Accession Number:

AD1167707

Title:

Dialogue-AMR Parsing Pipeline

Descriptive Note:

[Technical Report, Technical Report]

Corporate Author:

U.S. Army Combat Capabilities Development Command,Army Research Laboratory

Personal Author(s):

• Abrams, Mitchell
• Bonial, Claire
• Voss, Clare

Report Date:

2022-04-26

Pagination or Media Count:

28

Abstract:

This research forms part of a larger project focused on natural language understanding NLU in the development of a two-way humanrobot dialogue system in the search and navigation domain. We leverage Abstract Meaning Representation AMR to capture and structure the semantic content of natural language instructions in a machine-readable, directed, a-cyclic graph. Two key challenges exist for NLU in this task 1 how to effectively map AMR to a constrained robot-action specification within a particular domain and 2 how to preserve necessary elements for general understanding of human language with the goal that our robot may expand its capabilities beyond a single domain. To address these challenges, we establish a two-step NLU approach in which automatically obtained AMR graphs of the input language are converted into Dialogue-AMR graphs, which is a new version of AMR that is augmented with tense, aspect, and speech act information. Here, we detail both rule-based and classifier-based methods to transform AMR graphs into Dialogue-AMR graphs, thereby bridging the gap from unconstrained natural-language input to a fixed set of robot actions.

Descriptors:

• natural language processing
• supervised machine learning
• machine learning
• natural language understanding
• autonomous navigation
• language
• computational linguistics
• natural languages
• navigation
• standards
• computer languages
• linguistics
• abstracts
• artificial intelligence software
• computational science
• dialogue systems
• robot navigation

Subject Categories:

• Linguistics

Distribution Statement:

[A, Approved For Public Release]