Word sense disambiguation
What it is
Most common words have more than one meaning. A «bank» can hold money or a river, to «run» a company is not to run a race. Word sense disambiguation, WSD for short, picks the meaning a word has in its sentence from a list of senses, usually those of a dictionary such as WordNet.
People do it from context without effort; a program has to weigh the other words of the sentence, the topic of the text and how common each sense is. The first sense in the dictionary is a strong baseline that is hard to beat, and the finer the list of senses, the harder the task.
How Mova does it
Mova's world model chooses a WordNet sense from the context: the other words of the sentence, or of the question when there is no sentence, score the candidate senses, and the choice is shown with its score. On its frozen set of 74 questions the core with this selection answered 72 right, none wrong and 2 «unknown».
The papers (22)
- Paraphrasing with Bilingual Parallel Corpora — Colin Bannard, Chris Callison-Burch, 2005 · 534 citations
- I don't believe in word senses — Adam Kilgarriff, 1997 · 396 citations
- Finding Predominant Word Senses in Untagged Text — Diana McCarthy, Rob Koeling, Julie Weeds, John Carroll, 2004 · 310 citations
- WordNet: A Lexical Database for English — George A. Miller, 1994 · 99 citations
- Generationary or «How We Went beyond Word Sense Inventories and Learned to Gloss» — Michele Bevilacqua, Marco Maru, Roberto Navigli, 2020 · 43 citations
- Enhanced UD Dependencies with Neutralized Diathesis Alternation — Marie Candito, Bruno Guillaume, Guy Perrier, Djamé Seddah, 2017 · 18 citations
- The lexical pragmatics of count-mass polysemy — Ingrid L. Falkum, 2017 · 13 citations
- Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change Analysis — Mario Giulianelli, Iris Luden, Raquel Fernandez, Andrey Kutuzov, 2023 · 10 citations
- Large Scale Substitution-based Word Sense Induction — Matan Eyal, Shoval Sadde, Hillel Taub-Tabib, Yoav Goldberg, 2022 · 9 citations
- OntoSem Methods for Processing Semantic Ellipsis — Marjorie McShane, Stephen Beale, Sergei Nirenburg, 2004 · 8 citations
- Developing an interlingual translation lexicon using WordNets and Grammatical Framework — Shafqat Mumtaz Virk, K.V.S. Prasad, Aarne Ranta, Krasimir Angelov, 2014 · 6 citations
- Automatic Identification of Infrequent Word Senses — Diana McCarthy, Rob Koeling, Julie Weeds, John Carroll, 2004 · 6 citations
- Do Large Language Models Understand Word Senses? — Domenico Meconi, Simone Stirpe, Federico Martelli, 2025 · 4 citations
- Word Sense Induction with Attentive Context Clustering — Moshe Stekel, Amos Azaria, Shai Gordin, 2021 · 3 citations
- The Parallel Meaning Bank: A Framework for Semantically Annotating Multiple Languages — Lasha Abzianidze, Rik van Noord, Chunliu Wang, Johan Bos, 2020 · 2 citations
- In the LLM era, Word Sense Induction remains unsolved — Anna Mosolova, Marie Candito, Carlos Ramisch, 2025 · 1 citations
- Crowdsourced Hedge Term Disambiguation — Morgan Ulinski, Julia Hirschberg, 2019 · 1 citations
- English Word Sense Disambiguation in 2026: When the Labels Become the Bottleneck — Vassili Philippov, Amro Salman, Dmitrii Andreev, Penny Hands, 2026
- Unpacking Ambiguity: The Interaction of Polysemous Discourse Markers and Non-DM Signals — Jingni Wu, Amir Zeldes, 2025
- From polysemy to semantic change: remarks on the lexeme miṣwà in Biblical and Mishnaic Hebrew — Romina Vergari, 2021
- MacBERTh: Development and Evaluation of a Historically Pre-trained Language Model for English (1450-1950) — Enrique Manjavacas Arevalo, Lauren Fonteyn, 2021
- Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison — Alessandro Raganato, Jose Camacho-Collados, Roberto Navigli, 2017
This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/topics/word-sense-disambiguation/