{"url":"/task/sentence-retrieval","name":"Sentence Retrieval","slug":"sentence-retrieval","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":82,"papers_with_code":36,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/peerqa","name":"PeerQA","full_name":"","num_papers_in_archive":12},{"url":"/dataset/nitibench","name":"NitiBench","full_name":"","num_papers_in_archive":1},{"url":"/dataset/wangchanx-legal-thaiccl-rag","name":"WangchanX-Legal-ThaiCCL-RAG","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":36,"tagged_in_all":82,"items":[{"url":"/paper/towards-unsupervised-dense-information","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","date":"2021-12-16","arxiv_id":"2112.09118","repositories_listed":6,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/stacked-cross-attention-for-image-text","title":"Stacked Cross Attention for Image-Text Matching","date":"2018-03-21","arxiv_id":"1803.08024","repositories_listed":6,"syntology":{"n":16,"n_ran":7,"n_unverified":9,"n_pointer_only":1}},{"url":"/paper/xtreme-a-massively-multilingual-multi-task","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","date":"2020-03-24","arxiv_id":"2003.11080","repositories_listed":4,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/colbertv2-effective-and-efficient-retrieval","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","date":"2021-12-02","arxiv_id":"2112.01488","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/multimodal-convolutional-neural-networks-for","title":"Multimodal Convolutional Neural Networks for Matching Image and Sentence","date":"2015-04-23","arxiv_id":"1504.06063","repositories_listed":3,"syntology":null},{"url":"/paper/crosslingual-transfer-learning-for-low","title":"Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs","date":"2023-05-22","arxiv_id":"2305.12818","repositories_listed":2,"syntology":null},{"url":"/paper/large-dual-encoders-are-generalizable","title":"Large Dual Encoders Are Generalizable Retrievers","date":"2021-12-15","arxiv_id":"2112.07899","repositories_listed":2,"syntology":null},{"url":"/paper/xtreme-a-massively-multilingual-multi-task-1","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalisation","date":"2020-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/robust-cross-lingual-embeddings-from-parallel-1","title":"Robust Cross-lingual Embeddings from Parallel Sentences","date":"2019-12-28","arxiv_id":"1912.12481","repositories_listed":2,"syntology":null},{"url":"/paper/flickr30k-entities-collecting-region-to","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","date":"2015-05-19","arxiv_id":"1505.04870","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/peerqa-a-scientific-question-answering","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","date":"2025-02-19","arxiv_id":"2502.13668","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/preference-tuning-for-toxicity-mitigation","title":"Preference Tuning For Toxicity Mitigation Generalizes Across Languages","date":"2024-06-23","arxiv_id":"2406.16235","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/3shnet-boosting-image-sentence-retrieval-via","title":"3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting","date":"2024-04-26","arxiv_id":"2404.17273","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/m3-a-multi-task-mixed-objective-learning","title":"M3: A Multi-Task Mixed-Objective Learning Framework for Open-Domain Multi-Hop Dense Sentence Retrieval","date":"2024-03-21","arxiv_id":"2403.14074","repositories_listed":1,"syntology":null},{"url":"/paper/splade-v3-new-baselines-for-splade","title":"SPLADE-v3: New baselines for SPLADE","date":"2024-03-11","arxiv_id":"2403.06789","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/discovering-low-rank-subspaces-for-language","title":"Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations","date":"2024-01-11","arxiv_id":"2401.05792","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":8}},{"url":"/paper/fast-and-accurate-factual-inconsistency","title":"Fast and Accurate Factual Inconsistency Detection Over Long Documents","date":"2023-10-19","arxiv_id":"2310.13189","repositories_listed":1,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":9}},{"url":"/paper/how-to-train-your-dragon-diverse-augmentation","title":"How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval","date":"2023-02-15","arxiv_id":"2302.07452","repositories_listed":1,"syntology":null},{"url":"/paper/contra-con-text-tra-nsformer-for-cross-modal","title":"ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval","date":"2022-10-09","arxiv_id":"2210.04341","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-context-aware-sentence","title":"Unsupervised Context Aware Sentence Representation Pretraining for Multi-lingual Dense Retrieval","date":"2022-06-07","arxiv_id":"2206.03281","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/ems-efficient-and-effective-massively","title":"EMS: Efficient and Effective Massively Multilingual Sentence Embedding Learning","date":"2022-05-31","arxiv_id":"2205.15744","repositories_listed":1,"syntology":null},{"url":"/paper/gere-generative-evidence-retrieval-for-fact","title":"GERE: Generative Evidence Retrieval for Fact Verification","date":"2022-04-12","arxiv_id":"2204.05511","repositories_listed":1,"syntology":null},{"url":"/paper/on-cross-lingual-retrieval-with-multilingual","title":"On Cross-Lingual Retrieval with Multilingual Text Encoders","date":"2021-12-21","arxiv_id":"2112.11031","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-impact-of-evidence-aware","title":"Understanding the Impact of Evidence-Aware Sentence Selection for Fact Checking","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/lightweight-cross-lingual-sentence","title":"Lightweight Cross-Lingual Sentence Representation Learning","date":"2021-05-28","arxiv_id":"2105.13856","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-multilingual-text-encoders-for","title":"Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval","date":"2021-01-21","arxiv_id":"2101.08370","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/similarity-reasoning-and-filtration-for-image","title":"Similarity Reasoning and Filtration for Image-Text Matching","date":"2021-01-05","arxiv_id":"2101.01368","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_unverified":2,"n_pointer_only":12}},{"url":"/paper/indicnlpsuite-monolingual-corpora-evaluation","title":"IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages","date":"2020-11-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/veco-variable-encoder-decoder-pre-training-1","title":"VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation","date":"2020-10-30","arxiv_id":"2010.16046","repositories_listed":1,"syntology":null},{"url":"/paper/fact-extraction-and-verification-the-fever","title":"A Review on Fact Extraction and Verification","date":"2020-10-06","arxiv_id":"2010.03001","repositories_listed":1,"syntology":null}],"syntology_records":14,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}