Incorporating Politeness across Languages in Customer Care Responses: Towards building a Multi-lingual Empathetic Dialogue Agent

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 4172–4182 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 4172 Incorporating Politeness across Languages in Customer Care Responses: Towards building a Multi-lingual Empathetic Dialogue Agent Mauajama Firdaus, Asif Ekbal, Pushpak Bhattacharyya Indian Institute of Technology Patna Bihta, Bihar-801106, India {mauajama.pcs16, asif, pb}@iitp.ac.in Abstract Customer satisfaction is an essential aspect of customer care systems. It is imperative for such systems to be polite while handling the customer requests or demands. In this paper, we present a large multi-lingual conversational dataset for En- glish and Hindi. We choose data from Twitter having both generic and courteous responses between customer care agents and aggrieved users. We also propose strong baselines that can induce courteous behaviour in generic customer care re- sponse in a multi-lingual scenario. We build a deep learning framework that can simultaneously handle different languages and incorporate polite behaviour in the customer care agent’s responses. Our system is competent in generating responses in different languages (here, English and Hindi) depending on the customer’s preference and also is able to converse with humans in an empathetic manner to ensure customer satisfaction and retention. Experimental results show that our proposed models can converse in both the languages and the information shared between the languages helps in improving the performance of the overall system. Qualitative and quantitative analysis show that the proposed method can con- verse in an empathetic manner by incorporating courteousness in the responses and hence increasing customer satisfaction. Keywords: Courteous, Response generation, Deep Learning, Multilingualism 1. Introduction With the growth and progress in artificial intelligence (AI) along with natural language processing (NLP), dialogue systems have made a huge impact on humans by helping them in their daily works. Dialogue sys- tems are perfect examples of human-computer interac- tions. Such systems are highly prevalent nowadays in the form of chatbots and personal assistants like Ap- ple’s Siri, Microsoft’s Cortana, Amazon’s Alexa, and many more. The primary objective of these automated applications is to assist humans and help them in the smallest possible ways as humanly as possible. Natural lan- guage generation (NLG) module of every dialogue sys- tem is an essential component as it presents the in- formation to the user. To enhance the interactions between human and computers, recently researchers have focused on adapting different styles, emotions and personalities in text generation. Recent research has been inclined to make the system understand dif- ferent languages giving rise to multi-lingual applica- tions. With the significant focus on making the com- puter understand different languages as in (Masumura et al., 2018b; Masumura et al., 2018a; Upadhyay et al., 2018), researchers are aiming to make the dialogue systems language invariant as in real-world scenario. Also, for more extensive applications, it is crucial for these systems to be able to converse with humans in their preferred language, thereby increasing the usage and advancement of technology. Providing assistance to the customer through social media channels is attaining high …

Content truncated to 500 words