Similar articles

Abstract: question answering is an important problem that aims to deliver specific answers to questions posed by humans in natural language. How to efficiently identify the exact answer with respect to a given question has become an active line of research. Previous approaches in factoid question answering tasks typically focus on modeling the semantic relevance or syntactic relationship between a given question and its corresponding answer. Most of these models suffer when a question contains very little content that is indicative of the answer. In this paper, we devise an architecture named the temporality-enhanced knowledge memory network (TE-KMN) and apply the model to a factoid question answering dataset from a trivia competition called quiz bowl. Unlike most of the existing approaches, our model encodes not only the content of questions and answers, but also the temporal cues in a sequence of ordered sentences which gradually remark the answer. Moreover, our model collaboratively uses external knowledge for a better understanding of a given question. The experimental results demonstrate that our method achieves better performance than several state-of-the-art methods.

时序增强的知识记忆网络在问答中的应用

[1]Bahdanau D, Cho K, Bengio Y, 2014. Neural machine translation by jointly learning to align and translate. arXiv:1409.0473. https://arxiv.org/abs/1409.0473

[2]Bao JW, Duan N, Zhou M, et al., 2014. Knowledge-based question answering as machine translation. 52^nd Annual Meeting of the Association for Computational Linguistics, p.967-976.

[3]Barrón-Cedeño A, Filice S, Martino GDS, et al., 2015. Thread-level information for comment classification in community question answering. 53^rd Annual Meeting of the Association for Computational Linguistics, p.687-693.

[4]Bilotti MW, Elsas JL, Carbonell JG, et al., 2010. Rank learning for factoid question answering with linguistic and semantic constraints. 19^th ACM Conf on Information and Knowledge Management, p.459-468.

[5]Boyd-Graber JL, Satinoff B, He H, et al., 2012. Besting the quiz master: crowdsourcing incremental classification games. Joint Conf on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, p.1290-1301.

[6]Carr CE, 1993. Processing of temporal information in the brain. Ann Rev Neurosci, 16(1):223-243.

[7]Chen D, Bolton J, Manning CD, 2016. A thorough examination of the CNN/daily mail reading comprehension task. 54^th Annual Meeting of the Association for Computational Linguistics, p.2358-2367.

[8]Cho K, van Merrienboer B, Gülçehre Ç, et al., 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. Conf on Empirical Methods in Natural Language Processing, p.1724-1734.

[9]Chorowski J, Bahdanau D, Serdyuk D, et al., 2015. Attention-based models for speech recognition. Advances in Neural Information Processing Systems, p.577-585.

[10]Ding S, Cong G, Lin C, et al., 2008. Using conditional random fields to extract contexts and answers of questions from online forums. 46^th Annual Meeting of the Association for Computational Linguistics, p.710-718.

[11]Figueroa A, Atkinson J, 2011. Maximum entropy context models for ranking biographical answers to open-domain definition questions. 25^th AAAI Conf on Artificial Intelligence, p.1173-1179.

[12]Fillmore CJ, 1976. Frame semantics and the nature of language. Ann New York Acad Sci, 280(1):20-32.

[13]Ghazvininejad M, Brockett C, Chang M, et al., 2017. A knowledge-grounded neural conversation model. arXiv:1702.01932. https://arxiv.org/abs/1702.01932

[14]Graves A, Fernández S, Schmidhuber J, 2005. Bidirectional LSTM networks for improved phoneme classification and recognition. 15^th Int Conf on Artificial Neural Networks, p.799-804.

[15]Huang J, Zhou M, Yang D, 2007. Extracting chatbot knowledge from online discussion forums. 20^th Int Joint Conf on Artifical Intelligence, p.423-428.

[16]Ivry RB, 1996. The representation of temporal information in perception and motor control. Curr Opin Neurobiol, 6(6):851-857.

[17]Iyyer M, Boyd-Graber JL, Claudino LMB, et al., 2014. A neural network for factoid question answering over paragraphs. Conf on Empirical Methods in Natural Language Processing, p.633-644.

[18]Iyyer M, Manjunatha V, Boyd-Graber JL, et al., 2015. Deep unordered composition rivals syntactic methods for text classification. 53^rd Annual Meeting of the Association for Computational Linguistics, p.1681-1691.

[19]Jeon J, Croft WB, Lee JH, 2005. Finding similar questions in large question and answer archives. 14^th ACM Int Conf on Information and Knowledge Management, p.84-90.

[20]Joty SR, Barrón-Cedeño A, Martino GDS, et al., 2015. Global thread-level inference for comment classification in community question answering. Conf on Empirical Methods in Natural Language Processing, p.573-578.

[21]Jurczyk P, Agichtein E, 2007. Discovering authorities in question answer communities by using link analysis. 16^th ACM Conf on Information and Knowledge Management, p.919-922.

[22]Kalchbrenner N, Grefenstette E, Blunsom P, 2014. A convolutional neural network for modeling sentences. 52^nd Annual Meeting of the Association for Computational Linguistics, p.655-665.

[23]Le QV, Mikolov T, 2014. Distributed representations of sentences and documents. 31^st Int Conf on Machine Learning, p.1188-1196.

[24]Li B, Lyu MR, King I, 2012. Communities of Yahoo! Answers and Baidu Zhidao: complementing or competing? Int Joint Conf on Neural Networks, p.1-8.

[25]Luong T, Pham H, Manning CD, 2015. Effective approaches to attention-based neural machine translation. Conf on Empirical Methods in Natural Language Processing, p.1412-1421.

[26]Ma X, Hovy EH, 2016. End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF. 54^th Annual Meeting of the Association for Computational Linguistics, p.1064-1074.

[27]Mikolov T, Karafiát, Burget L, et al., 2010. Recurrent neural network based language model. 11^th Annual Conf of the Int Speech Communication Association, p.1045-1048.

[28]Mikolov T, Chen K, Corrado G, et al., 2013. Efficient estimation of word representations in vector space. arXiv:1301.3781. https://arxiv.org/abs/1301.3781

[29]Minsky M, 1991. Society of mind: a response to four reviews. Artif Intell, 48(3):371-396.

[30]Nakashole N, Mitchell TM, 2015. A knowledge-intensive model for prepositional phrase attachment. 53^rd Annual Meeting of the Association for Computational Linguistics, p.365-375.

[31]Navigli R, Velardi P, 2010. Learning word-class lattices for definition and hypernym extraction. 48^th Annual Meeting of the Association for Computational Linguistics, p.1318-1327.

[32]Pan B, Li H, Zhao Z, et al., 2017. MEMEN: multi-layer embedding with memory networks for machine comprehension. arXiv:1707.09098. https://arxiv.org/abs/1707.09098

[33]Pan Y, 2016. Heading toward artificial intelligence 2.0. Engineering, 2(4):409-413.

[34]Qiu X, Huang X, 2015. Convolutional neural tensor network architecture for community-based question answering. 24^th Int Joint Conf on Artificial Intelligence, p.1305-1311.

[35]Rush AM, Chopra S, Weston J, 2015. A neural attention model for abstractive sentence summarization. Conf on Empirical Methods in Natural Language Processing, p.379-389.

[36]Schweppe J, Rummer R, 2013. Attention, working memory, and long-term memory in multimedia learning: an integrated perspective based on process models of working memory. Ed Psychol Rev, 26(2):285-306.

[37]Shah C, Pomerantz J, 2010. Evaluating and predicting answer quality in community QA. 33^rd Int ACM SIGIR Conf on Research and Development in Information Retrieval, p.411-418.

[38]Shen Y, Rong W, Sun Z, et al., 2015. Question/Answer matching for CQA system via combining lexical and sequential information. 29^th AAAI Conf on Artificial Intelligence, p.275-281.

[39]Sukhbaatar S, Szlam A, Weston J, et al., 2015. End-to-end memory networks. Advances in Neural Information Processing Systems, p.2440-2448.

[40]Sun R, Jiang J, Tan YF, et al., 2005. Using syntactic and semantic relation analysis in question answering. 14^th Text REtrieval Conf.

[41]Sutskever I, Vinyals O, Le QV, 2014. Sequence to sequence learning with neural networks. Advances in Neural Information Processing Systems, p.3104-3112.

[42]Wang B, Wang X, Sun C, et al., 2010. Modeling semantic relevance for question-answer pairs in web social communities. 48^th Annual Meeting of the Association for Computational Linguistics, p.1230-1238.

[43]Wang M, 2006. A Survey of Answer Extraction Techniques in Factoid Question Answering. https://cs.stanford.edu/people/mengqiu/publication/LSII-LitReview.pdf

[44]Wei X, Huang H, Nie L, et al., 2017. I know what you want to express: sentence element inference by incorporating external knowledge base. IEEE Trans Knowl Data Eng, 29(2):344-358.

[45]Xue X, Jeon J, Croft WB, 2008. Retrieval models for question and answer archives. 31^st Int ACM SIGIR Conf on Research and Development in Information Retrieval, p.475-482.

[46]Yang B, Mitchell TM, 2017. Leveraging knowledge bases in LSTMs for improving machine reading. 55^th Annual Meeting of the Association for Computational Linguistics, p.1436-1446.

[47]Yang Y, Zhuang Y, Wu F, et al., 2008. Harmonizing hierarchical manifolds for multimedia document semantics understanding and cross-media retrieval. IEEE Trans Multimed, 10(3):437-446.

[48]Yao X, Durme BV, 2014. Information extraction over structured data: question answering with freebase. 52^nd Annual Meeting of the Association for Computational Linguistics, p.956-966.

[49]Zheng S, Bao H, Zhao J, et al., 2015. A novel hierarchical convolutional neural network for question answering over paragraphs. IEEE/WIC/ACM Int Conf on Web Intelligence and Intelligent Agent Technology, p.60-66.

[50]Zhou G, Cai L, Zhao J, et al., 2011. Phrase-based translation model for question retrieval in community question answer archives. 49^th Annual Meeting of the Association for Computational Linguistics, p.653-662.

[51]Zhuang Y, Yang Y, Wu F, 2008. Mining semantic correlation of heterogeneous multimedia data for cross-media retrieval. IEEE Trans Multimed, 10(2):221-229.

[52]Zhuang Y, Wu F, Chen C, et al., 2017. Challenges and opportunities: from big data to knowledge in AI 2.0. Front Inform Technol Electron Eng, 18(1):3-14.