Improving Word Vector with Prior Knowledge in Semantic Dictionary
This addresses rare/unseen word issues in NLP tasks like NER, though it appears incremental as it builds on existing word vector methods.
The paper tackles the problem of rare and unseen words in word vector representations by leveraging semantic dictionary knowledge and morphological information, resulting in a 2.3% improvement over the state-of-the-art Heidel Time system in temporal expression recognition and significant gains in other NER tasks.
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.