Character-level Intra Attention Network for Natural Language Inference
This work addresses natural language inference, a key problem in language understanding, but appears incremental as it builds on existing neural network approaches with specific modifications.
The paper tackles natural language inference by proposing a Character-level Intra Attention Network (CIAN), which uses character-level convolutional networks and intra attention to achieve improved results on the MNLI corpus.
Natural language inference (NLI) is a central problem in language understanding. End-to-end artificial neural networks have reached state-of-the-art performance in NLI field recently. In this paper, we propose Character-level Intra Attention Network (CIAN) for the NLI task. In our model, we use the character-level convolutional network to replace the standard word embedding layer, and we use the intra attention to capture the intra-sentence semantics. The proposed CIAN model provides improved results based on a newly published MNLI corpus.