{"url":"/dataset/word-sense-disambiguation-a-unified","name":"Word Sense Disambiguation: a Unified Evaluation Framework and Empirical Comparison","full_name":null,"description_markdown":"The Evaluation framework of Raganato et al. 2017 includes two training sets (SemCor-Miller et al., 1993- and OMSTI-Taghipour and Ng, 2015-) and five test sets from the Senseval/SemEval series (Edmonds and Cotton, 2001; Snyder and Palmer, 2004; Pradhan et al., 2007; Navigli et al., 2013; Moro and Navigli, 2015), standardized to the same format and sense inventory (i.e. WordNet 3.0).\r\n\r\nTypically, there are two kinds of approach for WSD: supervised (which make use of sense-annotated training data) and knowledge-based (which make use of the properties of lexical resources).\r\n\r\n**Supervised:** The most widely used training corpus used is SemCor, with 226,036 sense annotations from 352 documents manually annotated. All supervised systems in the evaluation table are trained on SemCor. Some supervised methods, particularly neural architectures, usually employ the SemEval 2007 dataset as development set (marked by *). The most usual baseline is the Most Frequent Sense (MFS) heuristic, which selects for each target word the most frequent sense in the training data.\r\n\r\n**Knowledge-based:** Knowledge-based systems usually exploit WordNet or BabelNet as semantic network. The first sense given by the underlying sense inventory (i.e. WordNet 3.0) is included as a baseline.\r\n\r\nDescription from [NLP Progress](http://nlpprogress.com/english/word_sense_disambiguation.html)","description_withheld":null,"homepage":"http://lcl.uniroma1.it/wsdeval/","introduced_date":"2017-04-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/word-sense-disambiguation-a-unified","title":"Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison","first_author":"Aless Raganato","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Word Sense Disambiguation","url":"/task/word-sense-disambiguation","datasets_with_task":"/datasets/task/word-sense-disambiguation"},{"name":"Quantization","url":"/task/quantization","datasets_with_task":"/datasets/task/quantization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Knowledge-based:","Supervised:","Word Sense Disambiguation: a Unified Evaluation Framework and Empirical Comparison"],"data_loaders":[],"num_papers_in_archive":109,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/word-sense-disambiguation-on-supervised","task":"Word Sense Disambiguation","dataset_variant":"Supervised:","rows":27,"metrics":["Senseval 2","Senseval 3","SemEval 2007","SemEval 2013","SemEval 2015"],"first_row_in_archive_order":{"model":"SANDWiCH","paper":"/paper/sandwich-semantical-analysis-of-neighbours","metrics":{"SemEval 2007":"80.9","SemEval 2013":"92.6","SemEval 2015":"91.5","Senseval 2":"87.8","Senseval 3":"85.7"},"code_links":[{"title":"danielguzmanolivares/sandwich","url":"https://github.com/danielguzmanolivares/sandwich"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/word-sense-disambiguation-on-knowledge-based","task":"Word Sense Disambiguation","dataset_variant":"Knowledge-based:","rows":6,"metrics":["All","Senseval 2","Senseval 3","SemEval 2007","SemEval 2013","SemEval 2015"],"first_row_in_archive_order":{"model":"KEF","paper":"/paper/word-sense-disambiguation-a-comprehensive","metrics":{"All":"68.0","SemEval 2007":"56.9","SemEval 2013":"68.4","SemEval 2015":"72.3","Senseval 2":"69.6","Senseval 3":"66.1"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/quantization-on-knowledge-based","task":"Quantization","dataset_variant":"Knowledge-based:","rows":1,"metrics":["All"],"first_row_in_archive_order":{"model":"3DCNN_VIVA_5","paper":"/paper/lossless-compression-for-3dcnns-based-on","metrics":{"All":"84809664"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/sandwich-semantical-analysis-of-neighbours","title":"SANDWiCH: Semantical Analysis of Neighbours for Disambiguating Words in Context ad Hoc","date":"2025-03-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/glossgpt-gpt-for-word-sense-disambiguation","title":"GlossGPT: GPT for Word Sense Disambiguation using Few-shot Chain-of-Thought Prompting","date":"2025-03-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improved-word-sense-disambiguation-with","title":"Improved Word Sense Disambiguation with Enhanced Sense Representations","date":"2021-11-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/consec-word-sense-disambiguation-as","title":"ConSeC: Word Sense Disambiguation as Continuous Sense Comprehension","date":"2021-11-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/esc-redesigning-wsd-with-extractive-sense","title":"ESC: Redesigning WSD with Extractive Sense Comprehension","date":"2021-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/with-more-contexts-comes-better-performance","title":"With More Contexts Comes Better Performance: Contextualized Sense Embeddings for All-Round Word Sense Disambiguation","date":"2020-11-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sparsity-makes-sense-word-sense","title":"Sparsity Makes Sense: Word Sense Disambiguation Using Sparse Contextualized Word Representations","date":"2020-11-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/moving-down-the-long-tail-of-word-sense-1","title":"Moving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders","date":"2020-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/breaking-through-the-80-glass-ceiling-raising","title":"Breaking Through the 80\\% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information","date":"2020-07-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/word-sense-disambiguation-a-comprehensive","title":"Word Sense Disambiguation: A comprehensive knowledge exploitation framework","date":"2020-02-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/lossless-compression-for-3dcnns-based-on","title":"Compressing 3DCNNs Based on Tensor Train Decomposition","date":"2019-12-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improved-word-sense-disambiguation-using-pre","title":"Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations","date":"2019-10-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/glossbert-bert-for-word-sense-disambiguation","title":"GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge","date":"2019-08-20","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/sense-vocabulary-compression-through-the","title":"Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation","date":"2019-05-14","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/improving-the-coverage-and-the-generalization","title":"Improving the Coverage and the Generalization Ability of Neural Word Sense Disambiguation through Hypernymy and Hyponymy Relationships","date":"2018-11-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/incorporating-glosses-into-neural-word-sense","title":"Incorporating Glosses into Neural Word Sense Disambiguation","date":"2018-05-21","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/deep-contextualized-word-representations","title":"Deep contextualized word representations","date":"2018-02-15","rows_on_this_dataset":1,"code_links":46,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":58,"samples_ran":24,"samples_unverified":34,"pointer_only_for_licence":25,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/knowledge-based-word-sense-disambiguation","title":"Knowledge-based Word Sense Disambiguation using Topic Models","date":"2018-01-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/neural-sequence-learning-models-for-word","title":"Neural Sequence Learning Models for Word Sense Disambiguation","date":"2017-09-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/word-sense-disambiguation-a-unified","title":"Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison","date":"2017-04-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/random-walks-for-knowledge-based-word-sense","title":"Random Walks for Knowledge-Based Word Sense Disambiguation","date":"2014-03-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/entity-linking-meets-word-sense","title":"Entity Linking meets Word Sense Disambiguation: a Unified Approach","date":"2014-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":2,"samples_harvested":60,"samples_ran":26,"samples_unverified":34,"pointer_only_for_licence":25,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}