DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference
This work addresses a core problem in NLP for researchers and practitioners, but it is incremental as it builds on existing LSTM-based methods with enhancements.
The paper tackled the natural language inference task by proposing a dependent reading bidirectional LSTM network to model relationships between premise and hypothesis, achieving new state-of-the-art scores on the Stanford NLI dataset.
We present a novel deep learning architecture to address the natural language inference (NLI) task. Existing approaches mostly rely on simple reading mechanisms for independent encoding of the premise and hypothesis. Instead, we propose a novel dependent reading bidirectional LSTM network (DR-BiLSTM) to efficiently model the relationship between a premise and a hypothesis during encoding and inference. We also introduce a sophisticated ensemble strategy to combine our proposed models, which noticeably improves final predictions. Finally, we demonstrate how the results can be improved further with an additional preprocessing step. Our evaluation shows that DR-BiLSTM obtains the best single model and ensemble model results achieving the new state-of-the-art scores on the Stanford NLI dataset.