Detecting mild cognitive impairment by exploiting linguistic information from transcripts

Veronika Vincze, Gábor Gosztolya, László Tóth, Ildikó Hoffmann, Gréta Szatlóczki, Zoltán Bánréti, M. Pákáski, J. Kálmán

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Here we seek to automatically identify Hungarian patients suffering from mild cognitive impairment (MCI) based on linguistic features collected from their speech transcripts. Our system uses machine learning techniques and is based on several linguistic features like characteristics of spontaneous speech as well as features exploiting morphological and syntactic parsing. Our results suggest that it is primarily morphological and speechbased features that help distinguish MCI patients from healthy controls.

Original languageEnglish
Title of host publication54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages181-187
Number of pages7
ISBN (Electronic)9781510827592
Publication statusPublished - Jan 1 2016
Event54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Berlin, Germany
Duration: Aug 7 2016Aug 12 2016

Other

Other54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
CountryGermany
CityBerlin
Period8/7/168/12/16

Fingerprint

Linguistics
linguistics
Syntactics
Hungarian
Learning systems
learning
Mild Cognitive Impairment
Linguistic Features
Spontaneous Speech
Syntactic Parsing
Machine Learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Linguistics and Language
  • Software
  • Language and Linguistics

Cite this

Vincze, V., Gosztolya, G., Tóth, L., Hoffmann, I., Szatlóczki, G., Bánréti, Z., ... Kálmán, J. (2016). Detecting mild cognitive impairment by exploiting linguistic information from transcripts. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers (pp. 181-187). Association for Computational Linguistics (ACL).

Detecting mild cognitive impairment by exploiting linguistic information from transcripts. / Vincze, Veronika; Gosztolya, Gábor; Tóth, László; Hoffmann, Ildikó; Szatlóczki, Gréta; Bánréti, Zoltán; Pákáski, M.; Kálmán, J.

54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers. Association for Computational Linguistics (ACL), 2016. p. 181-187.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Vincze, V, Gosztolya, G, Tóth, L, Hoffmann, I, Szatlóczki, G, Bánréti, Z, Pákáski, M & Kálmán, J 2016, Detecting mild cognitive impairment by exploiting linguistic information from transcripts. in 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers. Association for Computational Linguistics (ACL), pp. 181-187, 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, Berlin, Germany, 8/7/16.
Vincze V, Gosztolya G, Tóth L, Hoffmann I, Szatlóczki G, Bánréti Z et al. Detecting mild cognitive impairment by exploiting linguistic information from transcripts. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers. Association for Computational Linguistics (ACL). 2016. p. 181-187
Vincze, Veronika ; Gosztolya, Gábor ; Tóth, László ; Hoffmann, Ildikó ; Szatlóczki, Gréta ; Bánréti, Zoltán ; Pákáski, M. ; Kálmán, J. / Detecting mild cognitive impairment by exploiting linguistic information from transcripts. 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers. Association for Computational Linguistics (ACL), 2016. pp. 181-187
@inproceedings{e3da3fe265b543a48b765b9be4ccc12f,
title = "Detecting mild cognitive impairment by exploiting linguistic information from transcripts",
abstract = "Here we seek to automatically identify Hungarian patients suffering from mild cognitive impairment (MCI) based on linguistic features collected from their speech transcripts. Our system uses machine learning techniques and is based on several linguistic features like characteristics of spontaneous speech as well as features exploiting morphological and syntactic parsing. Our results suggest that it is primarily morphological and speechbased features that help distinguish MCI patients from healthy controls.",
author = "Veronika Vincze and G{\'a}bor Gosztolya and L{\'a}szl{\'o} T{\'o}th and Ildik{\'o} Hoffmann and Gr{\'e}ta Szatl{\'o}czki and Zolt{\'a}n B{\'a}nr{\'e}ti and M. P{\'a}k{\'a}ski and J. K{\'a}lm{\'a}n",
year = "2016",
month = "1",
day = "1",
language = "English",
pages = "181--187",
booktitle = "54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Detecting mild cognitive impairment by exploiting linguistic information from transcripts

AU - Vincze, Veronika

AU - Gosztolya, Gábor

AU - Tóth, László

AU - Hoffmann, Ildikó

AU - Szatlóczki, Gréta

AU - Bánréti, Zoltán

AU - Pákáski, M.

AU - Kálmán, J.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Here we seek to automatically identify Hungarian patients suffering from mild cognitive impairment (MCI) based on linguistic features collected from their speech transcripts. Our system uses machine learning techniques and is based on several linguistic features like characteristics of spontaneous speech as well as features exploiting morphological and syntactic parsing. Our results suggest that it is primarily morphological and speechbased features that help distinguish MCI patients from healthy controls.

AB - Here we seek to automatically identify Hungarian patients suffering from mild cognitive impairment (MCI) based on linguistic features collected from their speech transcripts. Our system uses machine learning techniques and is based on several linguistic features like characteristics of spontaneous speech as well as features exploiting morphological and syntactic parsing. Our results suggest that it is primarily morphological and speechbased features that help distinguish MCI patients from healthy controls.

UR - http://www.scopus.com/inward/record.url?scp=85016565652&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016565652&partnerID=8YFLogxK

M3 - Conference contribution

SP - 181

EP - 187

BT - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers

PB - Association for Computational Linguistics (ACL)

ER -