Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation
This addresses a specific bottleneck in language models for speech recognition applications, but is incremental in nature.
The paper tackles the problem of unreliable probability estimates for rare words in neural language models by augmenting word embedding matrices to enrich rare word representations. The method reduces word error rate by 6% relative and improves rare word recognition accuracy by 16% absolute in a speech recognition task.
The neural language models (NLM) achieve strong generalization capability by learning the dense representation of words and using them to estimate probability distribution function. However, learning the representation of rare words is a challenging problem causing the NLM to produce unreliable probability estimates. To address this problem, we propose a method to enrich representations of rare words in pre-trained NLM and consequently improve its probability estimation performance. The proposed method augments the word embedding matrices of pre-trained NLM while keeping other parameters unchanged. Specifically, our method updates the embedding vectors of rare words using embedding vectors of other semantically and syntactically similar words. To evaluate the proposed method, we enrich the rare street names in the pre-trained NLM and use it to rescore 100-best hypotheses output from the Singapore English speech recognition system. The enriched NLM reduces the word error rate by 6% relative and improves the recognition accuracy of the rare words by 16% absolute as compared to the baseline NLM.