028.", | |
| "Kenji Watanabe took gold in the 200 metres at the championships in Nagoya on Saturday.", | |
| "The tennis open in Melbourne ended with Clara Weiss lifting her first trophy.", | |
| "Liam O'Brien scored twice as Dunmore Rovers won the cup at their home ground.", | |
| "The cycling race from Lyon to Annecy was won by Pieter de Vries after a late sprint.", | |
| "Amira Haddad set a national record in the long jump at the meet in Doha." | |
| ] | |
| } | |
| } | |
| } | |