Finding the Middle Ground - A Model for Planning Satisficing Answers

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 547–557, Berlin, Germany, August 7-12, 2016. c⃝2016 Association for Computational Linguistics Finding the Middle Ground - A Model for Planning Satisficing Answers Sabine Janzen Saarland University Saarbr¨ucken, Germany janzen@iss.uni-saarland.de Wolfgang Maaß Saarland University Saarbr¨ucken, Germany maass@iss.uni-saarland.de Tobias Kowatsch University of St. Gallen St. Gallen, Switzerland tobias.kowatsch@unisg.ch Abstract To establish sophisticated dialogue sys- tems, text planning needs to cope with congruent as well as incongruent inter- locutor interests as given in everyday di- alogues. Little attention has been given to this topic in text planning in contrast to di- alogues that are fully aligned with antic- ipated user interests. When considering dialogues with congruent and incongru- ent interlocutor interests, dialogue part- ners are facing the constant challenge of finding a balance between cooperation and competition. We introduce the concept of fairness that operationalize an equal and adequate, i.e. equitable satisfaction of all interlocutors’ interests. Focusing on Question-Answering (QA) settings, we describe an answer planning approach that support fair dialogues under congruent and incongruent interlocutor interests. Due to the fact that fairness is subjective per se, we present promising results from an empirical study (N=107) in which human subjects interacted with a QA system im- plementing the proposed approach. 1 Introduction For building dialogue systems that cope with con- tradictions and individual interests of dialog part- ners, text planning is required to process incon- gruent and congruent interests of interlocutors. So far, research on dialogue systems focusses on sup- porting dialogues that are fully aligned with antic- ipated user interests, e.g., (Hovy, 1991; Grosz and Kraus, 1996; Moore and Paris, 1993; Lochbaum, 1998; Rich and Sidner, 1997), and, thus, max- imizing cooperativeness (Bunt and Black, 2000, 191 p. 5). Few approaches exist that investi- gate text planning with pure conflict, e.g., (Jame- son et al., 1994; Hadjinikolis et al., 2013; Black and Atkinson, 2011; Prakken, 2006). When con- sidering dialogues with congruent as well as in- congruent interlocutors interests, dialogue part- ners are facing the constant challenge of finding a balance between cooperation and competition (Parikh, 2010). We introduce the concept of fair- ness that operationalize an equal and adequate, i.e. equitable satisfaction of all interlocutors’ in- terests (Oxford Dictionaries, 2016). Focusing on Question-Answering (QA) settings, we describe an answer planning approach that support fair dia- logues under congruent and incongruent interests of interlocutors. Due to the fact that fairness is subjective per se, we present results from an em- pirical study in which human subjects interacted with a QA system in various dialogue settings. When determining appropriate answers in text planning, approaches range from (1) wrong an- swer avoidance concepts technically checking the correctness of answers, e.g., Dong et al. (2011), and (2) opponent models in persuasion dialogues for choosing most suitable arguments, e.g., Had- jinikolis et al. (2013), to (3) the prediction of emo- tions of interlocutors to generate answers, e.g., Hasegawa et al. (2013). Here, related work is rel- evant that focuses on the determination of …

Content truncated to 500 words