Lattice CNNs for Matching Based Chinese Question Answering
This addresses the challenge of Chinese question answering for NLP applications, but it is incremental as it builds on existing matching models with a novel adaptation for Chinese text.
The paper tackles the problem of short text matching in Chinese, where word mismatch and expression diversity are exacerbated by the lack of explicit word segmentation, by proposing a lattice-based CNN model (LCNs) that utilizes multi-granularity information from word lattices while handling noise; experimental results show it significantly outperforms state-of-the-art matching models and baselines on document-based and knowledge-based question answering tasks.
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.