Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation
arXiv:1904.03799 · doi:10.21437/Interspeech.2019-1858
Abstract
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.
arXiv comment5 pages, 2 figures, accepted to INTERSPEECH 2019
References in corpus (6)
- Efficient Estimation of Word Representations in Vector Space
- Recurrent Neural Network Regularization
- Character-Aware Neural Language Models
- Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation
- Learning to Compute Word Embeddings On the Fly
- Unsupervised and Efficient Vocabulary Expansion for Recurrent Neural Network Language Models in ASR
Cited by in corpus (4)
- Taking Notes on the Fly Helps BERT Pre-training
- Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid ASR Systems
- Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems
- Enriching Under-Represented Named-Entities To Improve Speech Recognition Performance