Planning, Inference and Pragmatics in Sequential Language Games

Planning, Inference and Pragmatics in Sequential Language Games Fereshte Khani Stanford University fereshte@stanford.edu Noah D. Goodman Stanford University ngoodman@stanford.edu Percy Liang Stanford University pliang@cs.stanford.edu Abstract We study sequential language games in which two players, each with private information, communicate to achieve a common goal. In such games, a successful player must (i) in- fer the partner’s private information from the partner’s messages, (ii) generate messages that are most likely to help with the goal, and (iii) reason pragmatically about the partner’s strat- egy. We propose a model that captures all three characteristics and demonstrate their im- portance in capturing human behavior on a new goal-oriented dataset we collected using crowdsourcing. 1 Introduction Human communication is extraordinarily rich. Peo- ple routinely choose what to say based on their goals (planning), figure out the state of the world based on what others say (inference), all while tak- ing into account that others are strategizing agents too (pragmatics). All three aspects have been stud- ied in both the linguistics and AI communities. For planning, Markov Decision Processes and their ex- tensions can be used to compute utility-maximizing actions via forward-looking recurrences (e.g., Vo- gel et al. (2013a)). For inference, model-theoretic semantics (Montague, 1973) provides a mechanism for utterances to constrain possible worlds, and this has been implemented recently in semantic parsing (Matuszek et al., 2012; Krishnamurthy and Kollar, 2013). Finally, for pragmatics, the cooperative prin- ciple of Grice (1975) can be realized by models in which a speaker simulates a listener—e.g., Franke (2009) and Frank and Goodman (2012). Find B2 Find B2 B ? B ? C ? Pletter view ? 2 ? 3 ? 2 Pdigit view Pletter: square Pdigit: circle Pletter: click (1,3) Planning: Let me first try square, which is just one possibility. Inference: The square’s letter must be B. Pragmatics: The square’s digit can- not be 2. Figure 1: A game of InfoJigsaw played by two hu- man players. One of the players (Pletter) only sees the letters, while the other one (Pdigit) only sees the digits. Their goal is to identify the goal object, B2, by exchanging a few words. The clouds show the hypothesized role of planning, inference, and prag- matics in the players’ choice of utterances. In this game, the bottom object is the goal (position (1, 3)). There have been a few previous efforts in the lan- guage games literature to combine the three aspects. Hawkins et al. (2015) proposed a model of commu- nication between a questioner and an answerer based on only one round of question answering. Vogel et al. (2013b) proposed a model of two agents playing a restricted version of the game from the Cards Cor- pus (Potts, 2012), where the agents only communi- cate once.1 In this work, we seek to capture all three aspects in a single, unified framework which allows 1Specifically, two agents must both co-locate with a specific card. The agent which finds the card sooner shares the card location information with the other agent. 543 Transactions …

Content truncated to 500 words