Improving Word Vector with Prior Knowledge in Semantic Dictionary

TL;DR

This paper enhances word vector representations by integrating semantic dictionary knowledge and morphological information, improving performance on NLP tasks like temporal expression recognition and NER.

Contribution

It introduces a method to incorporate semantic dictionary data into word vectors, addressing issues with rare and unseen words in NLP applications.

Findings

2.3% improvement over Heidel Time in temporal expression recognition

Significant gains in named entity recognition tasks

Semantic dictionary Hownet effectively computes lexical similarity

Abstract

Using low dimensional vector space to represent words has been very effective in many NLP tasks. However, it doesn't work well when faced with the problem of rare and unseen words. In this paper, we propose to leverage the knowledge in semantic dictionary in combination with some morphological information to build an enhanced vector space. We get an improvement of 2.3% over the state-of-the-art Heidel Time system in temporal expression recognition, and obtain a large gain in other name entity recognition (NER) tasks. The semantic dictionary Hownet alone also shows promising results in computing lexical similarity.