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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 107 papers

TitleStatusHype
Vector representations of text data in deep learning—0
AutoSense Model for Word Sense InductionCode0
Word Sense Induction using Knowledge Embeddings—0
Disambiguated skip-gram model—0
Word Sense Induction with Neural biLM and Symmetric PatternsCode0
How much does a word weigh? Weighting word embeddings for word sense induction—0
Russian word sense induction by clustering averaged word embeddingsCode0
The brWaC Corpus: A New Open Resource for Brazilian Portuguese—0
Retrofitting Word Representations for Unsupervised Sense Aware Word Similarities—0
Leveraging Lexical Substitutes for Unsupervised Word Sense Induction—0
Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings—0
Word sense induction using word embeddings and community detection in complex networks—0
RUSSE'2018: A Shared Task on Word Sense Induction for the Russian Language—0
On Modeling Sense Relatedness in Multi-prototype Word Embedding—0
Finding Individual Word Sense Changes and their Delay in Appearance—0
Parsing with Context Embeddings—0
A Simple Approach to Learn Polysemous Word EmbeddingsCode0
Improved Word Representation Learning with SememesCode0
Using Pseudowords for Algorithm Comparison: An Evaluation Framework for Graph-based Word Sense Induction—0
Watset: Automatic Induction of Synsets from a Graph of SynonymsCode0
Automated WordNet Construction Using Word EmbeddingsCode0
Supervised and unsupervised approaches to measuring usage similarity—0
Unsupervised Does Not Mean Uninterpretable: The Case for Word Sense Induction and Disambiguation—0
Structured Generative Models of Continuous Features for Word Sense Induction—0
Context-Dependent Sense Embedding—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