Abstract
The recent rapid developments in neural networks have stimulated significant performance progress in detecting breakdown in dialogue. The existing research focuses on detecting breakdown from the data label using different features such as word similarity and topic transition; however, these features are insufficient to capture contextual features. Therefore, we used ELMo language model to extract the contextual feature to help to detect the breakdown which faces a challenge due to the basis of human opinion. Another crucial challenge facing breakdown detection is the lack annotated dataset. To take this challenge we used sentiment as the data label with contextualized ELMo embedding model to detect the breakdown in dialogue. The model was evaluated with state-of-the-art models and the results shows the proposed model outperforms other models.
Fully documented templates are available in the elsarticle package on CTAN.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Tsunomori, Y., Higashinaka, R., Takahashi, T., Inaba, M.: Evaluating dialogue breakdown detection in chat-oriented dialogue systems (2018)
Takayama, J., Nomoto, E., Arase, Y.: Dialogue breakdown detection considering annotation biases. In: Proceedings of the Dialog System Technology Challenge 6 Workshop (DSTC6) (2017)
Ge, L., Moh, T.-S.: Improving text classification with word embedding. In: 2017 IEEE International Conference on Big Data (Big Data), pp. 1796–1805. IEEE (2017)
Mikolov, T., Le, Q.V., Sutskever, I.: Exploiting similarities among languages for machine translation. arXiv preprint arXiv:1309.4168 (2013)
Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)
Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135–146 (2017)
Peters, M.E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., Zettlemoyer, L.: Deep contextualized word representations. arXiv preprint arXiv:1802.05365 (2018)
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C.D., Ng, A.Y., Potts, C.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1631–1642 (2013)
Sang, E.F., De Meulder, F.: Introduction to the CoNLL-2003 shared task: language-independent named entity recognition, arXiv preprint arXiv:cs/0306050 (2003)
Sugiyama, H.: Dialogue breakdown detection based on estimating appropriateness of topic transition. In: Dialog System Technology Challenges (DSTC6) (2017)
Horii, T., Mori, H., Araki, M.: Breakdown detector for chat-oriented dialogue, pp. 119–127. Springer, Singapore (2017). https://doi.org/10.1007/978-981-10-2585-3_9
Sugiyama, H.: Empirical feature analysis for dialogue breakdown detection. Comput. Speech Lang. 54, 140–150 (2019)
Takayama, J., Nomoto, E., Arase, Y.: Dialogue breakdown detection robust to variations in annotators and dialogue systems. Comput. Speech Lang. 54, 31–43 (2019)
Xie, Z., Ling, G.: Dialogue breakdown detection using hierarchical bi-directional LSTMs. In: Proceedings of the Dialog System Technology Challenges Workshop (DSTC6) (2017)
Lee, S., Lee, D., Hooshyar, D., Jo, J., Lim, H.: Integrating breakdown detection into dialogue systems to improve knowledge management: encoding temporal utterances with memory attention. Inf. Technol. Manag. 21(1), 51–59 (2020)
Almansor, E.H., Hussain, F.K.: Modeling the chatbot quality of services (CQoS) using word embedding to intelligently detect inappropriate responses. In: International Conference on Advanced Information Networking and Applications, pp. 60–70. Springer (2020)
Higashinaka, R., Funakoshi, K., Araki, M., Tsukahara, H., Kobayashi, Y., Mizukami, M.: Towards taxonomy of errors in chat-oriented dialogue systems. In: Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 87–95 (2015)
Hutto, C.J., Gilbert, E.: VADER: a parsimonious rule-based model for sentiment analysis of social media text. In: Eighth International AAAI Conference on Weblogs and Social Media (2014)
Brownlee, J.: Master Machine Learning Algorithms: discover how they work and implement them from scratch (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Almansor, E.H., Hussain, F.K. (2021). Sentiment-Driven Breakdown Detection Model Using Contextual Embedding ElMo. In: Barolli, L., Woungang, I., Enokido, T. (eds) Advanced Information Networking and Applications. AINA 2021. Lecture Notes in Networks and Systems, vol 225. Springer, Cham. https://doi.org/10.1007/978-3-030-75100-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-75100-5_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75099-2
Online ISBN: 978-3-030-75100-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)