Multi-turn Inference Matching Network for Natural Language Inference
arXiv:1901.02222 · doi:10.1007/978-3-319-99501-4_11
Abstract
Natural Language Inference (NLI) is a fundamental and challenging task in Natural Language Processing (NLP). Most existing methods only apply one-pass inference process on a mixed matching feature, which is a concatenation of different matching features between a premise and a hypothesis. In this paper, we propose a new model called Multi-turn Inference Matching Network (MIMN) to perform multi-turn inference on different matching features. In each turn, the model focuses on one particular matching feature instead of the mixed matching feature. To enhance the interaction between different matching features, a memory component is employed to store the history inference information. The inference of each turn is performed on the current matching feature and the memory. We conduct experiments on three different NLI datasets. The experimental results show that our model outperforms or achieves the state-of-the-art performance on all the three datasets.
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Neural Machine Translation by Jointly Learning to Align and Translate
- TensorFlow: A system for large-scale machine learning
- Enhanced LSTM for Natural Language Inference
- Reasoning about Entailment with Neural Attention
- Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention
- Natural Language Inference over Interaction Space
- DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
- A Compare-Aggregate Model for Matching Text Sequences
- Modelling Interaction of Sentence Pair with coupled-LSTMs
- Natural Language Inference from Multiple Premises