Suffix Bidirectional Long Short-Term Memory

Recurrent neural networks have become ubiquitous in computing representations of sequential data, especially textual data in natural language processing. In particular, Bidirectional LSTMs are at the heart of several neural models achieving state-of-the-art performance in a wide variety of tasks in NLP. We propose a general and effective improvement to the BiLSTM model which encodes each suffix and prefix of a sequence of tokens in both forward and reverse directions. We call our model Suffix BiLSTM or SuBiLSTM. Using an extensive set of experiments, we demonstrate that using SuBiLSTM instead of a BiLSTM in existing base models leads to improvements in performance in learning general sentence representations, text classification, textual entailment and named entity recognition. We achieve new state-of-the-art results for fine-grained sentiment classification and question classification using SuBiLSTM.