Word Sense Induction

15 papers with code • 2 benchmarks • 2 datasets

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

Most implemented papers

Breaking Sticks and Ambiguities with Adaptive Skip-gram

sbos/AdaGram.jl 25 Feb 2015

Recently proposed Skip-gram model is a powerful method for learning high-dimensional word representations that capture rich semantic relationships between words.

A Simple Approach to Learn Polysemous Word Embeddings

dingwc/multisense 6 Jul 2017

Evaluating these methods is also problematic, as rigorous quantitative evaluations in this space is limited, especially when compared with single-sense embeddings.

Towards better substitution-based word sense induction

asafamr/bertwsi 29 May 2019

Word sense induction (WSI) is the task of unsupervised clustering of word usages within a sentence to distinguish senses.

Automated WordNet Construction Using Word Embeddings

mkhodak/pawn WS 2017

To evaluate our method we construct two 600-word testsets for word-to-synset matching in French and Russian using native speakers and evaluate the performance of our method along with several other recent approaches.

Watset: Automatic Induction of Synsets from a Graph of Synonyms

dustalov/watset ACL 2017

This paper presents a new graph-based approach that induces synsets using synonymy dictionaries and word embeddings.

Improved Word Representation Learning with Sememes

thunlp/SE-WRL ACL 2017

The key idea is to utilize word sememes to capture exact meanings of a word within specific contexts accurately.

Russian word sense induction by clustering averaged word embeddings

akutuzov/russian_wsi 6 May 2018

The paper reports our participation in the shared task on word sense induction and disambiguation for the Russian language (RUSSE-2018).

Word Sense Induction with Neural biLM and Symmetric Patterns

asafamr/SymPatternWSI EMNLP 2018

An established method for Word Sense Induction (WSI) uses a language model to predict probable substitutes for target words, and induces senses by clustering these resulting substitute vectors.