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 26–50 of 107 papers

TitleStatusHype
Combining Neural Language Models for WordSense Induction—0
Concreteness and Corpora: A Theoretical and Practical Study—0
context2vec: Learning Generic Context Embedding with Bidirectional LSTM—0
Context-Dependent Sense Embedding—0
Cross-lingual WSD for Translation Extraction from Comparable Corpora—0
Automatic Biomedical Term Polysemy Detection—0
A Sense-Based Translation Model for Statistical Machine Translation—0
Duluth: Word Sense Discrimination in the Service of Lexicography—0
Duluth : Word Sense Induction Applied to Web Page Clustering—0
Efficiency in Ambiguity: Two Models of Probabilistic Semantics for Natural Language—0
Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings—0
Evaluating Unsupervised Ensembles when applied to Word Sense Induction—0
A Sense-Topic Model for Word Sense Induction with Unsupervised Data Enrichment—0
Finding Individual Word Sense Changes and their Delay in Appearance—0
From the Culinary to the Political Meaning of ``quenelle'' : Using Topic Models For Identifying Novel Senses (De la quenelle culinaire \`a la quenelle politique : identification de changements s\'emantiques \`a l'aide des Topic Models) [in French]—0
Graph-Based Induction of Word Senses in Croatian—0
BOS at SemEval-2020 Task 1: Word Sense Induction via Lexical Substitution for Lexical Semantic Change Detection—0
How much does a word weigh? Weighting word embeddings for word sense induction—0
Improved Estimation of Entropy for Evaluation of Word Sense Induction—0
Capturing Anomalies in the Choice of Content Words in Compositional Distributional Semantic Space—0
Inducing Word Sense with Automatically Learned Hidden Concepts—0
Large Scale Substitution-based Word Sense Induction—0
Learning Sense-specific Word Embeddings By Exploiting Bilingual Resources—0
Leveraging Lexical Substitutes for Unsupervised Word Sense Induction—0
Mixing in Some Knowledge: Enriched Context Patterns for Bayesian Word Sense Induction—0
Show:102550
← PrevPage 2 of 5Next →

Benchmark Results

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