Browse > Natural Language Processing > Word Sense Induction

Word Sense Induction

10 papers with code · Natural Language Processing

State-of-the-art leaderboards

Trend Dataset Best Method Paper title Paper Code Compare

Greatest papers with code

Breaking Sticks and Ambiguities with Adaptive Skip-gram

25 Feb 2015sbos/AdaGram.jl

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

WORD SENSE INDUCTION

Word Sense Induction with Neural biLM and Symmetric Patterns

EMNLP 2018 asafamr/SymPatternWSI

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.

WORD SENSE INDUCTION

Watset: Automatic Induction of Synsets from a Graph of Synonyms

ACL 2017 dustalov/watset

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

WORD EMBEDDINGS WORD SENSE INDUCTION

AutoSense Model for Word Sense Induction

22 Nov 2018rktamplayo/AutoSense

Thus, we aim to eliminate these requirements and solve the sense granularity problem by proposing AutoSense, a latent variable model based on two observations: (1) senses are represented as a distribution over topics, and (2) senses generate pairings between the target word and its neighboring word.

WORD SENSE INDUCTION

Towards better substitution-based word sense induction

29 May 2019asafamr/bertwsi

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

WORD SENSE INDUCTION

Russian word sense induction by clustering averaged word embeddings

6 May 2018akutuzov/russian_wsi

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

WORD EMBEDDINGS WORD SENSE INDUCTION

Automated WordNet Construction Using Word Embeddings

WS 2017 mkhodak/pawn

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.

INFORMATION RETRIEVAL MACHINE TRANSLATION WORD EMBEDDINGS WORD SENSE INDUCTION