ROUGE metric computed with rouge-score-rs

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,10 +1,148 @@
 ---
-title: Rouge
-emoji: 📚
-colorFrom: purple
-colorTo: blue
+title: ROUGE (rouge-score-rs)
+emoji: 🦀
+colorFrom: blue
+colorTo: red
 sdk: static
+app_file: index.html
 pinned: false
+license: apache-2.0
+tags:
+- evaluate
+- metric
+description: >-
+  ROUGE computed with rouge-score-rs, a Rust implementation of Google's rouge-score.
+  Same inputs, options and scores as the `rouge` metric, computed faster.
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Metric Card for ROUGE (rouge-score-rs)
+
+## Metric Description
+ROUGE, or Recall-Oriented Understudy for Gisting Evaluation, is a set of metrics and a software package used for evaluating automatic summarization and machine translation software in natural language processing. The metrics compare an automatically produced summary or translation against a reference or a set of references (human-produced) summary or translation.
+
+Note that ROUGE is case insensitive, meaning that upper case letters are treated the same way as lower case letters.
+
+This metric has the same inputs, options and outputs as the [`rouge`](https://huggingface.co/spaces/evaluate-metric/rouge) metric and, for the inputs listed under [Compatibility](#compatibility), returns identical scores. It computes them with [`rouge-score-rs`](https://pypi.org/project/rouge-score-rs/) ([source](https://github.com/SyntaxSpirits/rougers)), a Rust implementation of the [Google Research reimplementation of ROUGE](https://github.com/google-research/google-research/tree/master/rouge), instead of the pure Python `rouge-score` package.
+
+This Space is maintained by SyntaxSpirits and is not affiliated with Google or Hugging Face. It is derived from the Apache-2.0 [`evaluate-metric/rouge`](https://huggingface.co/spaces/evaluate-metric/rouge) Space by the HuggingFace Evaluate Authors; see [LICENSE](LICENSE).
+
+Install the dependencies before loading the metric (tested with `rouge-score-rs` 0.1.1):
+
+```bash
+pip install evaluate 'rouge-score-rs[aggregate]>=0.1.1'
+```
+
+## How to Use
+At minimum, this metric takes as input a list of predictions and a list of references:
+```python
+>>> import evaluate
+>>> rouge = evaluate.load('SyntaxSpirits/rouge')
+>>> predictions = ["hello there", "general kenobi"]
+>>> references = ["hello there", "general kenobi"]
+>>> results = rouge.compute(predictions=predictions,
+...                         references=references)
+>>> print({key: round(value, 4) for key, value in results.items()})
+{'rouge1': 1.0, 'rouge2': 1.0, 'rougeL': 1.0, 'rougeLsum': 1.0}
+```
+
+One can also pass a custom tokenizer, which is especially useful for non-Latin languages: the default tokenizer keeps only the ASCII letters `a`–`z` and digits.
+```python
+>>> results = rouge.compute(predictions=predictions,
+...                         references=references,
+...                         tokenizer=lambda x: x.split())
+>>> print({key: round(value, 4) for key, value in results.items()})
+{'rouge1': 1.0, 'rouge2': 1.0, 'rougeL': 1.0, 'rougeLsum': 1.0}
+```
+
+It can also deal with lists of references for each prediction. For every ROUGE type, the reference with the highest F1 is used:
+```python
+>>> rouge = evaluate.load('SyntaxSpirits/rouge', seed=0)
+>>> predictions = ["hello there", "general kenobi"]
+>>> references = [["hello", "there"], ["general kenobi", "general yoda"]]
+>>> results = rouge.compute(predictions=predictions,
+...                         references=references)
+>>> print({key: round(value, 4) for key, value in results.items()})
+{'rouge1': 0.8333, 'rouge2': 0.5, 'rougeL': 0.8333, 'rougeLsum': 0.8333}
+```
+
+### Inputs
+- **predictions** (`list` of `str`): predictions to score.
+- **references** (`list` of `str` or `list` of `list` of `str`): one reference per prediction, or several references per prediction.
+- **rouge_types** (`list`): ROUGE types to calculate. Defaults to `['rouge1', 'rouge2', 'rougeL', 'rougeLsum']`.
+    - `"rouge1"` to `"rouge9"`: n-gram based scoring, e.g. `"rouge2"` for bigrams.
+    - `"rougeL"`: longest common subsequence based scoring.
+    - `"rougeLsum"`: summary-level longest common subsequence; sentences are separated by `"\n"`. See [here](https://github.com/huggingface/datasets/issues/617) for more information.
+- **use_aggregator** (`boolean`): if `True`, returns aggregated scores. Defaults to `True`.
+- **use_stemmer** (`boolean`): if `True`, the default tokenizer applies the Porter stemmer to tokens longer than three characters. Defaults to `False`.
+- **tokenizer** (callable, optional): a function that splits a string into a list of string tokens. Lowercasing and stemming are done only by the default tokenizer.
+
+### Output Values
+The output is a dictionary with one entry for each ROUGE type in `rouge_types`; each value is an F1 score between 0 and 1.
+
+If `use_aggregator=True` (the default), each entry is the median of 1,000 bootstrap means of the per-prediction F1 scores, as in the `rouge` metric. The bootstrap uses NumPy's random state; pass `seed` to `evaluate.load` to make it reproducible and comparable with the `rouge` metric loaded with the same seed.
+
+If `use_aggregator=False`, each entry is a list with one F1 score per prediction.
+
+### Examples
+An example without aggregation:
+```python
+>>> rouge = evaluate.load('SyntaxSpirits/rouge')
+>>> predictions = ["hello goodbye", "ankh morpork"]
+>>> references = ["goodbye", "general kenobi"]
+>>> results = rouge.compute(predictions=predictions,
+...                         references=references,
+...                         use_aggregator=False)
+>>> print(list(results.keys()))
+['rouge1', 'rouge2', 'rougeL', 'rougeLsum']
+>>> print([round(score, 4) for score in results["rouge1"]])
+[0.6667, 0.0]
+```
+
+The same example, but with aggregation:
+```python
+>>> rouge = evaluate.load('SyntaxSpirits/rouge', seed=0)
+>>> results = rouge.compute(predictions=predictions,
+...                         references=references,
+...                         use_aggregator=True)
+>>> print(round(results["rouge1"], 4))
+0.3333
+```
+
+The same example, but only calculating `rouge1`:
+```python
+>>> results = rouge.compute(predictions=predictions,
+...                         references=references,
+...                         rouge_types=['rouge1'])
+>>> print({key: round(value, 4) for key, value in results.items()})
+{'rouge1': 0.3333}
+```
+
+## Compatibility
+Scores are bit-for-bit identical to the `rouge` metric for string inputs with the default tokenizer, with or without stemming, and with custom tokenizers that return lists of strings. This is checked against `rouge-score` 0.1.2 by the [rouge-score-rs test suite](https://github.com/SyntaxSpirits/rougers#compatibility) and, for this metric, by comparing both metrics with the same seed on thousands of random examples.
+
+Differences from the `rouge` metric:
+- Tokens returned by a custom tokenizer must be hashable, such as strings.
+- An unknown ROUGE type raises `ValueError` when the scorer is created, and malformed inputs (for example `None` instead of a string) can raise a different exception type.
+
+## Speed
+Pair scoring runs in Rust. With the default tokenizer and one reference per prediction, all pairs are scored in one call that uses every CPU core unless `RAYON_NUM_THREADS` limits it (in a process forked after such a call, pairs are scored on one thread). Aggregation still runs the same NumPy bootstrap as the `rouge` metric, so it benefits less.
+
+## Limitations and Bias
+See [Schluter (2017)](https://aclanthology.org/E17-2007/) for an in-depth discussion of many of ROUGE's limits.
+
+## Citation
+```bibtex
+@inproceedings{lin-2004-rouge,
+    title = "{ROUGE}: A Package for Automatic Evaluation of Summaries",
+    author = "Lin, Chin-Yew",
+    booktitle = "Text Summarization Branches Out",
+    month = jul,
+    year = "2004",
+    address = "Barcelona, Spain",
+    publisher = "Association for Computational Linguistics",
+    url = "https://www.aclweb.org/anthology/W04-1013",
+    pages = "74--81",
+}
+```
+
+## Further References

index.html

@@ -1,19 +1,34 @@
-<!doctype html>
-<html>
-	<head>
-		<meta charset="utf-8" />
-		<meta name="viewport" content="width=device-width" />
-		<title>My static Space</title>
-		<link rel="stylesheet" href="style.css" />
-	</head>
-	<body>
-		<div class="card">
-			<h1>Welcome to your static Space!</h1>
-			<p>You can modify this app directly by editing <i>index.html</i> in the Files and versions tab.</p>
-			<p>
-				Also don't forget to check the
-				<a href="https://huggingface.co/docs/hub/spaces" target="_blank">Spaces documentation</a>.
-			</p>
-		</div>
-	</body>
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<title>ROUGE (rouge-score-rs)</title>
+<style>
+  body { font-family: system-ui, -apple-system, sans-serif; max-width: 760px; margin: 40px auto; padding: 0 20px; line-height: 1.55; color: #1f2328; }
+  pre { background: #f6f8fa; padding: 14px 16px; border-radius: 6px; overflow-x: auto; }
+  code { font-family: ui-monospace, SFMono-Regular, Menlo, monospace; font-size: 0.92em; }
+  a { color: #0969da; }
+</style>
+</head>
+<body>
+<h1>ROUGE (rouge-score-rs)</h1>
+<p>An <a href="https://huggingface.co/docs/evaluate">Evaluate</a> metric with the same inputs, options and scores as
+<a href="https://huggingface.co/spaces/evaluate-metric/rouge"><code>rouge</code></a>, computed with
+<a href="https://pypi.org/project/rouge-score-rs/">rouge-score-rs</a>, a Rust implementation of Google's
+<code>rouge-score</code>.</p>
+<pre><code>pip install evaluate 'rouge-score-rs[aggregate]&gt;=0.1.1'</code></pre>
+<pre><code>import evaluate
+
+rouge = evaluate.load("SyntaxSpirits/rouge")
+results = rouge.compute(
+    predictions=["hello there", "general kenobi"],
+    references=["hello there", "general kenobi"],
+)
+print(results)  # {'rouge1': 1.0, 'rouge2': 1.0, 'rougeL': 1.0, 'rougeLsum': 1.0}</code></pre>
+<p>Inputs, outputs, compatibility notes and examples are in the
+<a href="https://huggingface.co/spaces/SyntaxSpirits/rouge/blob/main/README.md">metric card</a>.
+Source code: <a href="https://github.com/SyntaxSpirits/rougers">SyntaxSpirits/rougers</a>.
+Not affiliated with Google or Hugging Face.</p>
+</body>
 </html>

rouge.py

@@ -0,0 +1,172 @@
+# Copyright 2020 The HuggingFace Evaluate Authors.
+# Modified in 2026 by SyntaxSpirits: scores with rouge-score-rs instead of rouge-score.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+""" ROUGE metric computed with rouge-score-rs, a Rust implementation of Google's rouge-score. """
+
+import datasets
+import numpy  # Here to have a nice missing dependency error message early on
+import rouge_score_rs
+from packaging import version
+from rouge_score_rs import rouge_scorer, scoring
+
+import evaluate
+
+
+if version.parse(rouge_score_rs.__version__) < version.parse("0.1.1"):
+    raise ImportError("This metric requires rouge-score-rs>=0.1.1: pip install -U 'rouge-score-rs[aggregate]>=0.1.1'")
+
+
+_CITATION = """\
+@inproceedings{lin-2004-rouge,
+    title = "{ROUGE}: A Package for Automatic Evaluation of Summaries",
+    author = "Lin, Chin-Yew",
+    booktitle = "Text Summarization Branches Out",
+    month = jul,
+    year = "2004",
+    address = "Barcelona, Spain",
+    publisher = "Association for Computational Linguistics",
+    url = "https://www.aclweb.org/anthology/W04-1013",
+    pages = "74--81",
+}
+"""
+
+_DESCRIPTION = """\
+ROUGE, or Recall-Oriented Understudy for Gisting Evaluation, is a set of metrics and a software package used for
+evaluating automatic summarization and machine translation software in natural language processing.
+The metrics compare an automatically produced summary or translation against a reference or a set of references (human-produced) summary or translation.
+
+With the default tokenizer, ROUGE is case insensitive, meaning that upper case letters are treated the same way as
+lower case letters.
+
+This metric uses rouge-score-rs (https://github.com/SyntaxSpirits/rougers), a Rust implementation of
+Google Research's reimplementation of ROUGE (https://github.com/google-research/google-research/tree/master/rouge).
+It gives the same scores as the `rouge` metric for string inputs and tokenizers that return lists of strings,
+and computes them faster.
+"""
+
+_KWARGS_DESCRIPTION = """
+Calculates ROUGE F1 scores for a list of predictions and references.
+Args:
+    predictions: list of predictions to score, as strings.
+    references: list with one reference string per prediction, or a list of reference strings per prediction.
+        With several references, the one with the highest F1 is used for each ROUGE type.
+    rouge_types: A list of rouge types to calculate.
+        Valid names:
+        `"rouge{n}"` for n from 1 to 9 (e.g. `"rouge1"`, `"rouge2"`): n-gram based scoring,
+        `"rougeL"`: Longest common subsequence based scoring.
+        `"rougeLsum"`: rougeLsum splits text using `"\n"`.
+        See details in https://github.com/huggingface/datasets/issues/617
+    use_stemmer: Bool indicating whether the default tokenizer should apply the Porter stemmer.
+    use_aggregator: If True, return for each ROUGE type the median of 1,000 bootstrap means of the
+        per-prediction scores (pass `seed` to `evaluate.load` for reproducible values); if False, return
+        one score per prediction.
+    tokenizer: Optional callable splitting a string into a list of string tokens. Lowercasing and
+        stemming are only done by the default tokenizer.
+Returns:
+    rouge1: rouge_1 (f1),
+    rouge2: rouge_2 (f1),
+    rougeL: rouge_l (f1),
+    rougeLsum: rouge_lsum (f1)
+Examples:
+
+    >>> rouge = evaluate.load('SyntaxSpirits/rouge')
+    >>> predictions = ["hello there", "general kenobi"]
+    >>> references = ["hello there", "general kenobi"]
+    >>> results = rouge.compute(predictions=predictions, references=references)
+    >>> print(results)
+    {'rouge1': 1.0, 'rouge2': 1.0, 'rougeL': 1.0, 'rougeLsum': 1.0}
+"""
+
+
+class Tokenizer:
+    """Helper class to wrap a callable into a class with a `tokenize` method as used by rouge-score."""
+
+    def __init__(self, tokenizer_func):
+        self.tokenizer_func = tokenizer_func
+
+    def tokenize(self, text):
+        return self.tokenizer_func(text)
+
+
+@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
+class Rouge(evaluate.Metric):
+    def _info(self):
+        return evaluate.MetricInfo(
+            description=_DESCRIPTION,
+            citation=_CITATION,
+            inputs_description=_KWARGS_DESCRIPTION,
+            features=[
+                datasets.Features(
+                    {
+                        "predictions": datasets.Value("string", id="sequence"),
+                        "references": datasets.Sequence(datasets.Value("string", id="sequence")),
+                    }
+                ),
+                datasets.Features(
+                    {
+                        "predictions": datasets.Value("string", id="sequence"),
+                        "references": datasets.Value("string", id="sequence"),
+                    }
+                ),
+            ],
+            codebase_urls=[
+                "https://huggingface.co/spaces/SyntaxSpirits/rouge",
+                "https://github.com/SyntaxSpirits/rougers",
+                "https://github.com/google-research/google-research/tree/master/rouge",
+            ],
+            reference_urls=[
+                "https://en.wikipedia.org/wiki/ROUGE_(metric)",
+                "https://github.com/google-research/google-research/tree/master/rouge",
+            ],
+        )
+
+    def _compute(
+        self, predictions, references, rouge_types=None, use_aggregator=True, use_stemmer=False, tokenizer=None
+    ):
+        if rouge_types is None:
+            rouge_types = ["rouge1", "rouge2", "rougeL", "rougeLsum"]
+
+        multi_ref = isinstance(references[0], list)
+
+        if tokenizer is not None:
+            tokenizer = Tokenizer(tokenizer)
+
+        scorer = rouge_scorer.RougeScorer(rouge_types=rouge_types, use_stemmer=use_stemmer, tokenizer=tokenizer)
+        if use_aggregator:
+            aggregator = scoring.BootstrapAggregator()
+        else:
+            scores = []
+
+        if multi_ref:
+            all_scores = (scorer.score_multi(ref, pred) for ref, pred in zip(references, predictions))
+        else:
+            all_scores = scorer.score_batch(references, predictions)
+
+        for score in all_scores:
+            if use_aggregator:
+                aggregator.add_scores(score)
+            else:
+                scores.append(score)
+
+        if use_aggregator:
+            result = aggregator.aggregate()
+            for key in result:
+                result[key] = result[key].mid.fmeasure
+
+        else:
+            result = {}
+            for key in scores[0]:
+                result[key] = list(score[key].fmeasure for score in scores)
+
+        return result