Wordsim-297

Most word embedding methods take a word as a basic unit and learn embeddings according to words¡¯ external contexts, ignoring the internal structures of words. However, in some languages such as Chinese, a word is usually composed of several characters and contains rich internal information. The semantic meaning of a word is also related to the meanings of its composing characters. Hence, we take Chinese for example, and present a character-enhanced word embedding model (CWE). In order to address the issues of character ambiguity and non-compositional words, we propose multiple-prototype character embeddings and an effective word selection method. We evaluate the effectiveness of CWE on word relatedness computation and analogical reasoning. The results show that CWE outperforms other baseline methods which ignore internal character information. We select a human-annotated corpus with news articles from The People¡¯s Daily for embedding learning. The corpus has 31 million words. The word vocabulary size is 105 thousand and the character vocabulary size is 6 thousand (covering 96% characters in national standard charset GB2312). We set vector dimension as 200 and context window size as 5. For optimization, we use both hierarchical softmax and 10-word negative sampling. We perform word selection for CWE and use pre-trained character embeddings as well. We introduce CBOW, Skip-Gram and GloVe as baseline methods, using the same vector dimension and default parameters. We evaluate the effectiveness of CWE on word relatedness computation and analogical reasoning.