Multiplex Word Embeddings for Selectional Preference Acquisition
This addresses the problem of representing words with varying functional roles in different syntactic relations for natural language processing applications, though it appears incremental as it builds on existing embedding methods.
The paper tackles the limitation of conventional word embeddings that use fixed vectors by proposing multiplex word embeddings with relational dependencies, achieving better performance with only 1/20 of the original embedding size in experiments on selectional preference acquisition and word similarity.
Conventional word embeddings represent words with fixed vectors, which are usually trained based on co-occurrence patterns among words. In doing so, however, the power of such representations is limited, where the same word might be functionalized separately under different syntactic relations. To address this limitation, one solution is to incorporate relational dependencies of different words into their embeddings. Therefore, in this paper, we propose a multiplex word embedding model, which can be easily extended according to various relations among words. As a result, each word has a center embedding to represent its overall semantics, and several relational embeddings to represent its relational dependencies. Compared to existing models, our model can effectively distinguish words with respect to different relations without introducing unnecessary sparseness. Moreover, to accommodate various relations, we use a small dimension for relational embeddings and our model is able to keep their effectiveness. Experiments on selectional preference acquisition and word similarity demonstrate the effectiveness of the proposed model, and a further study of scalability also proves that our embeddings only need 1/20 of the original embedding size to achieve better performance.