{"type":"ScholarlyArticle","title":"Knowledge-enhanced Hierarchical Attention for Community Question Answering with Multi-task and Adaptive Learning","authors":[{"name":"Min Yang","slug":"min-yang","given":"Min","family":"Yang","affiliation":"Shenzhen Institutes of Advanced Technology , Chinese Academy of Sciences"},{"name":"Lei Chen","slug":"lei-chen","given":"Lei","family":"Chen","affiliation":"Shenzhen Institutes of Advanced Technology , Chinese Academy of Sciences; University of Chinese Academy of Sciences"},{"name":"Xiaojun Chen","slug":"xiaojun-chen","given":"Xiaojun","family":"Chen","affiliation":"Shenzhen University"},{"name":"Qingyao Wu","slug":"qingyao-wu","given":"Qingyao","family":"Wu","affiliation":"South China University of Technology"},{"name":"Wei Zhou","slug":"wei-zhou","given":"Wei","family":"Zhou","affiliation":"Chongqing University"},{"name":"Ying Shen","slug":"ying-shen","given":"Ying","family":"Shen","affiliation":"Peking University Shenzhen Graduate School"}],"abstract":"In this paper, we propose a Knowledge-enhanced Hierarchical Attention for community question answering with Multi-task learning and Adaptive learning (KHAMA). First, we propose a hierarchical attention network to fully fuse knowledge from input documents and knowledge base (KB) by exploiting the semantic compositionality of the input sequences. The external factual knowledge helps recognize background knowledge (entity mentions and their relationships) and eliminate noise information from long documents that have sophisticated syntactic and semantic structures. In addition, we build multiple CQA models with adaptive boosting and then combine these models to learn a more effective and robust CQA system. Further- more, KHAMA is a multi-task learning model. It regards CQA as the primary task and question categorization as the auxiliary task, aiming at learning a category-aware document encoder and enhance the quality of identifying essential information from long questions. Extensive experiments on two benchmarks demonstrate that KHAMA achieves substantial improvements over the compared methods.","doi":"10.24963/ijcai.2019/743","url":"https://ijcai.org/proceedings/2019/743","pdf":"https://ijcai.org/proceedings/2019/0743.pdf","markdown":"https://ijcai.org/proceedings/2019/743.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/743","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Natural Language Processing","track":"Main track","number":743,"pages":{"first":5349,"last":5355},"keywords":["Natural Language Processing: Question Answering","Natural Language Processing: Natural Language Processing","Machine Learning: Deep Learning"],"videos":[],"references":[{"position":1,"raw":"[Bollacker et al., 2008] Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. Freebase: a collaboratively created graph database for structuring human knowledge. In SIGMOD, pages 1247-1250. ACM, 2008.","title":"Freebase: a collaboratively created graph database for structuring human knowledge","authors":"Bollacker","year":"2008","venue":"SIGMOD","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cao et al., 2017] Ziqiang Cao, Wenjie Li, Sujian Li, and Furu Wei. Improving multi-document summarization via text classification. In AAAI, pages 3053-3059, 2017.","title":"Improving multi-document summarization via text classification","authors":"Ziqiang Cao, Wenjie Li, Sujian Li, Furu Wei","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2017] Qin Chen, Qinmin Hu, Jimmy Xiangji Huang, Liang He, and Weijie An. Enhancing recurrent neural networks with positional attention for question an- swering. In SIGIR, pages 993-996. ACM, 2017.","title":"Enhancing recurrent neural networks with positional attention for question answering","authors":"Qin Chen, Qinmin Hu, Jimmy Xiangji Huang, Liang He, Weijie An","year":"2017","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Dos Santos et al., 2016] Cıcero Nogueira Dos Santos, Ming Tan, Bing Xiang, and Bowen Zhou. Attentive pooling net- works. CoRR, abs/1602.03609, 2016.","title":"Attentive pooling networks","authors":"Dos Santos","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Filice et al., 2016] Simone Filice, Danilo Croce, Alessan- dro Moschitti, and Roberto Basili. Kelp at semeval-2016 task 3: Learning semantic relations between questions and answers. In SemEval-2016, pages 1116-1123, 2016.","title":"Kelp at semeval-2016 task 3: Learning semantic relations between questions and answers","authors":"Simone Filice, Danilo Croce, Alessandro Moschitti, Roberto Basili","year":"2016","venue":"SemEval-2016","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Guo et al., 2017] Jiahui Guo, Bin Yue, Guandong Xu, Zhenglu Yang, and Jin-Mao Wei. An enhanced convo- lutional neural network model for answer selection. In WWW, pages 789-790, 2017.","title":"An enhanced convolutional neural network model for answer selection","authors":"Jiahui Guo, Bin Yue, Guandong Xu, Zhenglu Yang, Jin-Mao Wei","year":"2017","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Heilman and Smith, 2010] Michael Heilman and Noah A Smith. Tree edit models for recognizing textual entail- ments, paraphrases, and answers to questions. In NAACL, pages 1011-1019, 2010.","title":"Tree edit models for recognizing textual entailments, paraphrases, and answers to questions","authors":"Smith ; Heilman, Michael Heilman, Noah A Smith","year":"2010","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Lei et al., 2018] Zeyang Lei, Yujiu Yang, and Min Yang. Saan: A sentiment-aware attention network for sentiment analysis. In SIGIR, 2018.","title":"Saan: A sentiment-aware attention network for sentiment analysis","authors":"Lei","year":"2018","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Mikolov et al., 2013] Tomas Mikolov, Kai Chen, Greg Cor- rado, and Jeffrey Dean. Efficient estimation of word rep- resentations in vector space. In ICLR, pages 1-12, 2013.","title":"Efficient estimation of word representations in vector space","authors":"Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean","year":"2013","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Nakov et al., 2015] Preslav Nakov, Lluís Màrquez, Walid Magdy, Alessandro Moschitti, Jim Glass, and Bilal Ran- deree. SemEval-2015 task 3: Answer selection in com- munity question answering. In SemEval 2015, pages 269- 281, 2015.","title":"SemEval-2015 task 3: Answer selection in community question answering","authors":"Nakov","year":"2015","venue":"SemEval 2015","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Nakov et al., 2017] Preslav Nakov, Doris Hoogeveen, Lluís Màrquez, Alessandro Moschitti, Hamdy Mubarak, Timo- thy Baldwin, and Karin Verspoor. SemEval-2017 task 3: Community question answering. In SemEval-2017, pages 27-48, 2017.","title":"SemEval-2017 task 3: Community question answering","authors":"Nakov","year":"2017","venue":"SemEval-2017","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Perozzi et al., 2014] Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. Deepwalk: online learning of social rep- resentations. In SIGKDD, pages 701-710, 2014.","title":"Deepwalk: online learning of social representations","authors":"Bryan Perozzi, Rami Al-Rfou, Steven Skiena","year":"2014","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Peters et al., 2018] Matthew E Peters, Mark Neumann, Mo- hit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. Deep contextualized word repre- sentations. NAACL, 2018.","title":"Deep contextualized word representations","authors":"Mark Matthew E Peters, Mohit Neumann, Matt Iyyer, Christopher Gardner, Kenton Clark, Luke Lee, Zettlemoyer","year":"2018","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Qiu and Huang, 2015] Xipeng Qiu and Xuanjing Huang. Convolutional neural tensor network architecture for community-based question answering. In IJCAI, 2015.","title":"Convolutional neural tensor network architecture for community-based question answering","authors":"Huang Qiu, Xipeng Qiu, Xuanjing Huang","year":"2015","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/188"},{"position":15,"raw":"[Shen et al., 2018] Ying Shen, Yang Deng, Min Yang, Yaliang Li, Nan Du, Wei Fan, and Kai Lei. Knowledge- aware attentive neural network for ranking question an- swer pairs. In SIGIR, pages 901-904, 2018.","title":"Knowledgeaware attentive neural network for ranking question answer pairs","authors":"Ying Shen, Yang Deng, Min Yang, Yaliang Li, Nan Du, Wei Fan, Kai Lei","year":"2018","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Surdeanu et al., 2008] Mihai Surdeanu, Massimiliano Cia- ramita, and Hugo Zaragoza. Learning to rank answers on large online qa collections. ACL, pages 719-727, 2008.","title":"Learning to rank answers on large online qa collections","authors":"Mihai Surdeanu, Massimiliano Ciaramita, Hugo Zaragoza","year":"2008","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Tan et al., 2016a] Ming Tan, Cicero Dos Santos, Bing Xi- ang, and Bowen Zhou. Improved representation learning for question answer matching. In ACL, pages 464-473, 2016.","title":"Improved representation learning for question answer matching","authors":"Tan","year":"2016","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Tan et al., 2016b] Ming Tan, Cicero dos Santos, Bing Xi- ang, and Bowen Zhou. Lstm-based deep learning models for non-factoid answer selection. In ICLR, 2016.","title":"Lstm-based deep learning models for non-factoid answer selection","authors":"Tan","year":"2016","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Tay et al., 2017] Yi Tay, Minh C Phan, Luu Anh Tuan, and Siu Cheung Hui. Learning to rank question answer pairs with holographic dual lstm architecture. In SIGIR, 2017.","title":"Learning to rank question answer pairs with holographic dual lstm architecture","authors":"Yi Tay, Minh C Phan, Luu, Anh Tuan, Siu Cheung, Hui","year":"2017","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tay et al., 2018] Yi Tay, Luu Anh Tuan, and Siu Cheung Hui. Cross temporal recurrent networks for ranking ques- tion answer pairs. In AAAI, 2018.","title":"Cross temporal recurrent networks for ranking question answer pairs","authors":"Yi Tay, Anh Luu, Siu Tuan, Hui Cheung","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tran et al., 2015] Quan Hung Tran, Vu Tran, Tu Vu, Minh Nguyen, and Son Bao Pham. Jaist: Combining multiple features for answer selection in community question an- swering. In SemEval 2015, pages 215-219, 2015.","title":"Jaist: Combining multiple features for answer selection in community question answering","authors":"Hung Quan, Vu Tran, Tu Tran, Minh Vu, Son Bao Nguyen, Pham","year":"2015","venue":"SemEval 2015","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang and Nyberg, 2015] Di Wang and Eric Nyberg. A long short-term memory model for answer sentence selection in question answering. In ACL, 2015.","title":"A long short-term memory model for answer sentence selection in question answering","authors":"Di Wang, Eric Nyberg","year":"2015","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2017] Guoshun Wu, Yixuan Sheng, Man Lan, and Yuanbin Wu. Ecnu at semeval-2017 task 3: Using tra- ditional and deep learning methods to address community question answering task. In SemEval-2017, 2017.","title":"Ecnu at semeval-2017 task 3: Using traditional and deep learning methods to address community question answering task","authors":"Wu","year":"2017","venue":"SemEval-2017","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xiang et al., 2016] Yang Xiang, Xiaoqiang Zhou, Qingcai Chen, Zhihui Zheng, Buzhou Tang, Xiaolong Wang, and Yang Qin. Incorporating label dependency for answer quality tagging in community question answering via cnn- lstm-crf. In COLING, pages 1231-1241, 2016.","title":"Incorporating label dependency for answer quality tagging in community question answering via cnnlstm-crf","authors":"Yang Xiang, Xiaoqiang Zhou, Qingcai Chen, Zhihui Zheng, Buzhou Tang, Xiaolong Wang, Yang Qin","year":"2016","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yang et al., 2018] Dongdong Yang, Senzhang Wang, and Zhoujun Li. Ensemble neural relation extraction with adaptive boosting. In IJCAI, 2018.","title":"Ensemble neural relation extraction with adaptive boosting","authors":"Dongdong Yang, Senzhang Wang, Zhoujun Li","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/630"},{"position":26,"raw":"[Yang et al., 2019] Min Yang, Wenting Tu, Qiang Qu, Wei Zhou, Qiao Liu, and Jia Zhu. Advanced community question answering by leveraging external knowledge and multi-task learning. Knowledge-Based Systems, 2019.","title":"Advanced community question answering by leveraging external knowledge and multi-task learning","authors":"Yang","year":"2019","venue":"Knowledge-Based Systems","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yin et al., 2015] Wenpeng Yin, Hinrich Schütze, Bing Xi- ang, and Bowen Zhou. Abcnn: Attention-based convolu- tional neural network for modeling sentence pairs. Com- puter Science, 2015.","title":"Abcnn: Attention-based convolutional neural network for modeling sentence pairs","authors":"Yin","year":"2015","venue":"Computer Science","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Yu et al., 2014] Lei Yu, Karl Moritz Hermann, Phil Blun- som, and Stephen Pulman. Deep learning for answer sen- tence selection. In Proceedings of Deep Learning and Rep- resentation Learning Workshop. NIPS, 2014.","title":"Deep learning for answer sentence selection","authors":"Lei Yu, Karl Moritz Hermann, Phil Blunsom, Stephen Pulman","year":"2014","venue":"Proceedings of Deep Learning and Representation Learning Workshop. NIPS","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhang et al., 2017] Xiaodong Zhang, Sujian Li, Lei Sha, and Houfeng Wang. Attentive interactive neural networks for answer selection in community question answering. In AAAI, pages 3525-3531, 2017.","title":"Attentive interactive neural networks for answer selection in community question answering","authors":"Xiaodong Zhang, Sujian Li, Lei Sha, Houfeng Wang","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}