Using Lexical Alignment and Referring Ability to Address Data Sparsity in Situated Dialog Reference Resolution

Todd Shore, Gabriel Skantze


Abstract
Referring to entities in situated dialog is a collaborative process, whereby interlocutors often expand, repair and/or replace referring expressions in an iterative process, converging on conceptual pacts of referring language use in doing so. Nevertheless, much work on exophoric reference resolution (i.e. resolution of references to entities outside of a given text) follows a literary model, whereby individual referring expressions are interpreted as unique identifiers of their referents given the state of the dialog the referring expression is initiated. In this paper, we address this collaborative nature to improve dialogic reference resolution in two ways: First, we trained a words-as-classifiers logistic regression model of word semantics and incrementally adapt the model to idiosyncratic language between dyad partners during evaluation of the dialog. We then used these semantic models to learn the general referring ability of each word, which is independent of referent features. These methods facilitate accurate automatic reference resolution in situated dialog without annotation of referring expressions, even with little background data.
Anthology ID:
D18-1252
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2288–2297
Language:
URL:
https://www.aclweb.org/anthology/D18-1252
DOI:
10.18653/v1/D18-1252
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D18-1252.pdf
Attachment:
 D18-1252.Attachment.pdf
Video:
 https://vimeo.com/305936322