In this work, we present a model for the automatic generation of written dialogues, through the use of grammatical inference. This model allows the automatic recognition of grammars from a set dialogues employed as a training set. The inferred grammars are then used to generate templates of responses within the dialogues. The final objective is to apply this model in a specific domain dialogue system that answers questions in Spanish with the use of a knowledge base. The experiments carried out have been performend using the DIHANA project corpus which contains dialogues written in Spanish about schedules and prices of a rail system.
AlvarezG., RuizJ. and GarcíaP., Comparación de dos algoritmos recientes para inferencia gramatical de lenguajes regulares mediante autómatas no deterministas, Procesamiento del Lenguaje Natural, 2009, pages 21–36.
2.
AngluinD., Queries and concept learning, Machine Learning2 (4) (1988), 319–342.
BarlierM., PérolatJ., LarocheR. and PietquinO., Human-machine dialogue as a stochastic game. In Proceedings of the SIGDIAL 2015 Conference, The 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2–4 September 2015, Prague, Czech Republic, 2015, pages 2–11.
5.
Becerra-BonacheL., On the Learn ability of Mildly Context-Sensitive Languages using Positive Data and Correction Queries. PhD thesis, UNIVERSITAT ROVIRA I VIRGILI, FACULTAT DE LLETRES DEPARTAMENT DE FILOLOGIES ROMANIQUES, 2006.
6.
Becerra-BonacheL., Aproximación de la teoría de la inferencia gramatical a los estudios de adquisición del lenguaje, 2008, pages 327–338.
7.
BenedíJ., LieidaE., VaronaA., CastroM., GalianoI., JustoR., De LetonaI.L. and AntonioM., Design and acquisition of a telephone spontaneous speech dialogue corpus in spanish: Dihana. In In Fifth LREC, 2006, pages 1636–1639.
8.
CarrascoR.C. and OncinaJ., Learning stochastic regular grammars bymeans of a statemergingmethod. In Rafael C. Carrasco and Jose Oncina, editors, Grammatical Inference and Applications, pages 139–152, Berlin, Heidelberg, 1994. Springer Berlin Heidelberg.
9.
CosteF., FredouilleD., KermorvantC. and De la HigueraC., Introducing domain and typing bias in automata inference. In Georgios Paliouras and Yasubumi Sakakibara, editors, Grammatical Inference: Algorithms and Applications, pages 115–126, Berlin, Heidelberg, 2004. Springer Berlin Heidelberg.
10.
CurleyS.S. and HarangR.E., Grammatical inference and machine learning approaches to post-hoc langsec. In 2016 IEEE Security and Privacy Workshops (SPW), IEEE, 2016, pages 171–178.
11.
De la HigueraC., A bibliographical study of grammatical inference, Pattern Recognition38 (9) (2005), 1332–1348. Grammatical Inference.
12.
DusekO. and JuraícekF., A context-aware natural language generator for dialogue systems, CoRR, abs/1608.07076, 2016.
13.
FinkelJ.R., GrenagerT. and ManningC., Incorporating nonlocal information into information extraction systems by gibbs sampling. In Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, ACL ’05, pages 363–370, Stroudsburg, PA, USA, 2005. Association for Computational Linguistics.
14.
GoldE.M., Language identification in the limit, Information and Control10 (5) (1967), 447–474.
15.
GoldE Mark, Complexity of automaton identification from given data, Information and Control37 (3) (1978), 302–320.
16.
GriolD., HurtadoL., SanchisE. and SegarraE., Dos aproximaciones basadas en reglas para la gestión del diálogo, Procesamiento del Lenguaje Natural35 (2005), 213–220.
17.
KonstantopoulosS., An embodied dialogue system with personality and emotions. In Proceedings of the 2010 Workshop on Companionable Dialogue Systems, pages 31–36. Association for Computational Linguistics, 2010.
18.
LiJ., MonroeW., RitterA., JurafskyD., GalleyM. and GaoJ., Deep reinforcement learning for dialogue generation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas, USA, November 1-4, 2016, 2016, pages 1192–1202.
19.
LisonP., Probabilistic dialogue models with prior domain knowledge. In Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL ’12, pages 179–188, Stroudsburg, PA, USA, 2012. Association for Computational Linguistics.
LitmanD. and Forbes-RileyK., Evaluating a spoken dialogue system that detects and adapts to user affective states. pages 181–185, January 2014.
22.
MahadikS.K., Dialogue manager for spoken dialogue system : Review. 2017.
23.
MisuT., GeorgilaK., LeuskiA. and Traum.D., Reinforcement learning of question-answering dialogue policies for virtual museum guides. In Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL ’12, pages 84–93, Stroudsburg, PA, USA, 2012. Association for Computational Linguistics.
24.
PietquinO., Inverse reinforcement learning for interactive systems. In Proceedings of the 2nd Workshop on Machine Learning for Interactive Systems - Bridging the Gap Between Perception, Action and Communication, MLIS@IJCAI 2013, Beijing, China, August 4, 2013, 2013, pages 71–75.
25.
PietquinO., Inverse reinforcement learning for interactive systems. In Proceedings of the 2Nd Workshop on Machine Learning for Interactive Systems: Bridging the Gap Between Perception, Action and Communication, MLIS ’13, pages 71–75, New York, NY, USA, 2013. ACM.
26.
PngS.W. and PineauJ., Bayesian reinforcement learning for pomdp-based dialogue systems. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011, May 22-27, 2011, Prague Congress Center, Prague, Czech Republic, 2011, pages 2156–2159.
27.
SegarraE., SanchisE., GalianoM., GarcíaF. and HurtadoL.F., Extracting semantic information through automatic learning techniques, IJPRAI16 (3) (2002), 301–307.
28.
SordoniA., GalleyM., AuliM., BrockettC., JiY., MitchellM., NieJ.-Y., GaoJ. and DolanB., A Neural Network Approach to Context-Sensitive Generation of Conversational Responses. pages 196–205, Denver, Colorado, 2015. Association for Computational Linguistics.
29.
SutskeverI., VinyalsO. and LeQ.V., Sequence to sequence learning with neural networks, CoRR, abs/1409.3215, 2014.
30.
SuttonC.A. and McCallumA., An introduction to conditional random fields,, Foundations and Trends in Machine Learning4 (2010), 267–373.
31.
VidalE., ThollardF., de la HigueraC., CasacubertaF. and CarrascoR.C., Probabilistic finite-state machines – part ii, IEEE Transactions on Pattern Analysis and Machine Intelligence27 (2005), 1026–1039.
32.
VinyalsO. and LeQ.V., A neural conversational model, CoRR, abs/1506.05869, 2015.
33.
VázquezA., PintoD. and VilariñoD., Identificación de etiquetas semánticas para su uso en diálogos, Procesamiento del Lenguaje Natural, 2018, pages 99–107.
34.
WenT.-H., GasicM., MrksicN., SuP.-H., VandykeD. and YoungS.J., Semantically conditioned lstm-based natural language generation for spoken dialogue systems, CoRR, abs/1508.01745, 2015.
35.
YaoK., ZweigG. and PengB., Attention with intention for a neural network conversation model, CoRR, abs/1510.08565, 2015.
36.
YokomoriT., Grammatical Inference and Learning, pages 507–528. Springer Berlin Heidelberg, Berlin, Heidelberg, 2004.
37.
YoungS., GašicM., ThomsonB. and WilliamsJ.D., Pomdp-based statistical spoken dialog systems: A review, Proc. of the IEEE101 (5), 1160–1179, May 2013.
