SOTAVerified

Word Sense Induction

Word sense induction (WSI) is widely known as the “unsupervised version” of WSD. The problem states as: Given a target word (e.g., “cold”) and a collection of sentences (e.g., “I caught a cold”, “The weather is cold”) that use the word, cluster the sentences according to their different senses/meanings. We do not need to know the sense/meaning of each cluster, but sentences inside a cluster should have used the target words with the same sense.

Description from NLP Progress

Papers

Showing 110 of 107 papers

TitleStatusHype
PolyLM: Learning about Polysemy through Language ModelingCode1
RuDSI: graph-based word sense induction dataset for RussianCode1
AI-KU: Using Substitute Vectors and Co-Occurrence Modeling For Word Sense Induction and Disambiguation0
A State of the Art of Word Sense Induction: A Way Towards Word Sense Disambiguation for Under-Resourced Languages (\'Etat de l'art de l'induction de sens: une voie vers la d\'esambigu\" lexicale pour les langues peu dot\'ees) [in French]0
An Evaluation of Graded Sense Disambiguation using Word Sense Induction0
Applying cross-lingual WSD to wordnet development0
A Sense-Topic Model for Word Sense Induction with Unsupervised Data Enrichment0
A Sense-Based Translation Model for Statistical Machine Translation0
Absinth: A small world approach to word sense induction0
A Comparative Study of Lexical Substitution Approaches based on Neural Language Models0
Show:102550
← PrevPage 1 of 11Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1BERT+DPF-Score71.3Unverified
2AutoSenseF-Score61.7Unverified
3LDAF-Score60.7Unverified
4SE-WSI-fixF-Score55.1Unverified
5BNP-HCF-Score23.1Unverified