中文旅游问题匹配的目标是发现两个相似的问题,然而,在自然语言字面表达中存在多样性,且一个旅游问题通常又包括多个方面信息。因此,采用单一的相似度计算方法将导致信息获取不够完整、有用信息丢失、问题匹配不准确等问题。该文探讨利用答案作为辅助信息,通过多种句子相似度函数,抽取问题中不同方面的信息,生成不同的句子相似度向量表示,以增强句子间的关系。在此基础上,设计一个GRU融合层,使不同方面的信息进行融合,构建一个融合多种句子相似度函数的注意力网络的相似旅游问题识别模型。在旅游问答数据集的实验表明,该文方法提升了相似旅游问题识别任务的性能。
Abstract
Chinese tourism question identification is to detect two similar questions. To deal with the diversity in natural language expression and the complex information related in a tourism question, this paper proposes a question identification model based on attention neural network to capture the sentence similarity in multiple aspect. Linked by the identical answers, different aspects of question sentences are extracted via various similarities metrics. Then a GRU fusion layer is designed to fuse different aspects of information. The experimental results show that the proposed method improves the performance of similar question identification tasks on the tourism question and answer data sets.
关键词
句子表示 /
相似度函数 /
问题识别 /
问答
{{custom_keyword}} /
Key words
sentence expression /
similarity function /
question identification /
question and answer
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] STEPHEN E R, STEVE W, SUSAN J, et al. Okapi at TREC-3[C]//Proceedings of the 3rd Text Retrieval Conference. NIST, 1995: 109-109.
[2] ZHAI CH X, JOHN L. A study of smoothing methods for language models applied to information retrieval[J]. ACM Transactions on Information Systems, 2004, 22(2): 179-214.
[3] WANG ZH G, WAEL H, RADU F. Bilateral multi-perspective matching for natural language sentences[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence. IJCAI, 2017: 4144-4150.
[4] WANG Z H, FAN Y X, GUO J F, et al. Match2: A matching over matching model for similar question identification[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020: 559-568.
[5] JACOB D, MINGWEI C, KENTON L, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 4171- 4186.
[6] HUANG P, HE X D, GAO J F, et al. Learning deep structured semantic models for web search using click through data[C]//Proceedings of the 22nd ACM International Conference on Information & Knowledge Management. ACM, 2013: 2333-2338.
[7] SHEN Y L, HE X D, GAO J F, et al. A latent semantic model with convolutional-pooling structure for information retrieval[C]//Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management. ACM, 2014: 101-110.
[8] HAMID P, LI D, SHEN Y, et al. Semantic modelling with long-short-term memory for information retrieval[J]. arXiv preprint, 2014, arXiv: 1412.6629.
[9] CHEN Q, ZHU X D, LING ZH H, et al. Enhanced LSTM for natural language inference[J]. arXiv preprint, 2016, arXiv: 1609.06038.
[10] YANG R Q, ZHANG J H, GAO X, et al. Simple and effective text matching with richer alignment features[J]. arXiv preprint, 2019, arXiv: 1908.00300.
[11] LIANG D, ZHANG F B, ZHANG W D, et al. Adaptive multi-atention network incorporating answer information for duplicate question detection[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019: 95-104.
[12] AISHWARYA A, GANAPATHY S. NATARAJAN L S S, et al. SimsterQ: A similarity based clustering approach to opinion question answering[C]//Proceedings of the 3rd Workshop on e-Commerce and NLP, 2020: 69-76.
[13] CLARK K, KHANDELWAL U, LEVY O, et al. What does bert look at?: An analysis of BERT's attention[J]. arXiv preprint, 2019, arXiv: 1906.04341.
[14] COENEN A, REIF E, YUAN A, et al. Visualizing and measuring the geometry of BERT[J]. arXiv preprint, 2019, arXiv: 1906.02715.
[15] TIM R, EDWARD G, KARL M H, et al. Reasoning about entailment with neural attention[J]. arXiv preprint, 2015, arXiv: 1509.06664.
[16] HE K M, ZHANG X Y, REN SH Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
[17] LIN M, CHEN Q, SHUICHENG Y. Network in network[J]. arXiv preprint, 2013, arXiv: 1312.4400.
[18] LIU L Y, JIANG H M, HE P CH, et al. On the variance of the adaptive learning rate and beyond[J]. arXiv preprint, 2019, arXiv: 1908.03265.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(62076158,62072294);山西省重点研发计划项目(201803D421024)
{{custom_fund}}
PDF(2328 KB)
