Generating Discourse Inferences from Unscoped Episodic Logical Formulas

Kim, Gene Louis; Kane, Benjamin; Duong, Viet; Mendiratta, Muskaan; McGuire, Graeme; Sackstein, Sophie; Platonov, Georgiy; Schubert, Lenhart K.

doi:10.18653/v1/w19-3306

Cited by 4 publications

(2 citation statements)

References 16 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DM additionally has a limited module for generating and responding to pragmatic inferences, based on the work in [9]. In the case where either no times or no relations are obtained, and the question contains a presupposition (e.g.…”

Section: Interpreting Historical Questionsmentioning

confidence: 99%

History-Aware Question Answering in a Blocks World Dialogue System

Kane,

Platonov,

Schubert

2020

Preprint

Self Cite

View full text Add to dashboard Cite

It is essential for dialogue-based spatial reasoning systems to maintain memory of historical states of the world. In addition to conveying that the dialogue agent is mentally present and engaged with the task, referring to historical states may be crucial for enabling collaborative planning (e.g., for planning to return to a previous state, or diagnosing a past misstep). In this paper, we approach the problem of spatial memory in a multi-modal spoken dialogue system capable of answering questions about interaction history in a physical blocks world setting. This work builds upon a full spatial question-answering pipeline consisting of a vision system, speech input and output mediated by an animated avatar, a dialogue system that robustly interprets spatial queries, and a constraint solver that derives answers based on 3-D spatial modelling. The contributions of this work include a symbolic dialogue context registering knowledge about discourse history and changes in the world, as well as a natural language understanding module capable of interpreting free-form historical questions and querying the dialogue context to form an answer.

show abstract

Section: Interpreting Historical Questionsmentioning

confidence: 99%

History-Aware Question Answering in a Blocks World Dialogue System

Kane,

Platonov,

Schubert

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Though not strictly speech acts, the interconnected approach to meaning that this corpus annotates is directly relevant for deducing illocutionary force in a dialogue context. Kim et al (2019) similarly describe an annotation schema designed to capture discourse inferences via underlying semantic scope relations. Hajicova (2019) outlines an argument for modeling information and discourse relations explicitly in meaning representations.…”

Section: Related Workmentioning

confidence: 99%

Augmenting Abstract Meaning Representation for Human-Robot Dialogue

Bonial¹,

Donatelli²,

Lukin³

et al. 2019

Proceedings of the First International Workshop on Designing Meaning Representations

View full text Add to dashboard Cite

We detail refinements made to Abstract Meaning Representation (AMR) that make the representation more suitable for supporting a situated dialogue system, where a human remotely controls a robot for purposes of search and rescue and reconnaissance. We propose 36 augmented AMRs that capture speech acts, tense and aspect, and spatial information. This linguistic information is vital for representing important distinctions, for example whether the robot has moved, is moving, or will move. We evaluate two existing AMR parsers for their performance on dialogue data. We also outline a model for graph-to-graph conversion, in which output from AMR parsers is converted into our refined AMRs. The design scheme presented here, though task-specific, is extendable for broad coverage of speech acts using AMR in future task-independent work.

show abstract