Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner

Proceedings of the 22nd Conference on Computational Natural Language Learning (CoNLL 2018), pages 551–561 Brussels, Belgium, October 31 - November 1, 2018. c⃝2018 Association for Computational Linguistics 551 Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner Yury Zemlyanskiy University of Southern California Los Angeles, CA 90089 yury.zemlyanskiy@usc.edu Fei Sha Netflix Los Angeles, CA 90028 fsha@netflix.com∗ Abstract There have been several attempts to define a plausible motivation for a chit-chat dialogue agent that can lead to engaging conversations. In this work, we explore a new direction where the agent specifically focuses on discovering information about its interlocutor. We formal- ize this approach by defining a quantitative metric. We propose an algorithm for the agent to maximize it. We validate the idea with hu- man evaluation where our system outperforms various baselines. We demonstrate that the metric indeed correlates with the human judg- ments of engagingness. 1 Introduction There has been a significant progress in creat- ing end-to-end data-driven dialogue systems (Rit- ter et al., 2011; Vinyals and Le, 2015; Serban et al., 2017; Shang et al., 2015; Sordoni et al., 2015). The general scheme is to view dialogues as a sequence transduction process. This process is then modeled with the sequence-to-sequence (SEQ2SEQ) neural network (Sutskever et al., 2014) whose parameters are fit on large dialogue corpora such as OpenSubtitles (Tiedemann, 2009). What is especially appealing about these systems is that they do not require hand-crafted rules to generate reasonable responses in the open-domain dialogue (i.e., chit-chat) setting. An important goal of such systems is to be able to have a meaningful and engaging conversation with a real person. Despite the progress, how- ever, this goal remains elusive — current systems often generate generic and universally applicable responses (to any questions) such as “I do not know”. While such responses are reasonable in isolation, collectively too many of them are per- ∗On leave from U. of Southern California (feisha@usc.edu) ceived as dull and repetitive (Sordoni et al., 2015; Serban et al., 2017; Li et al., 2016a,b). It remains open what metrics to use to optimize a data-driven model to produce highly engaging dialogues (Liu et al., 2016). Li et al. (2016b,a) propose to use several heuristic criteria: how easy to answer the utterance with non-generic response, how grammatical the response is, etc. Zhang et al. (2018) suggests to use pre-defined facts about the conversation agents as the context for the dialogue. Specifically, conditioning on those facts (called “memories” in their approach), the dialogue be- comes “personalized”, purposefully coherent and is perceived being more engaging. In this paper, we investigate a different ap- proach which leverages the following intuition: an engaging dialogue between two agents is a conver- sation that is focused and intends to discover infor- mation with the goal of increased understanding of each other. In other words, discovering implies asking engaging and inquisitive questions that are not meant to be answered with dull responses. How do we use these intuitions to build engag- ing dialogue …

Content truncated to 500 words