You Shall Know the Most Frequent Sense by the Company it Keeps
Computation and Language
2019-02-18 v3
Abstract
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.
Keywords
Cite
@article{arxiv.1808.06729,
title = {You Shall Know the Most Frequent Sense by the Company it Keeps},
author = {Bradley Hauer and Yixing Luan and Grzegorz Kondrak},
journal= {arXiv preprint arXiv:1808.06729},
year = {2019}
}
Comments
Updated to reflect the camera-ready version accepted to ICSC 2019