Where’s Wally: The influence of visual salience on referring expression generation

Referring expression generation (REG) presents the converse problem to visualsearch: Given a scene and a specified target, how does one generate adescription which would allow somebody else to quickly and accurately locatethe target? Previous work in psycholinguistics and natural language processin...

Full description

Bibliographic Details
Main Authors: Alasdair Daniel Francis Clarke, Micha eElsner, Hannah eRohde
Format: Article
Language:English
Published: Frontiers Media S.A. 2013-06-01
Series:Frontiers in Psychology
Subjects:
Online Access:http://journal.frontiersin.org/Journal/10.3389/fpsyg.2013.00329/full
_version_ 1818501603041214464
author Alasdair Daniel Francis Clarke
Micha eElsner
Hannah eRohde
author_facet Alasdair Daniel Francis Clarke
Micha eElsner
Hannah eRohde
author_sort Alasdair Daniel Francis Clarke
collection DOAJ
description Referring expression generation (REG) presents the converse problem to visualsearch: Given a scene and a specified target, how does one generate adescription which would allow somebody else to quickly and accurately locatethe target? Previous work in psycholinguistics and natural language processingthat has addressed this question identifies only a limited role for vision inthis task. That previous work, which relies largely on simple scenes, tends totreat vision as a pre-process for extracting feature categories that arerelevant to disambiguation. However, the visual search literature suggeststhat some descriptions are better than others at enabling listeners to searchefficiently within complex stimuli. This paper presents the results of a studytesting whether speakers are sensitive to visual features that allow them tocompose such `good' descriptions. Our results show that visual properties(salience, clutter, area, and distance) influence REG for targets embedded inimages from the *Where's Wally?* books, which are an order of magnitudemore complex than traditional stimuli. Referring expressions for large salienttargets are shorter than those for smaller and less salient targets, and targets within highly cluttered scenes are described using more words.We also find that speakers are more likely to mention non-target landmarks thatare large, salient, and in close proximity to the target. These findingsidentfy a key role for visual salience in language production decisions and highlight the importance of scene complexity for REG.
first_indexed 2024-12-10T20:58:32Z
format Article
id doaj.art-3505a645462f4fc7894dfab9da57f831
institution Directory Open Access Journal
issn 1664-1078
language English
last_indexed 2024-12-10T20:58:32Z
publishDate 2013-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Psychology
spelling doaj.art-3505a645462f4fc7894dfab9da57f8312022-12-22T01:33:52ZengFrontiers Media S.A.Frontiers in Psychology1664-10782013-06-01410.3389/fpsyg.2013.0032949717Where’s Wally: The influence of visual salience on referring expression generationAlasdair Daniel Francis Clarke0Micha eElsner1Hannah eRohde2University of EdinburghThe Ohio State UniversityUniversity of EdinburghReferring expression generation (REG) presents the converse problem to visualsearch: Given a scene and a specified target, how does one generate adescription which would allow somebody else to quickly and accurately locatethe target? Previous work in psycholinguistics and natural language processingthat has addressed this question identifies only a limited role for vision inthis task. That previous work, which relies largely on simple scenes, tends totreat vision as a pre-process for extracting feature categories that arerelevant to disambiguation. However, the visual search literature suggeststhat some descriptions are better than others at enabling listeners to searchefficiently within complex stimuli. This paper presents the results of a studytesting whether speakers are sensitive to visual features that allow them tocompose such `good' descriptions. Our results show that visual properties(salience, clutter, area, and distance) influence REG for targets embedded inimages from the *Where's Wally?* books, which are an order of magnitudemore complex than traditional stimuli. Referring expressions for large salienttargets are shorter than those for smaller and less salient targets, and targets within highly cluttered scenes are described using more words.We also find that speakers are more likely to mention non-target landmarks thatare large, salient, and in close proximity to the target. These findingsidentfy a key role for visual salience in language production decisions and highlight the importance of scene complexity for REG.http://journal.frontiersin.org/Journal/10.3389/fpsyg.2013.00329/fullvisual searchvisual saliencyreferring expressionsvisual clutterreferring expression generation
spellingShingle Alasdair Daniel Francis Clarke
Micha eElsner
Hannah eRohde
Where’s Wally: The influence of visual salience on referring expression generation
Frontiers in Psychology
visual search
visual saliency
referring expressions
visual clutter
referring expression generation
title Where’s Wally: The influence of visual salience on referring expression generation
title_full Where’s Wally: The influence of visual salience on referring expression generation
title_fullStr Where’s Wally: The influence of visual salience on referring expression generation
title_full_unstemmed Where’s Wally: The influence of visual salience on referring expression generation
title_short Where’s Wally: The influence of visual salience on referring expression generation
title_sort where s wally the influence of visual salience on referring expression generation
topic visual search
visual saliency
referring expressions
visual clutter
referring expression generation
url http://journal.frontiersin.org/Journal/10.3389/fpsyg.2013.00329/full
work_keys_str_mv AT alasdairdanielfrancisclarke whereswallytheinfluenceofvisualsalienceonreferringexpressiongeneration
AT michaeelsner whereswallytheinfluenceofvisualsalienceonreferringexpressiongeneration
AT hannaherohde whereswallytheinfluenceofvisualsalienceonreferringexpressiongeneration