natural-language-processing
Word Sense Induction
3260 papers • 126 benchmarks • 313 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
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in word-sense-induction
Trend
Dataset
Best Model
Actions
SemEval 2010 WSI
SemEval 2010 WSI
Libraries
iUse these libraries to find word-sense-induction models and implementations
Datasets
Subtasks
No subtasks available.
Most implemented papers
A Simple Approach to Learn Polysemous Word Embeddings
Yifan Sun, Nikhil S. Rao, Weicong Ding•Wed Jul 05 2017
This paper proposes a simple method to learn a word representation, given any context, that only requires learning the usual single sense representation, and coefficients that can be learnt via a single pass over the data.
9