National High-Tech Research and Development (863) ProgramNational High Technology Research and Development Program of China [2015AA015401]; National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61533018, 61402220]; State Scholarship Fund of CSC [201608430240]; Philosophy and Social Science Foundation of Hunan Province [16YBA323]; Scientific Research Fund of Hunan Provincial Education DepartmentHunan Provincial Education Department [16C1378, 14B153]
机构署名：
本校为通讯机构
院系归属：
计算机科学与技术学院
摘要：
Word embedding has drawn a lot of attention due to its usefulness in many NLP tasks. So far a handful of neural-network based word embedding algorithms have been proposed without considering the effects of pronouns in the training corpus. In this paper, we propose using co-reference resolution to improve the word embedding by extracting better context. We evaluate four word embeddings with considerations of co-reference resolution and compare the quality of word embedding on the task of word analogy and word similarity on multiple data sets. Experiments show that by using co-reference resoluti...
