Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks
This addresses a bottleneck in NLP for researchers and practitioners by enabling more efficient and effective word embeddings through syntactic and semantic integration.
The paper tackles the problem of vocabulary explosion when incorporating syntactic context in word embeddings by proposing SynGCN, a Graph Convolution-based method that uses dependency context without increasing vocabulary size, achieving state-of-the-art performance on various NLP tasks and showing advantages when combined with ELMo.
Word embeddings have been widely adopted across several NLP applications. Most existing word embedding methods utilize sequential context of a word to learn its embedding. While there have been some attempts at utilizing syntactic context of a word, such methods result in an explosion of the vocabulary size. In this paper, we overcome this problem by proposing SynGCN, a flexible Graph Convolution based method for learning word embeddings. SynGCN utilizes the dependency context of a word without increasing the vocabulary size. Word embeddings learned by SynGCN outperform existing methods on various intrinsic and extrinsic tasks and provide an advantage when used with ELMo. We also propose SemGCN, an effective framework for incorporating diverse semantic knowledge for further enhancing learned word representations. We make the source code of both models available to encourage reproducible research.