Atlas.txt: Exploring Lingusitic Grounding Techniques for Communicating Spatial Information to Blind Users

Kavita E. Thomas, Somayajulu Sripada, Matthijs L. Noordzij

Research output: Contribution to journalArticle

6 Citations (Scopus)
5 Downloads (Pure)

Abstract

This paper describes exploratory research into automatically describing geo-referenced information to blind people. The goal is to produce texts giving an overview of the spatial layout, and a central concern of such texts is that they employ an appropriate linguistic reference frame which enables blind hearers to ground the information. The research presented in this paper was based on two hypotheses: (1) directly perceivable reference frames are easier to ground, and (2) spatial descriptions drawn from composite reference frame systems composed of more than one reference frame are easier to ground. An experiment exploring text comprehension on a range of texts employing different reference frame systems is presented. The main results indicate that the
second hypothesis is supported. A prototype of a natural language generation system which generates texts describing geo-referenced information from data is described.
Original languageEnglish
Pages (from-to)85-98
Number of pages14
JournalUniversal Access in the Information Society
Volume11
Issue number1
Early online date31 Dec 2010
DOIs
Publication statusPublished - Mar 2012

Fingerprint

Electric grounding
Linguistics
Composite materials
Experiments

Keywords

  • blind users
  • geo-referenced spatial information
  • natural language generation
  • reference frame preference

Cite this

Atlas.txt : Exploring Lingusitic Grounding Techniques for Communicating Spatial Information to Blind Users. / Thomas, Kavita E.; Sripada, Somayajulu; Noordzij, Matthijs L.

In: Universal Access in the Information Society, Vol. 11, No. 1, 03.2012, p. 85-98.

Research output: Contribution to journalArticle

@article{dde32202c1754c7dac970af54189de8f,
title = "Atlas.txt: Exploring Lingusitic Grounding Techniques for Communicating Spatial Information to Blind Users",
abstract = "This paper describes exploratory research into automatically describing geo-referenced information to blind people. The goal is to produce texts giving an overview of the spatial layout, and a central concern of such texts is that they employ an appropriate linguistic reference frame which enables blind hearers to ground the information. The research presented in this paper was based on two hypotheses: (1) directly perceivable reference frames are easier to ground, and (2) spatial descriptions drawn from composite reference frame systems composed of more than one reference frame are easier to ground. An experiment exploring text comprehension on a range of texts employing different reference frame systems is presented. The main results indicate that the second hypothesis is supported. A prototype of a natural language generation system which generates texts describing geo-referenced information from data is described.",
keywords = "blind users, geo-referenced spatial information, natural language generation, reference frame preference",
author = "Thomas, {Kavita E.} and Somayajulu Sripada and Noordzij, {Matthijs L.}",
year = "2012",
month = "3",
doi = "10.1007/s10209-010-0217-5",
language = "English",
volume = "11",
pages = "85--98",
journal = "Universal Access in the Information Society",
issn = "1615-5289",
publisher = "Springer Verlag",
number = "1",

}

TY - JOUR

T1 - Atlas.txt

T2 - Exploring Lingusitic Grounding Techniques for Communicating Spatial Information to Blind Users

AU - Thomas, Kavita E.

AU - Sripada, Somayajulu

AU - Noordzij, Matthijs L.

PY - 2012/3

Y1 - 2012/3

N2 - This paper describes exploratory research into automatically describing geo-referenced information to blind people. The goal is to produce texts giving an overview of the spatial layout, and a central concern of such texts is that they employ an appropriate linguistic reference frame which enables blind hearers to ground the information. The research presented in this paper was based on two hypotheses: (1) directly perceivable reference frames are easier to ground, and (2) spatial descriptions drawn from composite reference frame systems composed of more than one reference frame are easier to ground. An experiment exploring text comprehension on a range of texts employing different reference frame systems is presented. The main results indicate that the second hypothesis is supported. A prototype of a natural language generation system which generates texts describing geo-referenced information from data is described.

AB - This paper describes exploratory research into automatically describing geo-referenced information to blind people. The goal is to produce texts giving an overview of the spatial layout, and a central concern of such texts is that they employ an appropriate linguistic reference frame which enables blind hearers to ground the information. The research presented in this paper was based on two hypotheses: (1) directly perceivable reference frames are easier to ground, and (2) spatial descriptions drawn from composite reference frame systems composed of more than one reference frame are easier to ground. An experiment exploring text comprehension on a range of texts employing different reference frame systems is presented. The main results indicate that the second hypothesis is supported. A prototype of a natural language generation system which generates texts describing geo-referenced information from data is described.

KW - blind users

KW - geo-referenced spatial information

KW - natural language generation

KW - reference frame preference

U2 - 10.1007/s10209-010-0217-5

DO - 10.1007/s10209-010-0217-5

M3 - Article

VL - 11

SP - 85

EP - 98

JO - Universal Access in the Information Society

JF - Universal Access in the Information Society

SN - 1615-5289

IS - 1

ER -