Fast Extraction of Word Embedding from Q-contexts
This work addresses efficiency issues in NLP for researchers and practitioners by providing a faster alternative to existing word embedding methods, though it is incremental as it builds on prior context-based approaches.
The paper tackles the computational challenge of pre-training word embeddings for large vocabularies by introducing a method that uses a small fraction of typical contexts (Q-contexts) and mutual information to construct high-quality embeddings with negligible errors, achieving 11-13 times faster runtime than established methods while maintaining comparable performance on downstream NLP tasks.
The notion of word embedding plays a fundamental role in natural language processing (NLP). However, pre-training word embedding for very large-scale vocabulary is computationally challenging for most existing methods. In this work, we show that with merely a small fraction of contexts (Q-contexts)which are typical in the whole corpus (and their mutual information with words), one can construct high-quality word embedding with negligible errors. Mutual information between contexts and words can be encoded canonically as a sampling state, thus, Q-contexts can be fast constructed. Furthermore, we present an efficient and effective WEQ method, which is capable of extracting word embedding directly from these typical contexts. In practical scenarios, our algorithm runs 11$\sim$13 times faster than well-established methods. By comparing with well-known methods such as matrix factorization, word2vec, GloVeand fasttext, we demonstrate that our method achieves comparable performance on a variety of downstream NLP tasks, and in the meanwhile maintains run-time and resource advantages over all these baselines.