Home > Research > Publications & Outputs > Lattice CNNs for Matching Based Chinese Questio...

Research

Associated organisational units

Electronic data

  • paper

    Accepted author manuscript, 1.9 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Lattice CNNs for Matching Based Chinese Question Answering

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Lattice CNNs for Matching Based Chinese Question Answering. / Lai, Yuxuan; Feng, Yansong; Yu, Xiaohan et al.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence . Vol. 33 AAAI, 2019. p. 6634-6641.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Lai, Y, Feng, Y, Yu, X, Wang, Z, Xu, K & Zhao, D 2019, Lattice CNNs for Matching Based Chinese Question Answering. in Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence . vol. 33, AAAI, pp. 6634-6641. https://doi.org/10.1609/aaai.v33i01.33016634

APA

Lai, Y., Feng, Y., Yu, X., Wang, Z., Xu, K., & Zhao, D. (2019). Lattice CNNs for Matching Based Chinese Question Answering. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (Vol. 33, pp. 6634-6641). AAAI. https://doi.org/10.1609/aaai.v33i01.33016634

Vancouver

Lai Y, Feng Y, Yu X, Wang Z, Xu K, Zhao D. Lattice CNNs for Matching Based Chinese Question Answering. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence . Vol. 33. AAAI. 2019. p. 6634-6641 doi: 10.1609/aaai.v33i01.33016634

Author

Lai, Yuxuan ; Feng, Yansong ; Yu, Xiaohan et al. / Lattice CNNs for Matching Based Chinese Question Answering. Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence . Vol. 33 AAAI, 2019. pp. 6634-6641

Bibtex

@inproceedings{329bc465867f4eb5aca8ec0c13c0b78d,
title = "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.",
author = "Yuxuan Lai and Yansong Feng and Xiaohan Yu and Zheng Wang and Kun Xu and Dongyan Zhao",
year = "2019",
month = jul,
day = "17",
doi = "10.1609/aaai.v33i01.33016634",
language = "English",
isbn = "9781577358091",
volume = "33",
pages = "6634--6641",
booktitle = "Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence",
publisher = "AAAI",

}

RIS

TY - GEN

T1 - Lattice CNNs for Matching Based Chinese Question Answering

AU - Lai, Yuxuan

AU - Feng, Yansong

AU - Yu, Xiaohan

AU - Wang, Zheng

AU - Xu, Kun

AU - Zhao, Dongyan

PY - 2019/7/17

Y1 - 2019/7/17

N2 - 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.

AB - 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.

U2 - 10.1609/aaai.v33i01.33016634

DO - 10.1609/aaai.v33i01.33016634

M3 - Conference contribution/Paper

SN - 9781577358091

VL - 33

SP - 6634

EP - 6641

BT - Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence

PB - AAAI

ER -