pear-mt 1.0.0__tar.gz

pear_mt-1.0.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        https://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 2026 Lorenzo Proietti
+
+   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
+
+       https://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.

pear_mt-1.0.0/MANIFEST.in

@@ -0,0 +1 @@
+recursive-include tests *.json *.py

pear_mt-1.0.0/PKG-INFO

@@ -0,0 +1,310 @@
+Metadata-Version: 2.4
+Name: pear-mt
+Version: 1.0.0
+Summary: Inference package for PEAR machine translation metrics.
+Author: Lorenzo Proietti
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/prosho-97/pear
+Project-URL: Repository, https://github.com/prosho-97/pear
+Project-URL: Issues, https://github.com/prosho-97/pear/issues
+Project-URL: Paper, https://aclanthology.org/2026.acl-long.1953/
+Project-URL: Models, https://huggingface.co/collections/Prosho/pear
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: <3.14,>=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: huggingface-hub>=0.23
+Requires-Dist: numpy>=1.26
+Requires-Dist: pytorch-lightning>=2.4
+Requires-Dist: PyYAML>=6.0
+Requires-Dist: torch>=2.5
+Requires-Dist: transformers<6,>=4.40
+Provides-Extra: dev
+Requires-Dist: black>=24.0; extra == "dev"
+Requires-Dist: build>=1.2; extra == "dev"
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: twine>=5.1; extra == "dev"
+Dynamic: license-file
+
+<div align="center">
+
+# 🍐 PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation
+
+[![ACL 2026](https://img.shields.io/badge/ACL-2026-2f6fdd)](https://2026.aclweb.org/)
+[![ACL Anthology](https://img.shields.io/badge/ACL%20Anthology-paper-b31b1b)](https://aclanthology.org/2026.acl-long.1953/)
+[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Collection-ffcc4d)](https://huggingface.co/collections/Prosho/pear)
+[![PyPI](https://img.shields.io/pypi/v/pear-mt)](https://pypi.org/project/pear-mt/)
+[![Python](https://img.shields.io/pypi/pyversions/pear-mt)](https://pypi.org/project/pear-mt/)
+[![CI](https://github.com/prosho-97/pear/actions/workflows/ci.yml/badge.svg)](https://github.com/prosho-97/pear/actions/workflows/ci.yml)
+[![License](https://img.shields.io/badge/License-Apache%202.0-green)](https://www.apache.org/licenses/LICENSE-2.0)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000)](https://github.com/psf/black)
+
+</div>
+
+This repository provides the inference toolkit for 🍐**PEAR**: **P**airwise **E**valuation for **A**utomatic **R**elative Scoring in Machine Translation.
+
+PEAR reframes reference-free machine translation evaluation as a graded pairwise comparison: given a source segment and two candidate translations, it predicts both the **direction** and **magnitude** of their quality difference. The toolkit also supports reference-anchored PEAR scoring and PEAR-based minimum Bayes risk (MBR) decoding.
+
+* 📄 Paper: [ACL Anthology](https://aclanthology.org/2026.acl-long.1953/)
+* 🤗 Models and resources: [PEAR Hugging Face collection](https://huggingface.co/collections/Prosho/pear)
+
+## Installation
+
+PEAR supports Python 3.12 and 3.13. Install the published package from PyPI:
+
+```bash
+python -m pip install pear-mt
+```
+
+The PyPI distribution is named `pear-mt`; the Python import package is named
+`pear`, and the primary command-line program is also `pear`:
+
+```python
+import pear
+```
+
+To install from a local clone instead:
+
+```bash
+git clone https://github.com/prosho-97/pear.git
+cd pear
+python -m pip install .
+```
+
+For local development, install the development extra too:
+
+```bash
+python -m pip install -e ".[dev]"
+```
+
+## Loading a model
+
+```python
+import pear
+
+metric = pear.load_metric("pear")       # resolves to Prosho/pear on Hugging Face
+metric_xl = pear.load_metric("pear-xl") # resolves to Prosho/pear-xl on Hugging Face
+```
+
+You can also pass a Hugging Face repository ID or a local PEAR model checkpoint path:
+
+```python
+metric = pear.load_metric("Prosho/pear")
+metric = pear.load_metric("/path/to/checkpoints/model.ckpt")
+```
+
+### Reproducible model revisions
+
+The official `pear` and `pear-xl` aliases use checkpoint and encoder revisions
+pinned by this package. This keeps their results stable even when files on the
+Hugging Face Hub change.
+
+For another Hugging Face repository, PEAR follows that repository's default
+branch unless you provide revisions explicitly. `revision` pins the PEAR
+checkpoint repository; `encoder_revision` pins the underlying Transformers
+encoder. A full commit hash gives the strongest reproducibility:
+
+```python
+metric = pear.load_metric(
+    "organization/custom-pear",
+    revision="<checkpoint-commit>",
+    encoder_revision="<encoder-commit>",
+)
+```
+
+The same controls are available from the CLI:
+
+```bash
+pear score \
+    --hf-model organization/custom-pear \
+    --revision <checkpoint-commit> \
+    --encoder-revision <encoder-commit> \
+    --input pairs.tsv \
+    --output scored.tsv
+```
+
+Passing either option overrides the corresponding default. Local checkpoint
+paths do not use a Hub checkpoint revision, although
+`encoder_revision` can still pin an encoder that the checkpoint configuration
+loads from the Hub.
+
+## Pairwise QE scoring
+
+```python
+scores = pear.score_pairwise(
+    metric,
+    sources=["The cat is on the mat."],
+    translations_a=["El gato está en la alfombra."],
+    translations_b=["El gato está en el mapa."],
+)
+```
+
+Positive scores mean `translations_a` is preferred over `translations_b`.
+
+To score both candidate orders:
+
+```python
+scores = pear.score_pairwise(
+    metric,
+    sources=["The cat is on the mat."],
+    translations_a=["El gato está en la alfombra."],
+    translations_b=["El gato está en el mapa."],
+    mode="both",
+)
+# {"forward": [...], "reverse": [...]}
+```
+
+## Reference-anchored scoring
+
+Reference-anchored PEAR uses the human reference (or any other list of candidate translations) as the second candidate/anchor.
+
+```python
+scores = pear.score_reference_anchored(
+    metric,
+    sources=["The cat is on the mat."],
+    translations=["El gato está en la alfombra."],
+    references=["El gato está sobre la alfombra."],
+)
+```
+
+As with pairwise QE scoring, set `mode="both"` to score both candidate orders for reference-anchored inputs.
+
+## PEAR for MBR decoding
+
+```python
+from pear.mbr import pear_utility_matrix, select_mbr_hypothesis
+
+hyps = ["This is a good translation.", "This is a very good translation.", "This is a bad translation."]
+utility = pear_utility_matrix(metric, "Questa è una traduzione molto buona.", hyps, mode="half")
+index, expected_utility = select_mbr_hypothesis(utility)
+best = hyps[index]
+# best -> "This is a very good translation."
+```
+
+Use `mode="full"` to score all off-diagonal ordered pairs (N<sup>2</sup> - N comparisons). Use `mode="half"` to score one triangular half and fill the opposite direction by PEAR antisymmetry.
+
+## Batching, devices, and progress bars
+
+Python and CLI inference are batched. Use `batch_size` / `--batch-size` to control the number of pairwise examples per PEAR forward batch.
+
+By default, PEAR uses:
+
+```python
+gpus="auto"
+```
+
+This selects one available CUDA/MPS accelerator when present. Pass `gpus=0` or `--gpus 0` to force CPU. Progress bars are shown by default; in Python calls, control them with the `progress_bar` argument (`progress_bar=True` by default, or `progress_bar=False` to disable them).
+
+## CLI
+
+### Score a TSV file
+
+Pairwise input TSV must contain `src`, `mt_0`, and `mt_1` columns:
+
+```bash
+pear score --model pear --input pairs.tsv --output scored.tsv --batch-size 16
+pear score --hf-model Prosho/pear --input pairs.tsv --output scored.tsv --batch-size 16
+pear score --checkpoint /path/to/model.ckpt --input pairs.tsv --output scored.tsv --batch-size 16
+```
+
+Reference-anchored input TSV must contain `src`, `mt`, and `ref` columns:
+
+```bash
+pear score --model pear --mode reference --input refs.tsv --output scored.tsv --batch-size 16
+```
+
+Add `--both` to score both candidate orders.
+
+### Run MBR
+
+Input JSONL rows must contain `src` and `hypotheses`:
+
+```json
+{"src": "source text", "hypotheses": ["hyp A", "hyp B"]}
+```
+
+Run half- or full-matrix PEAR MBR:
+
+```bash
+pear mbr --model pear --input nbest.jsonl --output selected.jsonl --utility half --batch-size 16
+pear mbr --hf-model Prosho/pear-xl --input nbest.jsonl --output selected.jsonl --utility full --batch-size 16
+pear mbr --checkpoint /path/to/model.ckpt --input nbest.jsonl --output selected.jsonl --batch-size 16
+```
+
+## Development
+
+Install the development extra before running formatter checks:
+
+```bash
+python -m pip install -e ".[dev]"
+```
+
+Then run:
+
+```bash
+python -m black --check pear
+python -m pytest
+python -m compileall pear
+```
+
+Network tokenizer regressions use immutable encoder snapshots and run in CI
+against both Transformers 4.40.2 and the latest supported 5.x release. The
+multi-gigabyte checkpoint regression remains opt-in. Before creating a release
+tag, record its baseline under Transformers 4.40.2:
+
+```bash
+python -m pytest \
+    tests/test_regressions.py::test_released_checkpoints_match_440_scores_and_key_mismatches \
+    --run-checkpoint-integration \
+    --write-checkpoint-baseline=/tmp/pear-checkpoints-4.40.2.json
+```
+
+Then, on the same hardware and dtype under the latest Transformers 5.x, compare
+against that file:
+
+```bash
+python -m pytest \
+    tests/test_regressions.py::test_released_checkpoints_match_440_scores_and_key_mismatches \
+    --run-checkpoint-integration \
+    --checkpoint-baseline=/tmp/pear-checkpoints-4.40.2.json
+```
+
+The comparison requires the same checkpoint-key mismatch sets, finite scores,
+preference directions and rankings, and scores within `rtol=1e-4` and
+`atol=1e-4`.
+
+## Citation
+
+PEAR has been published at ACL 2026 (Main Conference). If you use it, please consider citing our paper as follows:
+
+```bibtex
+@inproceedings{proietti-etal-2026-pear,
+    title = "{PEAR}: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation",
+    author = "Proietti, Lorenzo  and
+      Grundkiewicz, Roman  and
+      Post, Matt",
+    editor = "Liakata, Maria  and
+      Moreira, Viviane P.  and
+      Zhang, Jiajun  and
+      Jurgens, David",
+    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
+    month = jul,
+    year = "2026",
+    address = "San Diego, California, United States",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2026.acl-long.1953/",
+    doi = "10.18653/v1/2026.acl-long.1953",
+    pages = "42189--42207",
+    ISBN = "979-8-89176-390-6"
+}
+```
+
+## License
+
+This project is released under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). See [`LICENSE`](LICENSE) for the full license text.