Knowledge-based Word Sense Disambiguation using Topic Models

5 Jan 2018Devendra Singh ChaplotRuslan Salakhutdinov

Word Sense Disambiguation is an open problem in Natural Language Processing which is particularly challenging and useful in the unsupervised setting where all the words in any given text need to be disambiguated without using any labeled data. Typically WSD systems use the sentence or a small window of words around the target word as the context for disambiguation because their computational complexity scales exponentially with the size of the context... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Word Sense Disambiguation Knowledge-based: WSD-TM All 66.9 # 1
Word Sense Disambiguation Knowledge-based: WSD-TM Senseval 2 **69.0** # 5
Word Sense Disambiguation Knowledge-based: WSD-TM Senseval 3 **66.9** # 5
Word Sense Disambiguation Knowledge-based: WSD-TM SemEval 2007 **55.6** # 5
Word Sense Disambiguation Knowledge-based: WSD-TM SemEval 2013 65.3 # 2
Word Sense Disambiguation Knowledge-based: WSD-TM SemEval 2015 69.6 # 1