Coherence, Symbol Grounding and Interactive Task Learning

Mattias Appelgren, Alex Lascarides

Research output: Chapter in Book/Report/Conference proceedingConference contribution


To teach agents through natural language interaction, we need methods for updating the agent’s knowledge, given a teacher’s feedback. But natural language is ambiguous at many levels and so a major challenge is for the agent to disambiguate the intended message, given the signal and the context in which it’s uttered. In this paper we look at how coherence relations can be used to help disambiguate the teachers’ feedback and so contribute to the agent’s reasoning about how to solve their domain-level task. We conduct experiments where the agent must learn to build towers that comply with a set of rules, which the agent starts out ignorant of. It is also unaware of the concepts used to express the rules. We extend a model for learning these tasks which is based on coherence and show experimentally that our extensions can improve how fast the agent learns.
Original languageEnglish
Title of host publicationProceedings of the 23rd Workshop on the Semantics and Pragmatics of Dialogue (SEMDIAL)
Place of PublicationQueen Mary University, London
Number of pages9
Publication statusPublished - 30 Sep 2019
Event23rd Workshop on the Semantics and Pragmatics of Dialogue (SEMDIAL) - London, United Kingdom
Duration: 4 Sep 20196 Sep 2019


Workshop23rd Workshop on the Semantics and Pragmatics of Dialogue (SEMDIAL)
Abbreviated titleSemDial 2019 - LondonLogue
Country/TerritoryUnited Kingdom
Internet address


Dive into the research topics of 'Coherence, Symbol Grounding and Interactive Task Learning'. Together they form a unique fingerprint.

Cite this