Predicting default and non-default aspectual coding: Impact and density of information features

Michael Richter; Tariq Yousef

Predicting default and non-default aspectual coding: Impact and density of information features

Michael Richter
, Tariq Yousef

Leipzig University

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › peer review

Abstract

This paper presents a study on the automatic classification of default and nondefault codings for aspect-marked verbs in six Slavic and one Baltic language. As classifier a Support Vector Machine (SVM) and as verbal features Shannon Information (SI) and Average Information Content (IC) have been utilised. In all languages high accuracy of the classification has been achieved. In addition, we found indications for the validity of the Uniform Information Density principle within SI and IC.

Originalsprog	Engelsk
Tidsskrift	CEUR Workshop Proceedings
Vol/bind	2521
ISSN	1613-0073
Status	Udgivet - 2019
Udgivet eksternt	Ja
Begivenhed	3rd Workshop on Natural Language for Artificial Intelligence, NL4AI 2019 - Rende, Italien Varighed: 19. nov. 2019 → 22. nov. 2019

Konference

Konference	3rd Workshop on Natural Language for Artificial Intelligence, NL4AI 2019
Land/Område	Italien
By	Rende
Periode	19/11/2019 → 22/11/2019

Bibliografisk note

Publisher Copyright:
Copyright © 2019 for this paper by its authors.

Finansiering

* Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundatino) project number: 357550571.

SDU link

Tjek adgangen til materialet i Syddansk Universitetsbiblioteks søgemaskine

Andre filer og links

Link to publication in Scopus

Citationsformater

@inproceedings{048cc07d4aa44687ba891b1c6f649895,

title = "Predicting default and non-default aspectual coding: Impact and density of information features",

abstract = "This paper presents a study on the automatic classification of default and nondefault codings for aspect-marked verbs in six Slavic and one Baltic language. As classifier a Support Vector Machine (SVM) and as verbal features Shannon Information (SI) and Average Information Content (IC) have been utilised. In all languages high accuracy of the classification has been achieved. In addition, we found indications for the validity of the Uniform Information Density principle within SI and IC.",

keywords = "Coding, Information content, Verb aspect",

author = "Michael Richter and Tariq Yousef",

note = "Funding Information: * Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundatino) project number: 357550571. Publisher Copyright: Copyright {\textcopyright} 2019 for this paper by its authors.; 3rd Workshop on Natural Language for Artificial Intelligence, NL4AI 2019 ; Conference date: 19-11-2019 Through 22-11-2019",

year = "2019",

language = "English",

volume = "2521",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - GEN

T1 - Predicting default and non-default aspectual coding

T2 - 3rd Workshop on Natural Language for Artificial Intelligence, NL4AI 2019

AU - Richter, Michael

AU - Yousef, Tariq

N1 - Funding Information: * Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundatino) project number: 357550571. Publisher Copyright: Copyright © 2019 for this paper by its authors.

PY - 2019

Y1 - 2019

N2 - This paper presents a study on the automatic classification of default and nondefault codings for aspect-marked verbs in six Slavic and one Baltic language. As classifier a Support Vector Machine (SVM) and as verbal features Shannon Information (SI) and Average Information Content (IC) have been utilised. In all languages high accuracy of the classification has been achieved. In addition, we found indications for the validity of the Uniform Information Density principle within SI and IC.

AB - This paper presents a study on the automatic classification of default and nondefault codings for aspect-marked verbs in six Slavic and one Baltic language. As classifier a Support Vector Machine (SVM) and as verbal features Shannon Information (SI) and Average Information Content (IC) have been utilised. In all languages high accuracy of the classification has been achieved. In addition, we found indications for the validity of the Uniform Information Density principle within SI and IC.

KW - Coding

KW - Information content

KW - Verb aspect

UR - https://www.scopus.com/pages/publications/85077506667

M3 - Conference article

AN - SCOPUS:85077506667

SN - 1613-0073

VL - 2521

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

Y2 - 19 November 2019 through 22 November 2019

ER -

Predicting default and non-default aspectual coding: Impact and density of information features

Abstract

Konference

Bibliografisk note

Finansiering

SDU link

Andre filer og links

Fingeraftryk

Citationsformater