word embedding, co-reference resolution, representation learning
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 resolution, the word embedding performance in the word analogy task can be improved by around 1.88%. We find that the words that are names of countries are affected the most, which is as expected.
Tsinghua University Press
Tonglee Chung, Bin Xu, Yongbin Liu et al. How Do Pronouns Affect Word Embedding. Tsinghua Science and Technology 2017, 22(6): 586-594.