Abstract
Natural Language Generation (NLG) is a crucial component of a Spoken Dialogue System. Its task is to generate utterances with intended attributes like fluency, variation, readability, scalability and adequacy. As the handcrafted models are rigid and tedious to build, people have proposed many statistical and deep-learning based models to bring about more suitable options for generating utterance on a given Dialogue-Act (DA). This paper presents some Recurrent Neural Network Language Generation (RNNLG) framework based models along with their analysis of how they extract intended meaning in terms of content planning (modelling semantic input) and surface realization (final sentence generation) on a proposed unaligned Hindi dataset. The models have shown consistent performance on our natively developed dataset where the Modified-Semantically-Controlled LSTM (MSC-LSTM) performs better than all in terms of total slot-error (T-Error).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
DA-vector is a 1-hot encoded vector of action-type and slot-value-type where values are corresponding to occurrences of a given slot e.g. sv.name._1, sv.name._2.
- 3.
Here, token is used to represent both word and slot-token e.g. SLOT_NAME, SLOT_AREA etc. in a delexicalised sentence.
- 4.
- 5.
The Cambridge University Python Multi-domain Statistical Dialogue System Toolkit http://www.camdial.org/pydial/.
- 6.
Utterances having minimum slot-error (S-Error) are selected.
- 7.
Ex.: inform(name= ;pricerange= ;kidsallowed=yes;food= ).
References
Walker, M.A., Rambow, O.C., Rogati, M.: Training a sentence planner for spoken dialogue using boosting. Comput. Speech Lang. 16(3), 409–433 (2002). Spoken Language Generation
Stent, A., Prasad, R., Walker, M.: Trainable sentence planning for complex information presentation in spoken dialog systems. In: Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics, ACL 2004. Association for Computational Linguistics, Stroudsburg, PA, USA (2004)
Malviya, S., Tiwary, U.S.: Knowledge based summarization and document generation using bayesian network. Procedia Comput. Sci. 89, 333–340 (2016)
Langkilde, I., Knight, K.: Generation that exploits corpus-based statistical knowledge. In: Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, ACL 1998/COLING 1998, Stroudsburg, PA, USA, pp. 704–710 (1998)
Rieser, V., Lemon, O.: Natural language generation as planning under uncertainty for spoken dialogue systems. In: Proceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009), pp. 683–691. Association for Computational Linguistics, Athens, Greece, March 2009
Oh, A.H., Rudnicky, A.I.: Stochastic language generation for spoken dialogue systems. In: ANLP-NAACL 2000 Workshop: Conversational Systems (2000)
Mairesse, F., et al.: Phrase-based statistical language generation using graphical models and active learning. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 1552–1561 (2010)
Mairesse, F., Young, S.: Stochastic language generation in dialogue using factored language models. Comput. Linguist. 40(4), 763–799 (2014)
Konstas, I., Lapata, M.: A global model for concept-to-text generation. J. Artif. Intell. Res. 48, 305–346 (2013)
Dušek, O., Jurčíček, F.: Sequence-to-sequence generation for spoken dialogue via deep syntax trees and strings. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). pp. 45–51. Berlin, Germany (Aug 2016)
Mei, H., Bansal, M., Walter, M.R.: What to talk about and how? selective generation using LSTMs with coarse-to-fine alignment. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics, San Diego, California, pp. 720–730 (2016)
Wen, T.H., Gašić, M., Mrkšić, N., Su, P.H., Vandyke, D., Young, S.: Semantically conditioned LSTM-based natural language generation for spoken dialogue systems. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal, pp. 1711–1721, September 2015
Wen, T.H., Young, S.: Recurrent neural network language generation for spoken dialogue systems. Comput. Speech Lang. 63, 101017 (2020)
Jain, S., Malviya, S., Mishra, R., Tiwary, U.S.: Sentiment analysis: An empirical comparative study of various machine learning approaches. In: Proceedings of the 14th International Conference on Natural Language Processing (ICON-2017), pp. 112–121. NLP Association of India, Kolkata, India, December 2017
Jurčíček, F., Dušek, O., Plátek, O., Žilka, L.: Alex: a statistical dialogue systems framework. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds.) TSD 2014. LNCS (LNAI), vol. 8655, pp. 587–594. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10816-2_71
Hu, Z., Halberg, G., Jimenez, C.R., Walker, M.A.: Entrainment in pedestrian direction giving: how many kinds of entrainment? In: Rudnicky, A., Raux, A., Lane, I., Misu, T. (eds.) Situated Dialog in Speech-Based Human-Computer Interaction. SCT, pp. 151–164. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-21834-2_14
Mikolov, T., Karafiát, M., Burget, L., Černocký, J., Khudanpur, S.: Recurrent neural network based language model. In: Eleventh Annual Conference of the International Speech Communication Association (2010)
Dhariya, O., Malviya, S., Tiwary, U.S.: A hybrid approach for hindi-english machine translation. In: 2017 International Conference on Information Networking (ICOIN), pp. 389–394. IEEE (2017)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of the ICLR (2015)
Wu, Y., et al.: Google’s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Singh, S., Malviya, S., Mishra, R., Barnwal, S.K., Tiwary, U.S. (2020). RNN Based Language Generation Models for a Hindi Dialogue System. In: Tiwary, U., Chaudhury, S. (eds) Intelligent Human Computer Interaction. IHCI 2019. Lecture Notes in Computer Science(), vol 11886. Springer, Cham. https://doi.org/10.1007/978-3-030-44689-5_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-44689-5_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-44688-8
Online ISBN: 978-3-030-44689-5
eBook Packages: Computer ScienceComputer Science (R0)