目前,关于问答的大部分研究都是面向正式文本的问答对。然而,与以往研究不同的是,该文关注于社会媒体上存在的非正式文本问答对。非正式文本会存在问题文本里包含多个问题以及回答文本里包含多个回答的情况。针对该情况,我们提出了一个新的任务: 问答配对,即对问题文本的每个问题,从答案文本中找到和该问题相关的句子。首先,我们从产品问答网站上收集了大规模非正式文本问答对,并在此基础上创建了一个产品问答配对语料库。其次,为了解决非正式文本中存在的噪声问题,提出了一种基于注意力机制的上下文相关的问答配对方法。实验结果表明,该文提出的方法能有效地提升非正式文本的问答配对的性能。
Abstract
To deal with the informal texts in social media where a question text has several questions and the answer text has several answers, we propose a new task named QA pairing, which means to identify the answer sentence(s) for each question. First, we build a novel QA pairing corpus with informal text, which is collected from a product reviewing website. Then, in order to resolve the noises in informal text, we propose a novel QA pairing approach, namely contextual QA pairing method based on attention network. Empirical studied demonstrate the effectiveness of the proposed approach to QA pairing.
关键词
非正式文本 /
问答配对 /
上下文相关 /
注意力机制
{{custom_keyword}} /
Key words
informal text /
QA pairing /
contextual /
attention mechanism
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Wang M,Manning C D. Probabilistic tree-edit models with structured latent variables for textual entailment and question answering[C]//Proceedings of the 23rd International Conference on Computational Linguistics,2010:1164-1172.
[2] Yih W,et al. Question answering using enhanced lexical semantic models[C]//Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics,2013:1744-1753.
[3] Yao X,Dueme B B. Answer extraction as sequence tagging with tree edit distance[C]//Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,2013:858-867.
[4] Severyn A,Moschitti A. Automatic feature engineering for answer selection and extraction[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing,2013:458-467.
[5] Feng M,et al. Applying deep learning to answer selection:A study and an open task[C]//Proceedings of IEEE Automatic Speech Recognition & Understanding,2015:813-820.
[6] Yang Y,Yih W,Meek C. WikiQA:A challenge dataset for open-domain question answering[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing,2015:2013-2018.
[7] Tan M,et al. Improved representation learning for question answer matching[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics,2016:464-473.
[8] Yin W,et al. ABCNN:Attention-based convolutional neural network for modeling sentence pairs[J]//Transactions of the Association for Computational Linguistics,2016,3(1):259-272.
[9] Wang S,Jiang J. A compare-aggregate model for matching text sequences[C]//Proceedings of the 5th International Conference on Learning Representations,2017:120-130.
[10] Wang Z,Hamza W,Florian R. Bilateral multi-perspective matching for natural language sentences[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence,2017:4144-4150.
[11] He H,Lin J. Pairwise word interaction modeling with deep neural networks for semantic similarity measurement[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,2016:937-948.
[12] Kingma D P,Ba J. Adam:A method for stochastic optimization[C]//Proceedings of the 3rd International Conference on Learning Representation,2015:1-15.
[13] 刘挺,车万翔,李生.基于最大熵分类器的语义角色标注[J].软件学报,2007,18(3):565-573.
[14] Bowman S R,et al. A large annotated corpus for learning natural language inference[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing,2015:632-642.
[15] Zhang B,et al. Shallow convolutional neural network for implicit discourse relation recognition[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing,2015:2230-2235.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61331011,61672366)
{{custom_fund}}
PDF(5373 KB)
