You Shall Know the Most Frequent Sense by the Company it Keeps

08/21/2018

∙

Unsupervised identification of the most frequent sense of a polysemous word is an important semantic task. We introduce two concepts that can benefit MFS detection: companions, which are the most frequently co-occurring words, and the most frequent translation in a bitext. We present two novel methods that incorporate these new concepts, and show that they advance the state of the art on MFS detection.

READ FULL TEXT

You Shall Know the Most Frequent Sense by the Company it Keeps

Probing for Semantic Classes: Diagnosing the Meaning Content of Word Embeddings

Fast Mining of Spatial Frequent Wordset from Social Database

Detecting Wandering Behavior of People with Dementia

Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation

Boosting Applied to Word Sense Disambiguation

Metaphorical Polysemy Detection: Conventional Metaphor meets Word Sense Disambiguation

Frequent or Systematic Changes? discussion on "Detecting possibly frequent change-points: Wild Binary Segmentation 2 and steepest-drop model selection."

You Shall Know the Most Frequent Sense by the Company it Keeps

Related Research

Probing for Semantic Classes: Diagnosing the Meaning Content of Word Embeddings

Fast Mining of Spatial Frequent Wordset from Social Database

Detecting Wandering Behavior of People with Dementia

Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation

Boosting Applied to Word Sense Disambiguation

Metaphorical Polysemy Detection: Conventional Metaphor meets Word Sense Disambiguation

Frequent or Systematic Changes? discussion on "Detecting possibly frequent change-points: Wild Binary Segmentation 2 and steepest-drop model selection."