Dialogue-AMR: Abstract Meaning Representation for Dialogue
Abstract
This paper describes a schema that enriches Abstract Meaning Representation (AMR) in order to provide a semantic representation for facilitating Natural Language Understanding (NLU) in dialogue systems. AMR offers a valuable level of abstraction of the propositional content of an utterance; however, it does not capture the illocutionary force or speakers intended contribution in the broader dialogue context (e.g., make a request or ask a question), nor does it capture tense or aspect. We explore dialogue in the domain of human-robot interaction, where a conversational robot is engaged in search and navigation tasks with a human partner. To address the limitations of standard AMR, we develop an inventory of speech acts suitable for our domain, and present "Dialogue-AMR", an enhanced AMR that represents not only the content of an utterance, but the illocutionary force behind it, as well as tense and aspect. To showcase the coverage of the schema, we use both manual and automatic methods to construct the "DialAMR" corpus - a corpus of human-robot dialogue annotated with standard AMR and our enriched Dialogue-AMR schema. Our automated methods can be used to incorporate AMR into a larger NLU pipeline supporting human-robot dialogue.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 11, 2020
- Accession Number
- AD1154255
Entities
People
- Claire N. Bonial
- Clare R. Voss
- David R Traum
- Lucia Donatelli
- Matthew Marge
- Mitchell Abrams
- Ron Artstein
- Stephanie M. Lukin
- Stephen Tratz
Organizations
- Saarland University
- United States Army Research Laboratory
- University of Southern California