GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena

Eva Vanmassenhove; Johanna Monti

doi:10.18653/v1/2021.gebnlp-1.1

GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena

Eva Vanmassenhove, Johanna Monti

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

7 Citations (Scopus)

Abstract

Languages differ in terms of the absence or presence of gender features, the number of gender classes and whether and where gender features are explicitly marked. These cross-linguistic differences can lead to ambiguities that are difficult to resolve, especially for sentence-level MT systems. The identification of ambiguity and its subsequent resolution is a challenging task for which currently there aren't any specific resources or challenge sets available. In this paper, we introduce gENder- IT, an English-Italian challenge set focusing on the resolution of natural gender phenomena by providing word-level gender tags on the English source side and multiple gender alternative translations, where needed, on the Italian target side.

Original language	English
Title of host publication	GeBNLP 2021
Subtitle of host publication	3rd Workshop on Gender Bias in Natural Language Processing
Editors	Marta R. Costa-jussa, Hila Gonen, Christian Hardmeier, Christian Hardmeier, Kellie Webster
Place of Publication	online
Publisher	Association for Computational Linguistics (ACL)
Pages	1-7
Number of pages	7
Volume	3
ISBN (Electronic)	9781954085619
DOIs	https://doi.org/10.18653/v1/2021.gebnlp-1.1
Publication status	Published - 2021
Event	3rd Workshop on Gender Bias in Natural Language Processing, GeBNLP 2021 - Virtual, Online, Thailand Duration: 5 Aug 2021 → …

Publication series

Name	GeBNLP 2021 - 3rd Workshop on Gender Bias in Natural Language Processing, Proceedings

Conference

Conference	3rd Workshop on Gender Bias in Natural Language Processing, GeBNLP 2021
Country/Territory	Thailand
City	Virtual, Online
Period	5/08/21 → …

Keywords

Languages
Cross-linguistic Differences
Gender

Access to Document

10.18653/v1/2021.gebnlp-1.1Licence: CC BY

Cite this

Vanmassenhove, E., & Monti, J. (2021). GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena. In M. R. Costa-jussa, H. Gonen, C. Hardmeier, C. Hardmeier, & K. Webster (Eds.), GeBNLP 2021: 3rd Workshop on Gender Bias in Natural Language Processing (Vol. 3, pp. 1-7). (GeBNLP 2021 - 3rd Workshop on Gender Bias in Natural Language Processing, Proceedings). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.gebnlp-1.1

Vanmassenhove, Eva ; Monti, Johanna. / GENder-IT : An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena. GeBNLP 2021: 3rd Workshop on Gender Bias in Natural Language Processing. editor / Marta R. Costa-jussa ; Hila Gonen ; Christian Hardmeier ; Christian Hardmeier ; Kellie Webster. Vol. 3 online : Association for Computational Linguistics (ACL), 2021. pp. 1-7 (GeBNLP 2021 - 3rd Workshop on Gender Bias in Natural Language Processing, Proceedings).

@inproceedings{b7e5839e8e8a451ebe3c5e4bf7561a5d,

title = "GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena",

abstract = "Languages differ in terms of the absence or presence of gender features, the number of gender classes and whether and where gender features are explicitly marked. These cross-linguistic differences can lead to ambiguities that are difficult to resolve, especially for sentence-level MT systems. The identification of ambiguity and its subsequent resolution is a challenging task for which currently there aren't any specific resources or challenge sets available. In this paper, we introduce gENder- IT, an English-Italian challenge set focusing on the resolution of natural gender phenomena by providing word-level gender tags on the English source side and multiple gender alternative translations, where needed, on the Italian target side. ",

keywords = "Languages, Cross-linguistic Differences, Gender",

author = "Eva Vanmassenhove and Johanna Monti",

note = "Publisher Copyright: {\textcopyright}2021 Association for Computational Linguistics.; 3rd Workshop on Gender Bias in Natural Language Processing, GeBNLP 2021 ; Conference date: 05-08-2021",

year = "2021",

doi = "10.18653/v1/2021.gebnlp-1.1",

language = "English",

volume = "3",

series = "GeBNLP 2021 - 3rd Workshop on Gender Bias in Natural Language Processing, Proceedings",

publisher = "Association for Computational Linguistics (ACL)",

pages = "1--7",

editor = "Costa-jussa, {Marta R.} and Hila Gonen and Christian Hardmeier and Christian Hardmeier and Kellie Webster",

booktitle = "GeBNLP 2021",

}

Vanmassenhove, E & Monti, J 2021, GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena. in MR Costa-jussa, H Gonen, C Hardmeier, C Hardmeier & K Webster (eds), GeBNLP 2021: 3rd Workshop on Gender Bias in Natural Language Processing. vol. 3, GeBNLP 2021 - 3rd Workshop on Gender Bias in Natural Language Processing, Proceedings, Association for Computational Linguistics (ACL), online, pp. 1-7, 3rd Workshop on Gender Bias in Natural Language Processing, GeBNLP 2021, Virtual, Online, Thailand, 5/08/21. https://doi.org/10.18653/v1/2021.gebnlp-1.1

GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena. / Vanmassenhove, Eva; Monti, Johanna.
GeBNLP 2021: 3rd Workshop on Gender Bias in Natural Language Processing. ed. / Marta R. Costa-jussa; Hila Gonen; Christian Hardmeier; Christian Hardmeier; Kellie Webster. Vol. 3 online: Association for Computational Linguistics (ACL), 2021. p. 1-7 (GeBNLP 2021 - 3rd Workshop on Gender Bias in Natural Language Processing, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - GENder-IT

T2 - 3rd Workshop on Gender Bias in Natural Language Processing, GeBNLP 2021

AU - Vanmassenhove, Eva

AU - Monti, Johanna

PY - 2021

Y1 - 2021

N2 - Languages differ in terms of the absence or presence of gender features, the number of gender classes and whether and where gender features are explicitly marked. These cross-linguistic differences can lead to ambiguities that are difficult to resolve, especially for sentence-level MT systems. The identification of ambiguity and its subsequent resolution is a challenging task for which currently there aren't any specific resources or challenge sets available. In this paper, we introduce gENder- IT, an English-Italian challenge set focusing on the resolution of natural gender phenomena by providing word-level gender tags on the English source side and multiple gender alternative translations, where needed, on the Italian target side.

AB - Languages differ in terms of the absence or presence of gender features, the number of gender classes and whether and where gender features are explicitly marked. These cross-linguistic differences can lead to ambiguities that are difficult to resolve, especially for sentence-level MT systems. The identification of ambiguity and its subsequent resolution is a challenging task for which currently there aren't any specific resources or challenge sets available. In this paper, we introduce gENder- IT, an English-Italian challenge set focusing on the resolution of natural gender phenomena by providing word-level gender tags on the English source side and multiple gender alternative translations, where needed, on the Italian target side.

KW - Languages

KW - Cross-linguistic Differences

KW - Gender

UR - http://www.scopus.com/inward/record.url?scp=85118297032&partnerID=8YFLogxK

U2 - 10.18653/v1/2021.gebnlp-1.1

DO - 10.18653/v1/2021.gebnlp-1.1

M3 - Conference contribution

AN - SCOPUS:85118297032

VL - 3

T3 - GeBNLP 2021 - 3rd Workshop on Gender Bias in Natural Language Processing, Proceedings

SP - 1

EP - 7

BT - GeBNLP 2021

A2 - Costa-jussa, Marta R.

A2 - Gonen, Hila

A2 - Hardmeier, Christian

A2 - Webster, Kellie

PB - Association for Computational Linguistics (ACL)

CY - online

Y2 - 5 August 2021

ER -

Vanmassenhove E, Monti J. GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena. In Costa-jussa MR, Gonen H, Hardmeier C, Hardmeier C, Webster K, editors, GeBNLP 2021: 3rd Workshop on Gender Bias in Natural Language Processing. Vol. 3. online: Association for Computational Linguistics (ACL). 2021. p. 1-7. (GeBNLP 2021 - 3rd Workshop on Gender Bias in Natural Language Processing, Proceedings). doi: 10.18653/v1/2021.gebnlp-1.1

GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this