Lattice CNNs for Matching Based Chinese Question Answering

Abstract

Short text matching often faces the challenges that there are great word mismatch and expression diversity between the two texts, which would be further aggravated in languages like Chinese where there is no natural space to segment words explicitly. In this paper, we propose a novel lattice based CNN model (LCNs) to utilize multi-granularity information inherent in the word lattice while maintaining strong ability to deal with the introduced noisy information for matching based question answering in Chinese. We conduct extensive experiments on both document based question answering and knowledge based question answering tasks, and experimental results show that the LCNs models can significantly outperform the state-of-the-art matching models and strong baselines by taking advantages of better ability to distill rich but discriminative information from the word lattice input.

AAAI 2019, code: https://github.com/Erutan-pku/LCN-for-Chinese-QA

References in corpus (6)

• ADADELTA: An Adaptive Learning Rate Method
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• Deep Learning for Answer Sentence Selection
• Lattice-Based Recurrent Neural Network Encoders for Neural Machine Translation
• Improved Neural Relation Detection for Knowledge Base Question Answering
• MatchZoo: A Toolkit for Deep Text Matching

Cited by in corpus (2)

• Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs
• Integrating Relation Constraints with Neural Relation Extractors