计算机科学 ›› 2021, Vol. 48 ›› Issue (12): 286-296.doi: 10.11896/jsjkx.210100209
黄欣1, 雷刚1, 曹远龙1, 陆明名2
HUANG Xin1, LEI Gang1, CAO Yuan-long1, LU Ming-ming2
摘要: 相比传统的一问一答,交互式问答增加了对话上下文和背景等信息,这为理解用户输入和推理答案带来了新的挑战。首先,用户输入不再局限于问题,还可以是告知问题细节、反馈答案可行与否等带有意图的语句,因此需要理解对话中每个语句的意图。其次,交互式问答允许多个角色同时参与一个问题的讨论,为每个角色生成个性化的答案,因此需要理解对话中存在的角色。再次,当交互式问答围绕一段背景文本展开时,需要理解这段背景文本,并从中抽取出问题的答案。文章对交互式问答的发展及前沿动态进行了调研,分别对无背景交互式问答、有背景交互式问答以及迁移学习在交互式问答的应用3个子方向的新方法和新发现进行了介绍,并对交互式问答的研究前景进行了分析和展望。
中图分类号:
[1]SARIKAYA R.The technology behind personal digital assis- tants:An overview of the system architecture and key components[J].IEEE Signal Processing Magazine,2017,34(1):67-81. [2]REDDY S,CHEN D,MANNING C D.CoQA:A Conversational Question Answering Challenge[J].Transactions of the Association for Computational Linguistics,2019,7:249-266. [3]LI X,CHEN Y N,LI L,et al.End-to-End Task-Completion Neural Dialogue Systems[C]//Proceedings of the Eighth International Joint Conference on Natural Language Processing.2017:733-743. [4]WEI Z,LIU Q,PENG B,et al.Task-oriented dialogue system for automatic diagnosis[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.2018:201-207. [5]SERBAN I V,SORDONI A,BENGIO Y,et al.Building end-to-end dialogue systems using generative hierarchical neural network models[C]//Thirtieth AAAI Conference on Artificial Intelligence.2016. [6]YAN R,SONG Y,WU H.Learning to respond with deep neural networks for retrieval-based human-computer conversation system[C]//Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval.2016:55-64. [7]WANG B X.Research on semantic mining for online community Q&A pairs [D].Harbin:Harbin Institute of Technology,2017. [8]ZHOU X Q.Research on interactive question answering tech- nology based on deep learning [D].Harbin:Harbin Institute of Technology,2017. [9]MITCHELL T M,BETTERIDGE J,CARLSON A,et al.Populating the semantic web by macro-reading internet text[C]//International Semantic Web Conference.2009:998-1002. [10]LOWE R,POW N,SERBAN I V,et al.The Ubuntu Dialogue Corpus:A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems[C]//Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue.2015:285-294. [11]QU C,YANG L,CROFT W B,et al.Analyzing and characterizing user intent in information seeking conversations[C]//The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval.2018:989-992. [12]ALIANNEJADI M,ZAMANI H,CRESTANI F,et al.Asking clarifying questions in open-domain information-seeking conversations[C]//Proceedings of the 42nd International ACMSIGIR Conference on Research and Development in Information Retrieval.2019:475-484. [13]WANG S,JIANG J.A compare-aggregate model for matching text sequences[C]//5th International Conference on Learning Representations(ICLR).2019. [14]SUTSKEVER I,VINYALS O,LE Q V.Sequence to sequence learning with neural networks[C]//Advances in Neural Information Processing Systems.2014:3104-3112. [15]WANG S,JIANG J.Learning Natural Language Inference with LSTM[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2016:1442-1451. [16]SCHUSTER M,PALIWAL K K.Bidirectional recurrent neural networks[J].IEEE Transactions on Signal Processing,1997,45(11):2673-2681. [17]LECUN Y,BOSER B,DENKER J S,et al.Backpropagation applied to handwritten zip code recognition[J].Neural Computation,1989,1(4):541-551. [18]ZHOU X,DONG D,WU H,et al.Multi-view response selection for human-computer conversation[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Proces-sing.2016:372-381. [19]WU Y,WU W,XING C,et al.Sequential Matching Network:A New Architecture for Multiturn Response Selection in Retrieval-Based Chatbots[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.2017:496-505. [20]VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]//Advances in Neural Information Processing Systems.2017:5998-6008. [21]BAHDANAU D,CHO K,BENGIO Y.Neural machine translation by jointly learning to align and translate[C]//3rd International Conference on Learning Representations(ICLR).2015. [22]ZHOU X,LI L,DONG D,et al.Multi-turn response selection for chatbots with deep attention matching network[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.2018:1118-1127. [23]ZHANG Z,LI J,ZHU P,et al.Modeling Multi-turn Conversation with Deep Utterance Aggregation[C]//Proceedings of the 27th International Conference on Computational Linguistics.2018:3740-3752. [24]ZONG C Q.Statistical natural language processing(Second Edition) [M].Beijing:Tsinghua University Press,2013:83-85. [25]TAO C,WU W,XU C,et al.Multi-representation fusion net- work for multi-turn response selection in retrieval-based chatbots[C]//Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining.2019:267-275. [26]MAO G,SU J,YU S,et al.Multi-Turn Response Selection for Chatbots With Hierarchical Aggregation Network of Multi-Representation[J].IEEE Access,2019,7:111736-111745. [27]TAO C,WU W,XU C,et al.One time of interaction may not be enough:Go deep with an interaction-over-interaction network for response selection in dialogues[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.2019:1-11. [28]LOWE R T,POW N,SERBAN I V,et al.Training end-to-end dialogue systems with the ubuntu dialogue corpus[J].Dialogue &Discourse,2017,8(1):31-65. [29]GUNASEKARA C,KUMMERFELD J K,POLYMENAKOS L,et al.Dstc7 task 1:Noetic end-to-end response selection[C]//Proceedings of the First Workshop on NLP for Conversational AI.2019:60-67. [30]CHEN Q,WANG W.Sequential attention-based network for noetic end-to-end response selection[J].arXiv:1901.02609,2019. [31]GU J C,LING Z H,RUAN Y P,et al.Building sequential infe- rence models for end-to-end response selection[J].arXiv:1812.00686,2018. [32]SUN S,TAM Y C,CAO J,et al.End-to-end Gated Self-attentive Memory Network for Dialog Response Selection[C]//Workshop on DSTC7.2019. [33]SUKHBAATAR S,WESTON J,FERGUS R,et al.End-to-end memory networks[C]//Advances in Neural Information Processing Systems.2015:2440-2448. [34]CHIANG T R,HUANG C W,SU S Y,et al.Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer[J].arXiv:1903.08953,2019. [35]LU J,XIE Z,LING G,et al.Spatio-Temporal Matching Net- work for Multi-Turn Responses Selection in Retrieval-Based Chatbots[C]//Workshop on DSTC7.2019. [36]WHANG T,LEE D,LEE C,et al.Enhanced Sequential Representation Augmented with Utterance-level Attention for Response Selection[C]//Workshop on DSTC7.2019. [37]SERBAN I V,SORDONI A,LOWE R,et al.A hierarchical latent variable encoder-decoder model for generating dialogues[C]//Thirty-First AAAI Conference on Artificial Intelligence.2017. [38]XING C,WU W,WU Y,et al.Topic aware neural response ge- neration[C]//Thirty-First AAAI Conference on Artificial Intelligence.2017. [39]WU Y,WU W,YANG D,et al.Neural response generation with dynamic vocabularies[C]//Thirty-Second AAAI Conference on Artificial Intelligence.2018. [40]LI J,GALLEY M,BROCKETT C,et al.A Diversity-Promoting Objective Function for Neural Conversation Models[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2016:110-119. [41]TIAN Z,YAN R,MOU L,et al.How to make context more useful? an empirical study on context-aware neural conversational models[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.2017:231-236. [42]ZHANG W,CUI Y,WANG Y,et al.Context-sensitive generation of open-domain conversational responses[C]//Proceedings of the 27th International Conference on Computational Linguistics.2018:2437-2447. [43]SANKAR C,SUBRAMANIAN S,PAL C,et al.Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.2019:32-37. [44]LI J,MONROE W,RITTER A,et al.Deep Reinforcement Learning for Dialogue Generation[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Proces-sing.2016:1192-1202. [45]LI J,MONROE W,SHI T,et al.Adversarial Learning for Neural Dialogue Generation[C]//Proceedings of the 2017 Confe-rence on Empirical Methods in Natural Language Processing.2017:2157-2169. [46]XU Z,LIU B,WANG B,et al.Neural response generation via gan with an approximate embedding layer[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.2017:617-626. [47]SONG Y,LI C T,NIE J Y,et al.An ensemble of retrieval-based and generation-based human computer conversation systems[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence.2018:4382-4388. [48]YAN R,ZHAO D.Coupled context modeling for deep chit-chat:towards conversations between human and computer[C]//Proceedings of the 24th ACMSIGKDD International Conference on Knowledge Discovery & Data Mining.2018:2574-2583. [49]WU Y,WEI F,HUANG S,et al.Response generation by context-aware prototype editing[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019,33:7281-7288. [50]LI H,MIN M R,GE Y,et al.A context-aware attention network for interactive question answering[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2017:927-935. [51]GAO Y,LI P,KING I,et al.Interconnected Question Generation with Coreference Alignment and Conversation Flow Mode-ling[C]//Proceedings of the 57th Annual Meeting of the Asso-ciation for Computational Linguistics.2019:4853-4862. [52]CAO Y T,RAO S,DAUM III H.Controlling the Specificity of Clarification Question Generation[C]//Proceedings of the 2019 Workshop on Widening NLP.2019:53-56. [53]RAO S,DAUM III H.Learning to Ask Good Questions:Ran- king Clarification Questions using Neural Expected Value of Perfect Information[C]//Proceedings of the 56th Annual Mee-ting of the Association for Computational Linguistics.2018:2737-2746. [54]QU C,YANG L,CROFT W B,et al.User intent prediction in information-seeking conversations[C]//Proceedings of the 2019 Conference on Human Information Interaction and Retrieval.2019:25-33. [55]YU Y,PENG S,YANG G H.Modeling Long-Range Context for Concurrent Dialogue Acts Recognition[C]//Proceedings of the 28th ACM International Conference on Information and Know-ledge Management.2019:2277-2280. [56]JUDY D,RON Z.Pragmatic determinants of intonation contours for dialogue systems[J].International Journal of Speech Technology,1997,1(2):109-120. [57]STOLCKE A,RIES K,COCCARO N,et al.Dialogue act mode- ling for automatic tagging and recognition of conversational speech[J].Computational linguistics,2000,26(3):339-373. [58]PARK S,KIM D,OH A.Conversation Model Fine-Tuning for Classifying Client Utterances in Counseling Dialogues[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2019:1448-1459. [59]SONG W.Research on topic based query intention recognition [D].Harbin:Harbin Institute of Technology,2013. [60]LU W,ZHOU H X,ZHANG X J.Review of Research on Query Intent[J].Journal of Library Science in China,2013,39(1):100-111. [61]CHEN H C.Mining consumption intention based on microblog [D].Harbin:Harbin Institute of Technology,2014. [62]JIA Y L,HAN D L,LIN H Y,et al.Consumption Intention Recognition Algorithm for Weibo Users[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2020,56(1):68-74. [63]ANG J,LIU Y,SHRIBERG E.Automatic dialog act segmentation and classification in multiparty meetings[C]//Proceedings.(ICASSP’05).IEEE International Conference on Acoustics,Speech,and Signal Processing.2005. [64]SURENDRAN D,LEVOW G A.Dialog act tagging with support vector machines and hidden Markov models[C]//Ninth International Conference on Spoken Language Processing.2006. [65]JI G,BILMES J.Dialog act tagging using graphical models[C]//Proceedings.(ICASSP’05).IEEE International Conference on Acoustics,Speech,and Signal Processing.2005. [66]KIM S N,CAVEDON L,BALDWIN T.Classifying dialogue acts in one-on-one live chats[C]//Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing.2010:862-871. [67]FERNANDEZ R,PICARD R W.Dialog Act Classification from Prosodic Features Using Support Vector Machines[C]//Speech Prosody 2002,International Conference.2002. [68]VENKATARAMAN A,FERRER L,STOLCKE A,et al. Training a prosody-based dialog act tagger from unlabeled data[C]//2003 IEEE International Conference on Acoustics,Speech,and Signal Processing.2003. [69]DIELMANN A,RENALS S.Recognition of dialogue acts in multiparty meetings using a switching DBN[J].IEEE Transactions on Audio,Speech,and Language Processing,2008,16(7):1303-1314. [70]QUARTERONI S,IVANOV A V,RICCARDI G.Simultaneous dialog act segmentation and classification from human-human spoken conversations[C]//2011 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).2011:5596-5599. [71]CHEN L,DI EUGENIO B.Multimodality and dialogue act classification in the RoboHelper project[C]//Proceedings of the SIGDIAL 2013 Conference.2013:183-192. [72]RIBEIRO E,RIBEIRO R,DE MATOS D M.The influence of context on dialogue act recognition[J].arXiv:1506.00839,2015. [73]BARAHONA L M R,GASIC M,MRKI N,et al.Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding[C]//Proceedings of COLING 2016,the 26th International Conference on Computational Linguistics:Technical Papers.2016:258-267. [74]KHANPOUR H,GUNTAKANDLA N,NIELSEN R.Dialogue act classification in domain-independent conversations using a deep recurrent neural network[C]//Proceedings of COLING 2016,the 26th International Conference on Computational Linguistics:Technical Papers.2016:2012-2021. [75]LIU Y,HAN K,TAN Z,et al.Using context information for dialog act classification in dnn framework[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.2017:2170-2178. [76]HERMANN K M,KOCISKY T,GREFENSTETTE E,et al. Teaching machines to read and comprehend[C]//Advances in Neural Information Processing Systems.2015:1693-1701. [77]ONISHI T,WANG H,BANSAL M,et al.Who did What:A Large-Scale Person-Centered Cloze Dataset[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.2016:2230-2235. [78]HILL F,BORDES A,CHOPRA S,et al.The goldilocks principle:Reading children’s books with explicit memory representations[C]//Proceedings of the Forth International Conference on Learning Representations.2016. [79]BAJGAR O,KADLEC R,KLEINDIENST J.Embracing data abundance:Booktest dataset for reading comprehension[J].ar-Xiv:1610.00956,2016. [80]DHINGRA B,LIU H,YANG Z,et al.Gated-Attention Readers for Text Comprehension[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.2017:1832-1846. [81]MA K,JURCZYK T,CHOI J D.Challenging Reading Comprehension on Daily Conversation:Passage Completion on Multiparty Dialog[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2018:2039-2048. [82]YANG Z,CHOI J D.FriendsQA:Open-domain question answering on TV show transcripts[C]//Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue.2019:188-197. [83]LI J,LIU M,KAN M Y,et al.Molweni:A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure[J].arXiv:2004.05080,2020. [84]CHEN D,BOLTON J,MANNING C D.A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.2016:2358-2367. [85]HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780. [86]TRISCHLER A,YE Z,YUAN X,et al.Natural Language Comprehension with the EpiReader[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Proces-sing.2016:128-137. [87]CUI Y,CHEN Z,WEI S,et al.Attention-over-Attention Neural Networks for Reading Comprehension[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.2017:593-602. [88]SAEIDI M,BARTOLO M,LEWIS P,et al.Interpretation of Natural Language Rules in Conversational Machine Reading[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.2018:2087-2097. [89]ELGOHARY A,ZHAO C,BOYD-GRABER J.A dataset and baselines for sequential open-domain question answering[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.2018:1077-1083. [90]SUN K,YU D,CHEN J,et al.DREAM:A Challenge Data Set and Models for Dialogue-Based Reading Comprehension[J].Transactions of the Association for Computational Linguistics,2019,7:217-231. [91]XU H,LIU B,SHU L,et al.Review conversational reading comprehension[J].arXiv:1902.00821,2019. [92]DAS A,KOTTUR S,GUPTA K,et al.Visual dialog[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:326-335. [93]IYYER M,YIH W T,CHANG M W.Search-based neural structured learning for sequential question answering[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.2017:1821-1831. [94]SAHA A,PAHUJA V,KHAPRA M M,et al.Complex sequential question answering:Towards learning to converse over linked question answer pairs with a knowledge graph[C]//Thirty-Second AAAI Conference on Artificial Intelligence.2018. [95]GUO D,TANG D,DUAN N,et al.Dialog-to-action:Conversational question answering over a large-scale know-ledge base[C]//Advances in Neural Information Processing Systems.2018:2942-2951. [96]CHRISTMANN P,SAHA ROY R,ABUJABAL A,et al.Look before you hop:Conversational question answering over know-ledge graphs using judicious context expansion[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management.2019:729-738. [97]LI Z J,WANG C B.Survey on Deep-learning-based Machine Reading Comprehension[J].Computer Science,2019,46(7):7-12. [98]RAJPURKAR P,ZHANG J,LOPYREV K,et al.SQuAD: 100000+ Questions for Machine Comprehension of Text[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.2016:2383-2392. [99]RAJPURKAR P,JIA R,LIANG P.Know What You Don’t Know:Unanswerable Questions for SQuAD[C]//Proceedings of the 56th Annual Meeting of the Association for Computatio-nal Linguistics.2018:784-789. [100]NGUYEN T,ROSENBERG M,SONG X,et al.MS MARCO:A human generated machine reading comprehension dataset[C]//CoCo 2016-Proceedings of the Workshop on Cognitive Computation:Integrating Neural and Symbolic Approaches 2016,co-located with the 30th Annual Conference on Neural Information Processing Systems,NIPS 2016.2016. [101]CHOI E,HE H,IYYER M,et al.QuAC:Question Answering in Context[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.2018:2174-2184. [102]DEVLIN J,CHANG M W,LEE K,et al.Bert:Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2019. [103]QIU X,SUN T,XU Y,et al.Pre-trained Models for Natural Language Processing:A Survey[J].arXiv:2003.08271,2020. [104]MA L,ZHANG W N,LI M,et al.A Survey of Document Grounded Dialogue Systems(DGDS)[J].arXiv:2004.13818,2020. [105]CHEN D,FISCH A,WESTON J,et al.Reading Wikipedia to Answer Open-Domain Questions[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.2017:1870-1879. [106]GU J,LU Z,LI H,et al.Incorporating Copying Mechanism in Sequence-to-Sequence Learning[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.2016:1631-1640. [107]SEE A,LIU P J,MANNING C D.Get To The Point:Summarization with Pointer-Generator Networks[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.2017:1073-1083. [108]ZHU C,ZENG M,HUANG X.SDNet:Contextualized Attention-based Deep Network for Conversational Question Answe-ring[J].arXiv:1812.03593,2018. [109]SU L,GUO J,FAN Y,et al.An Adaptive Framework for Conversational Question Answering[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:10041-10042. [110]MIN S,ZHONG V,SOCHER R,et al.Efficient and Robust Question Answering from Minimal Context over Documents[C]//Proceedings of the 56th Annual Meeting of the Asso-ciation for Computational Linguistics.2018:1725-1735. [111]GU Y,GUI X,LI D.TT-Net:Topic Transfer-Based Neural Network for Conversational Reading Comprehension[J].IEEE Access,2019,7:116696-116705. [112]BAI S,KOLTER J Z,KOLTUN V.An empirical evaluation of generic convolutional and recurrent networks for sequence mo-deling[J].arXiv:1803.01271,2018. [113]MANDYA A,BOLLEGALA D,COENEN F.Evaluating Co-re- ference Chains based Conversation History in Conversational Question Answering[C]//International Conference of the Paci-fic Association for Computational Linguistics.Springer,Singapore.2019:280-292. [114]SEO M,KEMBHAVI A,FARHADI A,et al.Bidirectional attention flow for machine comprehension[C]//5th International Conference on Learning Representations(ICLR).2017. [115]CLARK C,GARDNER M.Simple and Effective Multi-Para- graph Reading Comprehension[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.2018:845-855. [116]PETERS M,NEUMANN M,IYYER M,et al.Deep Contextua- lized Word Representations[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2018:2227-2237. [117]YATSKAR M.A Qualitative Comparison of CoQA,SQuAD2.0 and QuAC[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2019:2318-2323. [118]HUANG H Y,CHOI E,YIH W.FlowQA:Grasping Flow in History for Conversational Machine Comprehension[C]//7th International Conference on Learning Representations(ICLR).2019. [119]CHEN Y,WU L,ZAKI M J.Graphflow:Exploiting conversation flow with graph neural networks for conversational machine comprehension[J].arXiv:1908.00059,2019. [120]OHSUGI Y,SAITO I,NISHIDA K,et al.A Simple but Effective Method to Incorporate Multi-turn Context with BERT for Conversational Machine Comprehension[C]//Proceedings of the First Workshop on NLP for Conversational AI.2019:11-17. [121]YEH Y T,CHEN Y N.FlowDelta:Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension[C]//Proceedings of the 2nd Workshop on Machine Reading for Question Answering.2019:86-90. [122]QU C,YANG L,QIU M,et al.BERT with History Answer Embedding for Conversational Question Answering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval.2019:1133-1136. [123]QU C,YANG L,QIU M,et al.Attentive History Selection for Conversational Question Answering[C]//Proceedings of the 28th ACM International Conference on Information and Know-ledge Management.2019:1391-1400. [124]JU Y,ZHAO F,CHEN S,et al.Technical report on Conversational Question Answering[J].arXiv:1909.10772,2019. [125]LIU Y,OTT M,GOYAL N,et al.RoBERTa:A Robustly Optimized BERT Pretraining Approach[J].arXiv:1907.11692,2019. [126]GOODFELLOW I J,SHLENS J,SZEGEDY C.Explaining and harnessing adversarial examples[J].arXiv:1412.6572,2014. [127]HINTON G,VINYALS O,DEAN J.Distilling the knowledge in a neural network[J].arXiv:1503.02531,2015. [128]RUDER S.Neural Transfer Learning for Natural Language Processing[D].Galway,Ireland:National University of Ireland,2019. [129]QIU M,YANG L,JI F,et al.Transfer Learning for Context- Aware Question Matching in Information-seeking Conversations in E-commerce[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.2018:208-213. [130]WHANG T,LEE D,LEE C,et al.Domain adaptive training bert for response selection[J].arXiv:1908.04812,2019. [131]YAN R,ZHAO D,E W.Joint learning of response ranking and next utterance suggestion in human-computer conversation system[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval.2017:685-694. [132]TAO C,WU W,XU C,et al.Improving matching models with contextualized word representations for multiturn response selection in retrieval-based chatbots[J].arXiv:1808.07244,2018. [133]CHO K,VAN MERRIËNBOER B,GULCEHRE C,et al. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing(EMNLP).2014:1724-1734. [134]WOLF T,SANH V,CHAUMOND J,et al.TransferTransfo:A transfer learning approach for neural network based conversational agents[J].arXiv:1901.08149,2019. |
[1] | 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木. 中文预训练模型研究进展 Advances in Chinese Pre-training Models 计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018 |
[2] | 赵丹丹, 黄德根, 孟佳娜, 董宇, 张攀. 基于BERT-GRU-ATT模型的中文实体关系分类 Chinese Entity Relations Classification Based on BERT-GRU-ATT 计算机科学, 2022, 49(6): 319-325. https://doi.org/10.11896/jsjkx.210600123 |
[3] | 刘硕, 王庚润, 彭建华, 李柯. 基于混合字词特征的中文短文本分类算法 Chinese Short Text Classification Algorithm Based on Hybrid Features of Characters and Words 计算机科学, 2022, 49(4): 282-287. https://doi.org/10.11896/jsjkx.210200027 |
[4] | 侯宏旭, 孙硕, 乌尼尔. 蒙汉神经机器翻译研究综述 Survey of Mongolian-Chinese Neural Machine Translation 计算机科学, 2022, 49(1): 31-40. https://doi.org/10.11896/jsjkx.210900006 |
[5] | 汤世征, 张岩峰. DragDL:一种易用的深度学习模型可视化构建系统 DragDL:An Easy-to-Use Graphical DL Model Construction System 计算机科学, 2021, 48(8): 220-225. https://doi.org/10.11896/jsjkx.200900045 |
[6] | 王胜, 张仰森, 陈若愚, 向尕. 基于细粒度差异特征的文本匹配方法 Text Matching Method Based on Fine-grained Difference Features 计算机科学, 2021, 48(8): 60-65. https://doi.org/10.11896/jsjkx.200700008 |
[7] | 张玉帅, 赵欢, 李博. 基于BERT和BiLSTM的语义槽填充 Semantic Slot Filling Based on BERT and BiLSTM 计算机科学, 2021, 48(1): 247-252. https://doi.org/10.11896/jsjkx.191200088 |
[8] | 倪海清, 刘丹, 史梦雨. 基于语义感知的中文短文本摘要生成模型 Chinese Short Text Summarization Generation Model Based on Semantic-aware 计算机科学, 2020, 47(6): 74-78. https://doi.org/10.11896/jsjkx.190600006 |
[9] | 陈晓军, 向阳. 企业风险知识图谱的构建及应用 Construction and Application of Enterprise Risk Knowledge Graph 计算机科学, 2020, 47(11): 237-243. https://doi.org/10.11896/jsjkx.191000015 |
[10] | 宋砚秋, 李桂君, 李慧嘉. 基于势能背景信息的社团标签探测算法 Community Label Detection Algorithm Based on Potential Background Information 计算机科学, 2018, 45(6A): 314-317. |
[11] | 韩朝, 苗夺谦, 任福继. 基于粗糙集理论的中文知识问答的知识谓词分析 Rough Set Based Knowledge Predicate Analysis of Chinese Knowledge Based Question Answering 计算机科学, 2018, 45(6): 183-186. https://doi.org/10.11896/j.issn.1002-137X.2018.06.032 |
[12] | 王东升,王卫民,王石,符建辉,诸峰. 面向限定领域问答系统的自然语言理解方法综述 Research on Domain-specific Question Answering System Oriented Natural Language Understanding:A Survey 计算机科学, 2017, 44(8): 1-8. https://doi.org/10.11896/j.issn.1002-137X.2017.08.001 |
[13] | 李舟军,李水华. 基于Web的问答系统综述 Survey on Web-based Question Answering 计算机科学, 2017, 44(6): 1-7. https://doi.org/10.11896/j.issn.1002-137X.2017.06.001 |
[14] | 冶忠林,贾真,尹红风. 多领域自然语言问句理解研究 Research on Multi-domain Natural Language Question Understanding 计算机科学, 2017, 44(6): 216-221. https://doi.org/10.11896/j.issn.1002-137X.2017.06.036 |
[15] | 蒋 胜,王忠群,修 宇,皇苏斌,汪千松. 基于动态社会行为和用户背景的协同推荐方法 Collaborative Filtering Recommendation Method Based on Dynamic Social Behavior and Users’ Background Information 计算机科学, 2015, 42(3): 252-255. https://doi.org/10.11896/j.issn.1002-137X.2015.03.052 |
|