evalscope 0.5.3__py3-none-any.whl → 0.5.5__py3-none-any.whl

evalscope/backend/rag_eval/cmteb/tasks/Clustering.py

@@ -0,0 +1,252 @@
+import itertools
+
+from datasets import Dataset, DatasetDict
+
+from mteb.abstasks.AbsTaskClustering import AbsTaskClustering
+from mteb.abstasks.AbsTaskClusteringFast import (
+    AbsTaskClusteringFast,
+    check_label_distribution,
+)
+from mteb.abstasks.TaskMetadata import TaskMetadata
+
+NUM_SAMPLES = 2048
+
+
+class CLSClusteringFastS2S(AbsTaskClusteringFast):
+    max_document_to_embed = NUM_SAMPLES
+    max_fraction_of_documents_to_embed = None
+
+    metadata = TaskMetadata(
+        name="CLSClusteringS2S",
+        description="Clustering of titles from CLS dataset. Clustering of 13 sets on the main category.",
+        reference="https://arxiv.org/abs/2209.05034",
+        dataset={
+            "path": "C-MTEB/CLSClusteringS2S",
+            "revision": "e458b3f5414b62b7f9f83499ac1f5497ae2e869f",
+        },
+        type="Clustering",
+        category="s2s",
+        modalities=["text"],
+        eval_splits=["test"],
+        eval_langs=["cmn-Hans"],
+        main_score="v_measure",
+        date=("2022-01-01", "2022-09-12"),
+        domains=["Academic", "Written"],
+        task_subtypes=["Thematic clustering", "Topic classification"],
+        license="Apache-2.0",
+        annotations_creators="derived",
+        dialect=[],
+        sample_creation="found",
+        bibtex_citation="""@misc{li2022csl,
+            title={CSL: A Large-scale Chinese Scientific Literature Dataset}, 
+            author={Yudong Li and Yuqing Zhang and Zhe Zhao and Linlin Shen and Weijie Liu and Weiquan Mao and Hui Zhang},
+            year={2022},
+            eprint={2209.05034},
+            archivePrefix={arXiv},
+            primaryClass={cs.CL}
+        }""",
+        descriptive_stats={
+            "n_samples": {"test": NUM_SAMPLES},
+            "avg_character_length": {},
+        },
+    )
+
+    def dataset_transform(self):
+        ds = {}
+        for split in self.metadata.eval_splits:
+            labels = list(itertools.chain.from_iterable(self.dataset[split]["labels"]))
+            sentences = list(
+                itertools.chain.from_iterable(self.dataset[split]["sentences"])
+            )
+
+            check_label_distribution(self.dataset[split])
+
+            ds[split] = Dataset.from_dict({"labels": labels, "sentences": sentences})
+        self.dataset = DatasetDict(ds)
+        self.dataset = self.stratified_subsampling(
+            self.dataset,
+            self.seed,
+            self.metadata.eval_splits,
+            label="labels",
+            n_samples=NUM_SAMPLES,
+        )
+
+
+class CLSClusteringFastP2P(AbsTaskClusteringFast):
+    max_document_to_embed = NUM_SAMPLES
+    max_fraction_of_documents_to_embed = None
+
+    metadata = TaskMetadata(
+        name="CLSClusteringP2P",
+        description="Clustering of titles + abstract from CLS dataset. Clustering of 13 sets on the main category.",
+        reference="https://arxiv.org/abs/2209.05034",
+        dataset={
+            "path": "C-MTEB/CLSClusteringP2P",
+            "revision": "4b6227591c6c1a73bc76b1055f3b7f3588e72476",
+        },
+        type="Clustering",
+        category="p2p",
+        modalities=["text"],
+        eval_splits=["test"],
+        eval_langs=["cmn-Hans"],
+        main_score="v_measure",
+        date=("2022-01-01", "2022-09-12"),
+        domains=["Academic", "Written"],
+        task_subtypes=["Thematic clustering", "Topic classification"],
+        license="Apache-2.0",
+        annotations_creators="derived",
+        dialect=[],
+        sample_creation="found",
+        bibtex_citation="""@misc{li2022csl,
+            title={CSL: A Large-scale Chinese Scientific Literature Dataset}, 
+            author={Yudong Li and Yuqing Zhang and Zhe Zhao and Linlin Shen and Weijie Liu and Weiquan Mao and Hui Zhang},
+            year={2022},
+            eprint={2209.05034},
+            archivePrefix={arXiv},
+            primaryClass={cs.CL}
+        }""",
+        descriptive_stats={
+            "n_samples": {"test": NUM_SAMPLES},
+            "avg_character_length": {},
+        },
+    )
+
+    def dataset_transform(self):
+        ds = {}
+        for split in self.metadata.eval_splits:
+            labels = list(itertools.chain.from_iterable(self.dataset[split]["labels"]))
+            sentences = list(
+                itertools.chain.from_iterable(self.dataset[split]["sentences"])
+            )
+
+            check_label_distribution(self.dataset[split])
+
+            ds[split] = Dataset.from_dict({"labels": labels, "sentences": sentences})
+        self.dataset = DatasetDict(ds)
+        self.dataset = self.stratified_subsampling(
+            self.dataset,
+            self.seed,
+            self.metadata.eval_splits,
+            label="labels",
+            n_samples=NUM_SAMPLES,
+        )
+
+
+class ThuNewsClusteringFastS2S(AbsTaskClusteringFast):
+    max_document_to_embed = NUM_SAMPLES
+    max_fraction_of_documents_to_embed = None
+
+    metadata = TaskMetadata(
+        name="ThuNewsClusteringS2S",
+        dataset={
+            "path": "C-MTEB/ThuNewsClusteringS2S",
+            "revision": "8a8b2caeda43f39e13c4bc5bea0f8a667896e10d",
+        },
+        description="Clustering of titles from the THUCNews dataset",
+        reference="http://thuctc.thunlp.org/",
+        type="Clustering",
+        category="s2s",
+        modalities=["text"],
+        eval_splits=["test"],
+        eval_langs=["cmn-Hans"],
+        main_score="v_measure",
+        date=("2006-01-01", "2007-01-01"),
+        domains=["News", "Written"],
+        task_subtypes=["Thematic clustering", "Topic classification"],
+        license="Not specified",
+        annotations_creators="derived",
+        dialect=[],
+        sample_creation="found",
+        bibtex_citation="""@software{THUCTC,
+  author = {Sun, M. and Li, J. and Guo, Z. and Yu, Z. and Zheng, Y. and Si, X. and Liu, Z.},
+  title = {THUCTC: An Efficient Chinese Text Classifier},
+  year = {2016},
+  note = {THU Chinese Text Classification Toolkit},
+  publisher = {THU Natural Language Processing Lab},
+  url = {https://github.com/thunlp/THUCTC}
+}""",
+        descriptive_stats={
+            "n_samples": {"test": NUM_SAMPLES},
+            "avg_character_length": {},
+        },
+    )
+
+    def dataset_transform(self):
+        ds = {}
+        for split in self.metadata.eval_splits:
+            labels = list(itertools.chain.from_iterable(self.dataset[split]["labels"]))
+            sentences = list(
+                itertools.chain.from_iterable(self.dataset[split]["sentences"])
+            )
+
+            check_label_distribution(self.dataset[split])
+
+            ds[split] = Dataset.from_dict({"labels": labels, "sentences": sentences})
+        self.dataset = DatasetDict(ds)
+        self.dataset = self.stratified_subsampling(
+            self.dataset,
+            self.seed,
+            self.metadata.eval_splits,
+            label="labels",
+            n_samples=NUM_SAMPLES,
+        )
+
+
+class ThuNewsClusteringFastP2P(AbsTaskClusteringFast):
+    max_document_to_embed = NUM_SAMPLES
+    max_fraction_of_documents_to_embed = None
+
+    metadata = TaskMetadata(
+        name="ThuNewsClusteringP2P",
+        dataset={
+            "path": "C-MTEB/ThuNewsClusteringP2P",
+            "revision": "5798586b105c0434e4f0fe5e767abe619442cf93",
+        },
+        description="Clustering of titles + abstracts from the THUCNews dataset",
+        reference="http://thuctc.thunlp.org/",
+        type="Clustering",
+        category="p2p",
+        modalities=["text"],
+        eval_splits=["test"],
+        eval_langs=["cmn-Hans"],
+        main_score="v_measure",
+        date=("2006-01-01", "2007-01-01"),
+        domains=["News", "Written"],
+        task_subtypes=["Thematic clustering", "Topic classification"],
+        license="Not specified",
+        annotations_creators="derived",
+        dialect=[],
+        sample_creation="found",
+        bibtex_citation="""@software{THUCTC,
+  author = {Sun, M. and Li, J. and Guo, Z. and Yu, Z. and Zheng, Y. and Si, X. and Liu, Z.},
+  title = {THUCTC: An Efficient Chinese Text Classifier},
+  year = {2016},
+  note = {THU Chinese Text Classification Toolkit},
+  publisher = {THU Natural Language Processing Lab},
+  url = {https://github.com/thunlp/THUCTC}
+}""",
+        descriptive_stats={
+            "n_samples": {"test": NUM_SAMPLES},
+            "avg_character_length": {},
+        },
+    )
+
+    def dataset_transform(self):
+        ds = {}
+        for split in self.metadata.eval_splits:
+            labels = list(itertools.chain.from_iterable(self.dataset[split]["labels"]))
+            sentences = list(
+                itertools.chain.from_iterable(self.dataset[split]["sentences"])
+            )
+
+            check_label_distribution(self.dataset[split])
+
+            ds[split] = Dataset.from_dict({"labels": labels, "sentences": sentences})
+        self.dataset = DatasetDict(ds)
+        self.dataset = self.stratified_subsampling(
+            self.dataset,
+            self.seed,
+            self.metadata.eval_splits,
+            label="labels",
+            n_samples=NUM_SAMPLES,
+        )

evalscope/backend/rag_eval/cmteb/tasks/PairClassification.py

@@ -0,0 +1,113 @@
+from mteb.abstasks.AbsTaskPairClassification import AbsTaskPairClassification
+from mteb.abstasks.TaskMetadata import TaskMetadata
+
+
+class Ocnli(AbsTaskPairClassification):
+    metadata = TaskMetadata(
+        name="Ocnli",
+        description="Original Chinese Natural Language Inference dataset",
+        reference="https://arxiv.org/abs/2010.05444",
+        dataset={
+            "path": "C-MTEB/OCNLI",
+            "revision": "66e76a618a34d6d565d5538088562851e6daa7ec",
+        },
+        type="PairClassification",
+        category="s2s",
+        modalities=["text"],
+        eval_splits=["validation"],
+        eval_langs=["cmn-Hans"],
+        main_score="max_accuracy",
+        date=None,
+        domains=None,
+        task_subtypes=None,
+        license=None,
+        annotations_creators=None,
+        dialect=None,
+        sample_creation=None,
+        bibtex_citation="""@misc{hu2020ocnli,
+            title={OCNLI: Original Chinese Natural Language Inference}, 
+            author={Hai Hu and Kyle Richardson and Liang Xu and Lu Li and Sandra Kuebler and Lawrence S. Moss},
+            year={2020},
+            eprint={2010.05444},
+            archivePrefix={arXiv},
+            primaryClass={cs.CL}
+        }""",
+        descriptive_stats={"n_samples": None, "avg_character_length": None},
+    )
+
+    def dataset_transform(self):
+        self.dataset = self.dataset.rename_column("sent1", "sentence1")
+        self.dataset = self.dataset.rename_column("sent2", "sentence2")
+
+
+class Cmnli(AbsTaskPairClassification):
+    metadata = TaskMetadata(
+        name="Cmnli",
+        description="Chinese Multi-Genre NLI",
+        reference="https://huggingface.co/datasets/clue/viewer/cmnli",
+        dataset={
+            "path": "C-MTEB/CMNLI",
+            "revision": "41bc36f332156f7adc9e38f53777c959b2ae9766",
+        },
+        type="PairClassification",
+        category="s2s",
+        modalities=["text"],
+        eval_splits=["validation", "test"],
+        eval_langs=["cmn-Hans"],
+        main_score="max_accuracy",
+        date=None,
+        domains=None,
+        task_subtypes=None,
+        license=None,
+        annotations_creators=None,
+        dialect=None,
+        sample_creation=None,
+        bibtex_citation="""@inproceedings{xu-etal-2020-clue,
+            title = "{CLUE}: A {C}hinese Language Understanding Evaluation Benchmark",
+            author = "Xu, Liang  and
+            Hu, Hai  and
+            Zhang, Xuanwei  and
+            Li, Lu  and
+            Cao, Chenjie  and
+            Li, Yudong  and
+            Xu, Yechen  and
+            Sun, Kai  and
+            Yu, Dian  and
+            Yu, Cong  and
+            Tian, Yin  and
+            Dong, Qianqian  and
+            Liu, Weitang  and
+            Shi, Bo  and
+            Cui, Yiming  and
+            Li, Junyi  and
+            Zeng, Jun  and
+            Wang, Rongzhao  and
+            Xie, Weijian  and
+            Li, Yanting  and
+            Patterson, Yina  and
+            Tian, Zuoyu  and
+            Zhang, Yiwen  and
+            Zhou, He  and
+            Liu, Shaoweihua  and
+            Zhao, Zhe  and
+            Zhao, Qipeng  and
+            Yue, Cong  and
+            Zhang, Xinrui  and
+            Yang, Zhengliang  and
+            Richardson, Kyle  and
+            Lan, Zhenzhong",
+            booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
+            month = dec,
+            year = "2020",
+            address = "Barcelona, Spain (Online)",
+            publisher = "International Committee on Computational Linguistics",
+            url = "https://aclanthology.org/2020.coling-main.419",
+            doi = "10.18653/v1/2020.coling-main.419",
+            pages = "4762--4772",
+        }""",
+        descriptive_stats={"n_samples": None, "avg_character_length": None},
+    )
+
+    def dataset_transform(self):
+        self.dataset = self.dataset.rename_column("sent1", "sentence1")
+        self.dataset = self.dataset.rename_column("sent2", "sentence2")

evalscope/backend/rag_eval/cmteb/tasks/Reranking.py

@@ -0,0 +1,153 @@
+from typing import Any
+from mteb.abstasks.AbsTask import ScoresDict
+from mteb.abstasks.AbsTaskReranking import AbsTaskReranking
+from mteb.abstasks.TaskMetadata import HFSubset, TaskMetadata
+from mteb.encoder_interface import Encoder, EncoderWithQueryCorpusEncode
+
+
+class T2Reranking(AbsTaskReranking):
+    metadata = TaskMetadata(
+        name="T2Reranking",
+        description="T2Ranking: A large-scale Chinese Benchmark for Passage Ranking",
+        reference="https://arxiv.org/abs/2304.03679",
+        dataset={
+            "path": "C-MTEB/T2Reranking",
+            "revision": "76631901a18387f85eaa53e5450019b87ad58ef9",
+        },
+        type="Reranking",
+        category="s2s",
+        modalities=["text"],
+        eval_splits=["dev"],
+        eval_langs=["cmn-Hans"],
+        main_score="map",
+        date=None,
+        form=None,
+        domains=None,
+        task_subtypes=None,
+        license=None,
+        annotations_creators=None,
+        dialect=None,
+        sample_creation=None,
+        bibtex_citation="""@misc{xie2023t2ranking,
+      title={T2Ranking: A large-scale Chinese Benchmark for Passage Ranking}, 
+      author={Xiaohui Xie and Qian Dong and Bingning Wang and Feiyang Lv and Ting Yao and Weinan Gan and Zhijing Wu and Xiangsheng Li and Haitao Li and Yiqun Liu and Jin Ma},
+      year={2023},
+      eprint={2304.03679},
+      archivePrefix={arXiv},
+      primaryClass={cs.IR}
+}""",
+        descriptive_stats={"n_samples": None, "avg_character_length": None},
+    )
+
+
+class MMarcoReranking(AbsTaskReranking):
+    metadata = TaskMetadata(
+        name="MMarcoReranking",
+        description="mMARCO is a multilingual version of the MS MARCO passage ranking dataset",
+        reference="https://github.com/unicamp-dl/mMARCO",
+        dataset={
+            "path": "C-MTEB/Mmarco-reranking",
+            "revision": "8e0c766dbe9e16e1d221116a3f36795fbade07f6",
+        },
+        type="Reranking",
+        category="s2s",
+        modalities=["text"],
+        eval_splits=["dev"],
+        eval_langs=["cmn-Hans"],
+        main_score="map",
+        date=None,
+        form=None,
+        domains=None,
+        task_subtypes=None,
+        license=None,
+        annotations_creators=None,
+        dialect=None,
+        sample_creation=None,
+        bibtex_citation="""@misc{bonifacio2021mmarco,
+      title={mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset}, 
+      author={Luiz Henrique Bonifacio and Vitor Jeronymo and Hugo Queiroz Abonizio and Israel Campiotti and Marzieh Fadaee and  and Roberto Lotufo and Rodrigo Nogueira},
+      year={2021},
+      eprint={2108.13897},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}""",
+        descriptive_stats={"n_samples": None, "avg_character_length": None},
+    )
+
+
+class CMedQAv1(AbsTaskReranking):
+    metadata = TaskMetadata(
+        name="CMedQAv1",
+        description="Chinese community medical question answering",
+        reference="https://github.com/zhangsheng93/cMedQA",
+        dataset={
+            "path": "C-MTEB/CMedQAv1-reranking",
+            "revision": "8d7f1e942507dac42dc58017c1a001c3717da7df",
+        },
+        type="Reranking",
+        category="s2s",
+        modalities=["text"],
+        eval_splits=["test"],
+        eval_langs=["cmn-Hans"],
+        main_score="map",
+        date=("2017-01-01", "2017-07-26"),
+        domains=["Medical", "Written"],
+        task_subtypes=[],
+        license="Not specified",
+        annotations_creators="expert-annotated",
+        dialect=[],
+        sample_creation="found",
+        bibtex_citation="""@article{zhang2017chinese,
+  title={Chinese Medical Question Answer Matching Using End-to-End Character-Level Multi-Scale CNNs},
+  author={Zhang, Sheng and Zhang, Xin and Wang, Hui and Cheng, Jiajun and Li, Pei and Ding, Zhaoyun},
+  journal={Applied Sciences},
+  volume={7},
+  number={8},
+  pages={767},
+  year={2017},
+  publisher={Multidisciplinary Digital Publishing Institute}
+}""",
+        descriptive_stats={
+            "n_samples": {"test": 2000},
+            "avg_character_length": {"test": 165},
+        },
+    )
+
+
+class CMedQAv2(AbsTaskReranking):
+    metadata = TaskMetadata(
+        name="CMedQAv2",
+        description="Chinese community medical question answering",
+        reference="https://github.com/zhangsheng93/cMedQA2",
+        dataset={
+            "path": "C-MTEB/CMedQAv2-reranking",
+            "revision": "23d186750531a14a0357ca22cd92d712fd512ea0",
+        },
+        type="Reranking",
+        category="s2s",
+        modalities=["text"],
+        eval_splits=["test"],
+        eval_langs=["cmn-Hans"],
+        main_score="map",
+        date=None,
+        form=None,
+        domains=None,
+        task_subtypes=None,
+        license=None,
+        annotations_creators=None,
+        dialect=None,
+        sample_creation=None,
+        bibtex_citation="""@ARTICLE{8548603, 
+author={S. Zhang and X. Zhang and H. Wang and L. Guo and S. Liu}, 
+journal={IEEE Access}, 
+title={Multi-Scale Attentive Interaction Networks for Chinese Medical Question Answer Selection}, 
+year={2018}, 
+volume={6}, 
+number={}, 
+pages={74061-74071}, 
+keywords={Biomedical imaging;Data mining;Semantics;Medical services;Feature extraction;Knowledge discovery;Medical question answering;interactive attention;deep learning;deep neural networks}, 
+doi={10.1109/ACCESS.2018.2883637}, 
+ISSN={2169-3536}, 
+month={},}""",
+        descriptive_stats={"n_samples": None, "avg_character_length": None},
+    )