Speaker-dependent variation in content selection for referring expression generation

Jette Viethen, Robert Dale

Research output: Contribution to journalConference paper

Abstract

In this paper we describe machine learning experiments that aim to characterise the content selection process for distinguishing descriptions. Our experiments are based on two large corpora of human-produced descriptions of objects in relatively small visual scenes; the referring expressions are annotated with their semantic content. The visual context of reference is widely considered to be a primary determinant of content in referring expression generation, so we explore whether a model can be trained to predict the collection of descriptive attributes that should be used in a given situation. Our experiments demonstrate that speaker-specific preferences play a much more important role than existing approaches to referring expression generation acknowledge.
Original languageEnglish
Pages (from-to)81-89
Number of pages9
JournalAustralasian Language Technology Workshop 2010 : proceedings of the workshop
Volume8
Publication statusPublished - 2010
EventAustralasian Language Technology Workshop (8th : 2010) - Melbourne, Australia
Duration: 9 Dec 201010 Dec 2010

Fingerprint Dive into the research topics of 'Speaker-dependent variation in content selection for referring expression generation'. Together they form a unique fingerprint.

Cite this