Bootstrapping Semantic Parsers from Conversations

Conversations provide rich opportunities for interactive, continuous learning. When something goes wrong, a system can ask for clarification, rewording, or otherwise redirect the interaction to achieve its goals. In this paper, we present an approach for using conversational interactions of this type to induce semantic parsers. We demonstrate learning without any explicit annotation of the meanings of user utterances. Instead, we model meaning with latent variables, and introduce a loss function to measure how well potential meanings match the conversation. This loss drives the overall learning approach, which induces a weighted CCG grammar that could be used to automatically bootstrap the semantic analysis component in a complete dialog system. Experiments on DARPA Communicator conversational logs demonstrate effective learning, despite requiring no explicit meaning annotations.

• Type: Journal
• Year: 2011
• Where: EMNLP
• Authors: Yoav Artzi, Luke S. Zettlemoyer
• Keywords: Conversational Interactions, Darpa Communicator, EMNLP 2011, Latent Variables, Natural Language Processing