{"url":"/task/word-alignment","name":"Word Alignment","slug":"word-alignment","description_markdown":"**Word Alignment** is the task of finding the correspondence between source and target words in a pair of sentences that are translations of each other.\r\n\r\n\r\n<span class=\"description-source\">Source: [Neural Network-based Word Alignment through Score Aggregation ](https://arxiv.org/abs/1606.09560)</span>","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":551,"papers_with_code":92,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"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":4,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/word-alignment-on-en-es","slug":"word-alignment-on-en-es","dataset":"en-es","dataset_url":null,"rows_in_archive":2,"metrics":["P@1"],"first_row_in_archive_order":{"model":"Barycenter Alignment","paper_title":"Unsupervised Multilingual Alignment using Wasserstein Barycenter","paper_url":"/paper/unsupervised-multilingual-alignment-using","paper_date":"2020-01-28","arxiv_id":"2002.00743","code_links":[{"title":"alixxxin/multi-lang","url":"https://github.com/alixxxin/multi-lang"}],"syntology":null}},{"leaderboard":"/sota/word-alignment-on-en-fr","slug":"word-alignment-on-en-fr","dataset":"en-fr","dataset_url":null,"rows_in_archive":2,"metrics":["P@1"],"first_row_in_archive_order":{"model":"Barycenter Alignment","paper_title":"Unsupervised Multilingual Alignment using Wasserstein Barycenter","paper_url":"/paper/unsupervised-multilingual-alignment-using","paper_date":"2020-01-28","arxiv_id":"2002.00743","code_links":[{"title":"alixxxin/multi-lang","url":"https://github.com/alixxxin/multi-lang"}],"syntology":null}},{"leaderboard":"/sota/word-alignment-on-es-en","slug":"word-alignment-on-es-en","dataset":"es-en","dataset_url":null,"rows_in_archive":2,"metrics":["P@1"],"first_row_in_archive_order":{"model":"Barycenter Alignment","paper_title":"Unsupervised Multilingual Alignment using Wasserstein Barycenter","paper_url":"/paper/unsupervised-multilingual-alignment-using","paper_date":"2020-01-28","arxiv_id":"2002.00743","code_links":[{"title":"alixxxin/multi-lang","url":"https://github.com/alixxxin/multi-lang"}],"syntology":null}},{"leaderboard":"/sota/word-alignment-on-fr-en","slug":"word-alignment-on-fr-en","dataset":"fr-en","dataset_url":null,"rows_in_archive":2,"metrics":["P@1"],"first_row_in_archive_order":{"model":"Barycenter Alignment","paper_title":"Unsupervised Multilingual Alignment using Wasserstein Barycenter","paper_url":"/paper/unsupervised-multilingual-alignment-using","paper_date":"2020-01-28","arxiv_id":"2002.00743","code_links":[{"title":"alixxxin/multi-lang","url":"https://github.com/alixxxin/multi-lang"}],"syntology":null}},{"leaderboard":"/sota/word-alignment-on-en-it","slug":"word-alignment-on-en-it","dataset":"en-it","dataset_url":null,"rows_in_archive":1,"metrics":["P@1"],"first_row_in_archive_order":{"model":"Barycenter Alignment","paper_title":"Unsupervised Multilingual Alignment using Wasserstein Barycenter","paper_url":"/paper/unsupervised-multilingual-alignment-using","paper_date":"2020-01-28","arxiv_id":"2002.00743","code_links":[{"title":"alixxxin/multi-lang","url":"https://github.com/alixxxin/multi-lang"}],"syntology":null}},{"leaderboard":"/sota/word-alignment-on-muse-en-de","slug":"word-alignment-on-muse-en-de","dataset":"MUSE en-de","dataset_url":"/dataset/muse","rows_in_archive":1,"metrics":["P@1"],"first_row_in_archive_order":{"model":"Barycenter Alignment","paper_title":"Unsupervised Multilingual Alignment using Wasserstein Barycenter","paper_url":"/paper/unsupervised-multilingual-alignment-using","paper_date":"2020-01-28","arxiv_id":"2002.00743","code_links":[{"title":"alixxxin/multi-lang","url":"https://github.com/alixxxin/multi-lang"}],"syntology":null}},{"leaderboard":"/sota/word-alignment-on-muse-en-pt","slug":"word-alignment-on-muse-en-pt","dataset":"MUSE en-pt","dataset_url":"/dataset/muse","rows_in_archive":1,"metrics":["P@1"],"first_row_in_archive_order":{"model":"Barycenter Alignment","paper_title":"Unsupervised Multilingual Alignment using Wasserstein Barycenter","paper_url":"/paper/unsupervised-multilingual-alignment-using","paper_date":"2020-01-28","arxiv_id":"2002.00743","code_links":[{"title":"alixxxin/multi-lang","url":"https://github.com/alixxxin/multi-lang"}],"syntology":null}}],"datasets":[{"url":"/dataset/wmt-2016-news","name":"WMT 2016 News","full_name":"WMT 2016 News Translation Task","num_papers_in_archive":24},{"url":"/dataset/muse","name":"MUSE","full_name":"MUSE","num_papers_in_archive":2},{"url":"/dataset/bangla-word-analogy-1","name":"Bangla Word Analogy","full_name":"Bangla Word Analogy","num_papers_in_archive":1},{"url":"/dataset/europarl-concodisco-dataset","name":"Europarl ConcoDisco Dataset","full_name":null,"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":92,"tagged_in_all":551,"items":[{"url":"/paper/word-translation-without-parallel-data","title":"Word Translation Without Parallel Data","date":"2017-10-11","arxiv_id":"1710.04087","repositories_listed":20,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":8}},{"url":"/paper/addressing-the-rare-word-problem-in-neural","title":"Addressing the Rare Word Problem in Neural Machine Translation","date":"2014-10-30","arxiv_id":"1410.8206","repositories_listed":5,"syntology":null},{"url":"/paper/portaspeech-portable-and-high-quality","title":"PortaSpeech: Portable and High-Quality Generative Text-to-Speech","date":"2021-09-30","arxiv_id":"2109.15166","repositories_listed":4,"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/sparse-attention-with-linear-units","title":"Sparse Attention with Linear Units","date":"2021-04-14","arxiv_id":"2104.07012","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/word-alignment-by-fine-tuning-embeddings-on","title":"Word Alignment by Fine-tuning Embeddings on Parallel Corpora","date":"2021-01-20","arxiv_id":"2101.08231","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/end-to-end-slot-alignment-and-recognition-for","title":"End-to-End Slot Alignment and Recognition for Cross-Lingual NLU","date":"2020-04-29","arxiv_id":"2004.14353","repositories_listed":3,"syntology":null},{"url":"/paper/simalign-high-quality-word-alignments-without","title":"SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings","date":"2020-04-18","arxiv_id":"2004.08728","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/aligning-and-prompting-everything-all-at-once","title":"Aligning and Prompting Everything All at Once for Universal Visual Perception","date":"2023-12-04","arxiv_id":"2312.02153","repositories_listed":2,"syntology":{"n":14,"n_ran":2,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/wspalign-word-alignment-pre-training-via","title":"WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction","date":"2023-06-09","arxiv_id":"2306.05644","repositories_listed":2,"syntology":null},{"url":"/paper/alignatt-using-attention-based-audio","title":"AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation","date":"2023-05-19","arxiv_id":"2305.11408","repositories_listed":2,"syntology":null},{"url":"/paper/frustratingly-easy-label-projection-for-cross","title":"Frustratingly Easy Label Projection for Cross-lingual Transfer","date":"2022-11-28","arxiv_id":"2211.15613","repositories_listed":2,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/revitalize-region-feature-for-democratizing","title":"Revitalize Region Feature for Democratizing Video-Language Pre-training of Retrieval","date":"2022-03-15","arxiv_id":"2203.07720","repositories_listed":2,"syntology":null},{"url":"/paper/chrentranslate-cherokee-english-machine","title":"ChrEnTranslate: Cherokee-English Machine Translation Demo with Quality Estimation and Corrective Feedback","date":"2021-07-30","arxiv_id":"2107.14800","repositories_listed":2,"syntology":null},{"url":"/paper/the-devil-is-in-the-word-alignment-details-on","title":"The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks","date":"2025-05-15","arxiv_id":"2505.10507","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-often-say-one-thing-and","title":"Large Language Models Often Say One Thing and Do Another","date":"2025-03-10","arxiv_id":"2503.07003","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/binaryalign-word-alignment-as-binary-sequence","title":"BinaryAlign: Word Alignment as Binary Sequence Labeling","date":"2024-07-16","arxiv_id":"2407.12881","repositories_listed":1,"syntology":null},{"url":"/paper/image-text-co-decomposition-for-text","title":"Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation","date":"2024-04-05","arxiv_id":"2404.04231","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-contextualized-phrase-retrieval","title":"Cross-lingual Contextualized Phrase Retrieval","date":"2024-03-25","arxiv_id":"2403.16820","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":11}},{"url":"/paper/multilingual-coreference-resolution-in-low","title":"Multilingual Coreference Resolution in Low-resource South Asian Languages","date":"2024-02-21","arxiv_id":"2402.13571","repositories_listed":1,"syntology":null},{"url":"/paper/self-augmented-in-context-learning-for","title":"Self-Augmented In-Context Learning for Unsupervised Word Translation","date":"2024-02-15","arxiv_id":"2402.10024","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/constrained-decoding-for-cross-lingual-label","title":"Constrained Decoding for Cross-lingual Label Projection","date":"2024-02-05","arxiv_id":"2402.03131","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/salute-the-classic-revisiting-challenges-of","title":"Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models","date":"2024-01-16","arxiv_id":"2401.08350","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":8}},{"url":"/paper/linguistic-aware-patch-slimming-framework-for","title":"Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/codet-co-occurrence-guided-region-word-1","title":"CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection","date":"2023-10-25","arxiv_id":"2310.16667","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":8}},{"url":"/paper/on-bilingual-lexicon-induction-with-large","title":"On Bilingual Lexicon Induction with Large Language Models","date":"2023-10-21","arxiv_id":"2310.13995","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/improving-translation-faithfulness-of-large","title":"Improving Translation Faithfulness of Large Language Models via Augmenting Instructions","date":"2023-08-24","arxiv_id":"2308.12674","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":9}},{"url":"/paper/towards-arabic-multimodal-dataset-for","title":"Towards Arabic Multimodal Dataset for Sentiment Analysis","date":"2023-06-10","arxiv_id":"2306.06322","repositories_listed":1,"syntology":null},{"url":"/paper/unbalanced-optimal-transport-for-unbalanced","title":"Unbalanced Optimal Transport for Unbalanced Word Alignment","date":"2023-06-07","arxiv_id":"2306.04116","repositories_listed":1,"syntology":{"n":14,"n_ran":0,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/do-gpts-produce-less-literal-translations","title":"Do GPTs Produce Less Literal Translations?","date":"2023-05-26","arxiv_id":"2305.16806","repositories_listed":1,"syntology":null},{"url":"/paper/towards-unsupervised-recognition-of-semantic","title":"Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents","date":"2023-05-22","arxiv_id":"2305.13303","repositories_listed":1,"syntology":null}],"syntology_records":16,"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"}}