Conversational Semantic Parsing for Dialog State Tracking

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 8107–8117, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 8107 Conversational Semantic Parsing for Dialog State Tracking Jianpeng Cheng Devang Agrawal H´ector Mart´ınez Alonso Shruti Bhargava Joris Driesen Federico Flego Dain Kaplan Dimitri Kartsaklis Lin Li Dhivya Piraviperumal Jason D Williams Hong Yu Diarmuid ´O S´eaghdha Anders Johannsen Apple {jianpeng.cheng,hmartinezalonso,shruti bhargava,joris driesen, fflego,dain kaplan,dkartsaklis,lli9,dhivyaprp,jason williams4, hong yu,doseaghdha,ajohannsen}@apple.com Abstract We consider a new perspective on dialog state tracking (DST), the task of estimating a user’s goal through the course of a dialog. By formulating DST as a semantic parsing task over hierarchical representations, we can incorporate semantic compositionality, cross- domain knowledge sharing and co-reference. We present TreeDST, a dataset of 27k conversations annotated with tree-structured dialog states and system acts.1 We describe an encoder-decoder framework for DST with hierarchical representations, which leads to 20% improvement over state-of-the-art DST approaches that operate on a flat meaning space of slot-value pairs. 1 Introduction Task-based dialog systems, for example digital personal assistants, provide a linguistic user interface for all kinds of applications: from searching a database, booking a hotel, checking the weather to sending a text message. In order to understand the user, the system must be able to both parse the meaning of an utterance and relate it to the context of the conversation so far. While lacking the richness of a conversation between two humans, the dynamics of human-machine interaction can still be complex: the user may change their mind, correct a misunderstanding or refer back to previously-mentioned information. Language understanding for task-based dialog is often termed “dialog state tracking” (DST) (Williams et al., 2016), the mental model being that the intent of the user is a partially-observed state that must be re-estimated at every turn given new information. The dialog state is typically modelled as a set of independent slots, and a standard DST system will maintain a distribution 1The dataset is available at https://github.com/ apple/ml-tree-dst. over values for each slot. In contrast, language understanding for other NLP applications is often formulated as semantic parsing, which is the task of converting a single-turn utterance to a graph- structured meaning representation. Such meaning representations include logical forms, database queries and other programming languages. These two perspectives on language understanding—DST and semantic parsing— have complementary strengths and weaknesses. DST targets a fuller range of conversational dynamics but typically uses a simple and limiting meaning representation. Semantic parsing embraces a compositional view of meaning. By basing meaning on a space of combinable, reusable parts, compositionality can make the NLU problem space more tractable (repeated concepts must only be learned once) and more expressive (it becomes possible to represent nested intents). At the same time, most semantic parsing research treats a sentence as an isolated observation, detached from conversational context. This work unifies the two perspectives by reformulating DST as conversational semantic parsing. As in DST, the task is to track a user’s goal as it accumulates over the course of a …

Content truncated to 500 words