Poster – Paper 504

Investigating Stroke-Level Information for Learning Chinese Word Embeddings Shaosheng Cao, Wei Lu, Jun Zhou and Xiaolong Li Poster October 23, 2017, Poster and Demo Reception, 18:30-21:20 Festsaal 1 Download paper (preprint)

Abstract

We propose a novel method for learning Chinese word embeddings. Different from previous approaches, we investigate the effectiveness of the Chinese stroke-level information when learning Chinese word embeddings. Empirically, our model consistently outperforms several state-of-the-art methods, including skipgram, cbow, GloVe and CWE, on the standard word similarity and word analogy tasks.