Abstract
In this chapter, we learn how to manage a dialogue relying on the discourse of its utterances. We show how a dialogue structure can be built from an initial utterance. After that, we introduce an imaginary discourse tree to address the problem of involving background knowledge on demand, answering questions. An approach to dialogue management based on a lattice walk is described. We also propose Doc2Dialogue algorithm of converting a paragraph of text into a hypothetical dialogue based on an analysis of a discourse tree for this paragraph. This technique allows for a substantial extension of chatbot training datasets in an arbitrary domain. We evaluate constructed dialogues and conclude that deploying the proposed algorithm is a key in successful chatbot development in a broad range of domains where manual coding for dialogue management and providing relevant content is not practical.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adiwardana DD, Luong M, So DR, Hall J, Fiedel N, Thoppilan R, Yang Z, Kulshreshtha A, Nemade G, Lu Y, Le QV (2020) Towards a human-like open-domain chatbot. arXiv:2001.09977
Agostaro F, Augello A, Pilato G, Vassallo G, Gaglio S (2005) A conversational agent based on a conceptual interpretation of a data driven semantic space. In: Proceedings of AI*IA, LNAI, vol 3673, pp 381–392
Amiridze N, Kutsia T (2018) Anti-unification and natural language processing. In: Fifth workshop on natural language and computer science, NLCS’18, EasyChair Preprint no. 203
Augello A, Gentile M, Dignum F (2017) An overview of open-source chatbots social skills. In: Diplaris S, Satsiou A, Følstad A, Vafopoulos M, Vilarinho T (eds) Internet science. Lecture notes in computer science, vol 10750, pp 236–248
Banchs RE (2012) Movie-DiC: a movie dialogue corpus for research and development. In: Proceedings of the 50th annual meeting of the association for computational linguistics, pp 203–207
Barzilay R, Lapata M (2008) Modeling local coherence: an entity-based approach. Comput Linguist 34(1):1–34
Bordes A, Weston J (2016) Learning end-to-end goal-oriented dialog. In: ICRL 2017
CarPros Car Repair Dataset (2017) https://github.com/bgalitsky/relevance-based-on-parse-trees/blob/master/examples/CarRepairData_AnswerAnatomyDataset2.csv.zip. Obtained from https://www.2carpros.com.
Cartoonbank (2020) https://cartoonbank.ru/?page_id=29&category=5&offset=80
Chali Y, Joty SR, Hasan SA (2009) Complex question answering: unsupervised learning approaches and experiments. J Artif Int Res 35
Clarke J, Lapata M (2010) Discourse constraints for document compression. Comput Linguist 36(3):411–441
Codocedo V, Napoli A (2014) A proposition for combining pattern structures and relational concept analysis. In: Glodeanu CV, Kaytoue M, Sacarea C (eds) ICFCA 2014. LNCS (LNAI), vol 8478. Springer, Heidelberg, pp 96–111
Cohen W (2018) Enron email dataset. https://www.cs.cmu.edu/~./enron/. Accessed 10 July 2018
Csaky R (2019) Deep learning based chatbot models. arXiv:1908.08835
DeepPavlov.ai (2020) DeepPavlov: an open source conversational AI framework. https://deeppavlov.ai/
Du X, Shao J, Cardie C (2017) Learning to ask: neural question generation for reading comprehension. arXiv:1705.00106
Feng WV, Hirst G (2014) A linear-time bottom-up discourse parser with constraints and post-editing. In: Proceedings of the 52nd annual meeting of the association for computational linguistics (ACL 2014), Baltimore, USA, June 2014
Fidelity (2018) https://github.com/bgalitsky/relevance-based-on-parse-trees/blob/master/examples/Fidelity_FAQs_AnswerAnatomyDataset1.csv.zip
Galitsky B (2013) Transfer learning of syntactic structures for building taxonomies for search engines. Eng Appl Artif Intell 26(10):2504–2515
Galitsky B (2014) Learning parse structure of paragraphs and its applications in search. Eng Appl Artif Intell 32:160–184
Galitsky B (2016) Providing personalized recommendation for attending events based on individual interest profiles. AI Res 5(1) (Sciedu Press)
Galitsky, B, Chen H, Du S (2009) Inverting semantic structure of customer opinions expressed in forums and blogs. In: 17th international conference on conceptual structures, Suppl Proc
Galitsky B, Kovalerchuk B (2014) Improving web search relevance with learning structure of domain concepts. Clusters Orders Trees: Methods Appl 92:341–376
Galitsky B, Kuznetsov SO, Usikov D (2013) Parse thicket representation for multi-sentence search. In: International conference on conceptual structures, pp 153–172
Galitsky B, Dobrocsi G, de la Rosa JL (2012) Inferring the semantic properties of sentences by mining syntactic parse trees. Data Knowl Eng 81:21–45
Galitsky B, Ilvovsky D, Kuznetsov SO (2015a) Text classification into abstract classes based on discourse structure. In: Proceedings of recent advances in natural language processing, Hissar, Bulgaria, pp 200–207, 7–9 Sept 2015
Galitsky B, Ilvovsky D, Kuznetsov SO (2015b) Rhetoric map of an answer to compound queries. In: ACL-2, pp 681–686
Galitsky B (2017a) Matching parse thickets for open domain question answering. Data Knowl Eng 107:24–50
Galitsky B (2017b) Discovering rhetorical agreement between a request and response. Dialogue Discourse 8(2):167–205
Galitsky (2019a) Automated building of expanded datasets for training of autonomous agents. US Patent Application 16/426,878
Galitsky B (2019b) Rhetorical agreement: maintaining cohesive conversations. Developing enterprise chatbots. Springer, Cham, pp 327–363
Galitsky B (2019c) Semantic skeleton thesauri for question answering bots. Developing enterprise chatbots. Springer, Cham, pp 163–176
Galitsky B (2019d) Building chatbot thesaurus. In: Developing enterprise chatbots. Springer, Cham, pp 221–252
Galitsky B, Ilvovsky D (2017a) Chatbot with a discourse structure-driven dialogue management. In: EACL demo program
Galitsky B, Ilvovsky D (2017b) On a chat bot finding answers with optimal rhetoric representation. In: Proceedings of recent advances in natural language processing, Varna, Bulgaria, pp 253–259, 4–6 Sept 2017
Galitsky B, Makowski G (2017) Document classifier for a data loss prevention system based on learning rhetoric relations. In: CICLing 2017 Budapest, Hungary, 17–23 Apr 2017
Galitsky B, McKenna EW (2017) Sentiment extraction from consumer reviews for providing product recommendations. US Patent 9646078B2
Galitsky B, Ilvovsky D (2019) On a chatbot conducting virtual dialogues. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp 2925–2928.
Galitsky B, Ilvovsky D, Makhalova T (2019) Discourse-level dialogue management. In: Developing enterprise chatbots. Springer, Cham, Switzerland
Galitsky B, Shpitsberg I (2015) Evaluating assistance to individuals with autism in reasoning about mental world. Artificial intelligence applied to assistive technologies and smart environments: papers from the 2015 AAAI workshop
Galitsky B, Ilvovsky D, Lebedeva N, Usikov D (2014) Improving trust in automation of social promotion. In: AAAI Spring symposium on the intersection of robust intelligence and trust in autonomous systems, Stanford, CA
Galitsky B, Parnis A, Usikov D (2017) Exploring discourse structure of user-generated content. In: CICLing 2017, Budapest, Hungary, 17–23 Apr 2017
Galitsky B, Dobrocsi G, de la Rosa JL, Sergei O Kuznetsov (2011) Using generalization of syntactic parse trees for taxonomy capture on the web. In: 19th international conference on conceptual structures, ICCS 2011, pp 104–117
Godfrey J, Holliman E (1997) Switchboard-1 release 2. Linguistic Data Consortium, Philadelphia
Grosz B, Joshi AK, Scott Weinstein S (1995) Centering: a framework for modeling the local coherence of discourse. Comput Linguist 21(2):203–225
Gundel JK, Hedberg N, Zacharski R (1993) Cognitive status and the form of referring expressions in discourse. Language 69(2):274–307
Hardalov M, Koychev I, Nakov P (2019) Machine reading comprehension for answer re-ranking in customer support chatbots. arXiv:1902.04574
Heerschop B, Goossen F, Hogenboom A, Frasincar F, Kaymak U, de Jong F (2011) Polarity analysis of texts using discourse structure. In: Proceedings of the 20th ACM international conference on information and knowledge management, CIKM ’11. ACM, New York, NY, USA, pp 1061–1070
Heilman M, Smith NA (2010) Good question! statistical ranking for question generation. In: Human language technologies: the 2010 annual conference of the North American chapter of the Association for Computational Linguistics, pp 609–617
Ilvovsky D, Kirillovich A, Galitsky B (2020) Controlling chat bot multi-document navigation with the extended discourse trees. CLIB 63–71
Indri IR (2018) https://www.lemurproject.org/indri/. Accessed 11 Sept 2018
Irmer M (2010) Bridging inferences in discourse interpretation. PhD dissertation, University of Leipzig, Germany
Ivanov S, Webster C, Stoilova E, Slobodskoy D (2020) Biosecurity, automation technologies and economic resilience of travel, tourism and hospitality companies. osf.io
Jansen P, Surdeanu M, Clark P (2014) Discourse complements lexical semantics for nonfactoid answer reranking. ACL.
Joty SR, Moschitti A (2014) Discriminative reranking of discourse parses using tree kernels. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)
Joty SR, Carenini G, Ng RT, Mehdad Y (2013) Combining intra-and multi-sentential rhetorical parsing for document-level discourse analysis. In: ACL (1), pp 486–496
Jurafsky D, Martin JH (2000) Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition. Prentice Hall, Upper Saddle River
Kaggle (2019) Customer support on Twitter. https://www.kaggle.com/thoughtvector/customer-support-on-twitter. Accessed 18 Feb 2019
Kaytoue M, Codocedo V, Buzmakov A, Baixeries J, Kuznetsov SO, Napoli A (2015) Pattern structures and concept lattices for data mining and knowledge processing. In: Joint European conference on machine learning and knowledge discovery in databases. Springer, Cham, pp 227–231
Kelley JF (1984) An iterative design methodology for user-friendly natural language office information applications. ACM Trans Inf Syst
Kerly A, Hall P, Bull S (2007) Bringing chatbots into education: towards natural language negotiation of open learner models. Knowl-Based Syst 20(2):177–185
Kipper K, Korhonen A, Ryant N, Palmer M (2008) A large-scale classification of English verbs. Lang Resour Eval J 42:21–40
Kostelník P, Pisařovic I, Muroň M, Dařena F, Procházka D (2019) Chatbots for enterprises: outlook. Acta Univ Agric Silvic Mendel Brun 67:1541–1550
Kovalerchuk B, Kovalerchuk M (2017) Toward virtual data scientist with visual means. In: IJCNN
Kumar V, Ramakrishnan G, Li Y (2018) A framework for automatic question generation from text using deep reinforcement learning. CoRR. arXiv:1808.04
Kuyten P, Bollegala D, Hollerit B, Prendinger H, Aizawa K (2015) A discourse search engine based on rhetorical structure theory. In: Hanbury A, Kazai G, Rauber A, Fuhr N (eds) Advances in information retrieval. ECIR 2015. Lecture notes in computer science, vol 9022. Springer, Cham
LeThanh H, Abeysinghe G, Huyck C (2004) Generating discourse structures for written texts. In: Proceedings of the 20th international conference on computational linguistics, COLING ’04, Geneva, Switzerland. Association for Computational Linguistics.
Lin CY (2004) ROUGE: a package for automatic evaluation of summaries. In: Proceedings of the ACL workshop on text summarization branches out, Barcelona, Spain, pp 74–81, 25–26 July 2004
Lioma C, Larsen B, Lu W (2012) Rhetorical relations for information retrieval. In: SIGIR, Portland, Oregon, USA, 12–16 Aug 2012
Liu C-W, Lowe R, Serban I, Noseworthy M, Charlin L, Pineau J (2016) How not to evaluate your dialogue system: an empirical study of unsupervised evaluation metrics for dialogue response generation. In: EMNLP, pp 2122–2132
Louis A, Joshi AK, Nenkova A (2010) Discourse indicators for content selection in summarization. In: Fernandez R, Katagiri Y, Komatani K, Lemon O, Nakano M (eds) SIGDIAL conference. The Association for Computer Linguistics, pp 147–156
Lowe R, Pow N, Serban I, Pineau J (2015) The Ubuntu Dialogue Corpus: a large dataset for research in unstructured multi-turn dialogue systems. In: 16th annual meeting of the special interest group on discourse and dialogue, Prague, Czech Republic, pp 285–294, 2–4 Sept 2015
Lowe R, Serban IV, Noseworthy M, Charlin L, Pineau J (2016) On the evaluation of dialogue systems with next utterance classification. In: Special interest group on discourse and dialogue
Mann W, Thompson S (1988) Rhetorical structure theory: towards a functional theory of text organization. Text Interdiscip J Study Discourse 8(3):243–281
Marir F, Haouam K (2004) Rhetorical structure theory for content-based indexing and retrieval of web documents. In: ITRE 2004. 2nd international conference information technology: research and education, pp 160–164
Morato J, Llorens J, Genova G, Moreiro JA (2003) Experiments in discourse analysis impact on information classification and retrieval algorithms. Inf Process Manag 39:825–851
Morbini F, Forbell E, DeVault D, Sagae K Traum DR, Rizzo AA (2012) A mixed-initiative conversational dialogue system for healthcare. In: SIGDIAL ’12: proceedings of the 13th annual meeting of the special interest group on discourse and dialogue, pp 137–139, July 2012
Nagarajan V, Chandrasekar P (2014) Pivotal Sentiment Tree Classifier. IJSTR 3, I(11)
Nakamura R, Sudoh K, Yoshino K, Nakamura S (2018) Another diversity-promoting objective function for neural dialogue generation. arXiv:1811.08100
Nguyen DT, Joty S (2017) A neural local coherence model. ACL 1:1320–1330
Novikova J, Dusek O, Curry AC, Rieser V (2017) Why we need new evaluation metrics for NLG. In: EMNLP
Papineni K, Roukos S, Ward T, Zhu WJ (2002) BLEU: a method for automatic evaluation of machine translation (PDF). In: ACL-2002: 40th annual meeting of the Association for Computational Linguistics, pp 311–318
Plotkin GD (1970) A note on inductive generalization. Mach Intell 5(1):153–163
Poesio M, Stevenson R, Di Eugenio B, Hitzeman J (2004) Centering: a parametric theory and its instantiations. Comput Linguist 30(3):309–363
Rajpurkar P, Zhang J, Lopyrev K, Liang P (2016) Squad: 100,000+ questions for machine comprehension of text. arXiv:1606.05250
Rizk Y, Bhandwalder A, Boag S, Chakraborti T, Isahagian V, Khazaeni Y, Pollock F, Unuvar M (2020) A unified conversational assistant framework for business process automation. arXiv:2001.03543
Rus V, Lintean M (2012) A comparison of greedy and optimal assessment of natural language student input using word-to-word similarity metrics. In: Proceedings of the seventh workshop on building educational applications using NLP, Montreal, QC, Canada, pp 157–162
Serban IV, Lowe R, Henderson P, Charlin L, Pineau J (2017) A survey of available corpora for building data-driven dialogue systems. arXiv:1512.05742
Serban IV, Garcıa-Duran A, Gulcehre C, Ahn S, Chandar S, Courville A, Bengio Y (2016) Generating factoid questions with recurrent neural networks: the 30m factoid question-answer corpus. arXiv:1603.06807
Sidorov G, Velasquez F, Stamatatos E, Gelbukh A, Chanona-Hernández L (2012) Syntactic dependency-based N-grams as classification features. In: LNAI, vol 7630, pp 1–11
Singer H, Donlan D (1982) Active comprehension: Problem-solving schema with question generation for comprehension of complex short stories. Read Res Q 166–186
Singh Ospina N, Phillips KA, Rodriguez-Gutierrez R, Castaneda-Guarderas A, Gionfriddo MR, Branda ME, MontoriVM (2018) Eliciting the patient’s agenda—secondary analysis of recorded clinical encounters. J Gen Intern Med 1–5
Somasundaran S, Namata G, Wiebe J, Getoor L (2009) Supervised and unsupervised methods in employing discourse relations for improving opinion polarity classification. In: EMNLP. ACL, pp 170–179
Soricut R, Marcu D (2003) Sentence level discourse parsing using syntactic and lexical information. In: HLT-NAACL
Sun M, Chai JY (2007) Discourse processing for context question answering based on linguistic knowledge. Knowl-Based Syst 20:511–526
Surdeanu M, Hicks T, Valenzuela-Escarcega MA (2015) Two practical rhetorical structure theory parsers. In: Proceedings of the conference of the North American chapter of the Association for Computational Linguistics—human language technologies: software demonstrations (NAACL HLT)
Sutton RS, Barto AG (1998) Introduction to reinforcement learning, vol 135. MIT Press, Cambridge
Suwandaratna N, Perera U (2010) Discourse marker based topic identification and search results refining. In: 2010 5th international conference on information and automation for sustainability (ICIAFs), pp 119–125
Tanaka R, Ozeki A, Kato S, Lee A (2020) Context and knowledge aware conversational model and system combination for grounded response generation. Comput Speech Lang 62
Teufel S, Moens M (2002) Summarizing scientific articles: experiments with relevance and rhetorical status. Comput Linguist 28(4):409–445
Vorontsov K, Potapenko A (2015) Additive regularization of topic models. Mach Learn 101(1–3):303–323
Wang T, Yuan X, Trischler A (2017) A joint model for question answering and question generation. arXiv:1706.01450
Wang DY, Luk RWP, Wong K-F, Kwok KL (2006) An information retrieval approach based on discourse type. In: Kop C, Fliedl G, Mayr HC, Métais E (eds) NLDB. Lecture notes in computer science, vol 3999. Springer, pp 197–202
Wang W, Su J, Tan CL (2010) Kernel based discourse relation recognition with temporal ordering information. ACL
Wang Z, Lemon O (2013) A simple and generic belief tracking mechanism for the dialog state tracking challenge: on the believability of observed information. In: Proceedings of the SIGDIAL.
Webscope (2017). Yahoo! Answers dataset. https://webscope.sandbox.yahoo.com/catalog.php?datatype=l
Wilks YA (ed) (1999) Machine conversations. Kluwer
Young S, Gasic M, Thomson B, Williams J (2013) POMDP-based statistical spoken dialogue systems: a review. Proc IEEE 99:1–20
Yuan X, Wang T, Gulcehre C, Sordoni A, Bachman P, Subramanian S, Zhang S and Trischler A (2017) Machine comprehension by text-to-text neural question generation. arXiv:1705.02012
Zhao J, Chevalier F, Collins C, Balakrishnan R (2012) Facilitating discourse analysis with interactive visualization. IEEE Trans Vis Comput Graph 18(12):2639–2648
Zhao X, Wu W, Tao C, Xu C, Zhao D, Yan R (2020) Low-resource knowledge-grounded dialogue generation. arXiv:2002.10348
Zidrasco T, Shiramatsu S, Takasaki J, Ozono T, Shintani T (2010) Building and analyzing corpus to investigate appropriateness of argumentative discourse structure for facilitating consensus. In: García-Pedrajas N, Herrera F, Fyfe C, Benítez JM, Ali M (eds) Trends in applied intelligent systems. IEA/AIE 2010. Lecture notes in computer science, vol 6097. Springer, Berlin, Heidelberg
Acknowledgements
I am grateful to my colleagues Dmitry Ilvovsky and Tatyana Makhalova for help in the preparation of this chapter.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Galitsky, B. (2021). Chatbots for CRM and Dialogue Management. In: Artificial Intelligence for Customer Relationship Management. Human–Computer Interaction Series. Springer, Cham. https://doi.org/10.1007/978-3-030-61641-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-61641-0_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61640-3
Online ISBN: 978-3-030-61641-0
eBook Packages: Computer ScienceComputer Science (R0)