Character-level Intra Attention Network for Natural Language Inference
Computation and Language
2017-07-25 v1 Machine Learning
Abstract
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.
Cite
@article{arxiv.1707.07469,
title = {Character-level Intra Attention Network for Natural Language Inference},
author = {Han Yang and Marta R. Costa-jussà and José A. R. Fonollosa},
journal= {arXiv preprint arXiv:1707.07469},
year = {2017}
}
Comments
EMNLP Workshop RepEval 2017: The Second Workshop on Evaluating Vector Space Representations for NLP