Evaluation of Automatically Constructed Word Meaning
Explanations

C 2022

Evaluation of Automatically Constructed Word Meaning Explanations

STARÁ, Marie, Pavel RYCHLÝ and Aleš HORÁK

Basic information

Original name

Evaluation of Automatically Constructed Word Meaning Explanations

Authors

STARÁ, Marie, Pavel RYCHLÝ and Aleš HORÁK

Edition

Rickmansworth, UK, Logically Speaking: A Festschrift for Marie Duží, p. 99-112, 14 pp. Tributes, Volume 49, 2022

Publisher

College Publications

Other information

Language

English

Type of outcome

Kapitola resp. kapitoly v odborné knize

Field of Study

10200 1.2 Computer and information sciences

Country of publisher

United Kingdom of Great Britain and Northern Ireland

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

printed version "print"

References:

URL vydavatele preprint na arxiv.org

Organization unit

Faculty of Informatics

ISBN

978-1-84890-419-4

Keywords in English

explanations; word sketches; explanation construction

Abstract

V originále

Preparing exact and comprehensive word meaning explanations is one of the key steps in the process of monolingual dictionary writing. In standard methodology, the explanations need an expert lexicographer who spends a substantial amount of time checking the consistency between the descriptive text and corpus evidence. In the following text, we present a new tool that derives explanations automatically based on collective information from very large corpora, particularly on word sketches. We also propose a quantitative evaluation of the constructed explanations, concentrating on explanations of nouns. The methodology is to a certain extent language independent; however, the presented verification is limited to Czech and English. We show that the presented approach allows to create explanations that contain data useful for understanding the word meaning in approximately 90% of cases. However, in many cases, the result requires post-editing to remove redundant information.

Links

LM2018101, research and development project

Name: Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědy (Acronym: LINDAT/CLARIAH-CZ)

Investor: Ministry of Education, Youth and Sports of the CR

Citovat

STARÁ, Marie, Pavel RYCHLÝ and Aleš HORÁK. Evaluation of Automatically Constructed Word Meaning Explanations. In Pavel Materna and Bjørn Jespersen. Logically Speaking: A Festschrift for Marie Duží. Rickmansworth, UK: College Publications, 2022, p. 99-112. Tributes, Volume 49. ISBN 978-1-84890-419-4.

@inbook{2261598,
   author = {Stará, Marie and Rychlý, Pavel and Horák, Aleš},
   address = {Rickmansworth, UK},
   booktitle = {Logically Speaking: A Festschrift for Marie Duží},
   editor = {Pavel Materna and Bjørn Jespersen},
   keywords = {explanations; word sketches; explanation construction},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Rickmansworth, UK},
   isbn = {978-1-84890-419-4},
   pages = {99-112},
   publisher = {College Publications},
   title = {Evaluation of Automatically Constructed Word Meaning Explanations},
   url = {https://www.collegepublications.co.uk/tributes/?00049},
   year = {2022}
}

TY  - CHAP
ID  - 2261598
AU  - Stará, Marie - Rychlý, Pavel - Horák, Aleš
PY  - 2022
TI  - Evaluation of Automatically Constructed Word Meaning Explanations
VL  - Tributes, Volume 49
PB  - College Publications
CY  - Rickmansworth, UK
SN  - 9781848904194
KW  - explanations
KW  - word sketches
KW  - explanation construction
UR  - https://www.collegepublications.co.uk/tributes/?00049
N2  - Preparing exact and comprehensive word meaning explanations is one of the key steps in the process of monolingual dictionary writing. In standard methodology, the explanations need an expert lexicographer who spends a substantial amount of time checking the consistency between the descriptive text and corpus evidence. In the following text, we present a new tool that derives explanations automatically based on collective information from very large corpora, particularly on word sketches. We also propose a quantitative evaluation of the constructed explanations, concentrating on explanations of nouns. The methodology is to a certain extent language independent; however, the presented verification is limited to Czech and English. We show that the presented approach allows to create explanations that contain data useful for understanding the word meaning in approximately 90% of cases. However, in many cases, the result requires post-editing to remove redundant information.
ER  -

STARÁ, Marie, Pavel RYCHLÝ and Aleš HORÁK. Evaluation of Automatically Constructed Word Meaning Explanations. In Pavel Materna and Bjørn Jespersen. \textit{Logically Speaking: A Festschrift for Marie Duží}. Rickmansworth, UK: College Publications, 2022, p.~99-112. Tributes, Volume 49. ISBN~978-1-84890-419-4.

Detailed Information on Publication Record