A unified feature representation for lexical connotations

Emily Allaway; Kathleen McKeown

doi:10.18653/v1/2021.eacl-main.184

A unified feature representation for lexical connotations

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Ideological attitudes and stance are often expressed through subtle meanings of words and phrases. Understanding these connotations is critical to recognizing the cultural and emotional perspectives of the speaker. In this paper, we use distant labeling to create a new lexical resource representing connotation aspects for nouns and adjectives. Our analysis shows that it aligns well with human judgments. Additionally, we present a method for creating lexical representations that capture connotations within the embedding space and show that using the embeddings provides a statistically significant improvement on the task of stance detection when data is limited.

Original language	English
Title of host publication	Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics
Editors	Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Publisher	Association for Computational Linguistics
Pages	2145–2163
Number of pages	19
ISBN (Electronic)	9781954085022
DOIs	https://doi.org/10.18653/v1/2021.eacl-main.184
Publication status	Published - 23 Apr 2021
Event	16th Conference of the European Chapter of the Association for Computational Linguistics - Online Duration: 19 Apr 2021 → 23 Apr 2021 https://2021.eacl.org/

Publication series

Name	Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics
Publisher	ACL
ISSN (Print)	1525-2450

Conference

Conference	16th Conference of the European Chapter of the Association for Computational Linguistics
Abbreviated title	EACL 2021
Period	19/04/21 → 23/04/21
Internet address	https://2021.eacl.org/

Access to Document

10.18653/v1/2021.eacl-main.184Licence: Creative Commons: Attribution (CC-BY)

AllawayAndMcKeownEACL2021AUnifiedFeatureRepresentationFinal published version, 895 KBLicence: Creative Commons: Attribution (CC-BY)

Cite this

Allaway, E., & McKeown, K. (2021). A unified feature representation for lexical connotations. In P. Merlo, J. Tiedemann, & R. Tsarfaty (Eds.), Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (pp. 2145–2163). (Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.eacl-main.184

Allaway, Emily ; McKeown, Kathleen. / A unified feature representation for lexical connotations. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics. editor / Paola Merlo ; Jorg Tiedemann ; Reut Tsarfaty. Association for Computational Linguistics, 2021. pp. 2145–2163 (Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics).

@inproceedings{98380cfecbd14694bdaa70811598a5c4,

title = "A unified feature representation for lexical connotations",

abstract = "Ideological attitudes and stance are often expressed through subtle meanings of words and phrases. Understanding these connotations is critical to recognizing the cultural and emotional perspectives of the speaker. In this paper, we use distant labeling to create a new lexical resource representing connotation aspects for nouns and adjectives. Our analysis shows that it aligns well with human judgments. Additionally, we present a method for creating lexical representations that capture connotations within the embedding space and show that using the embeddings provides a statistically significant improvement on the task of stance detection when data is limited.",

author = "Emily Allaway and Kathleen McKeown",

year = "2021",

month = apr,

day = "23",

doi = "10.18653/v1/2021.eacl-main.184",

language = "English",

series = "Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

pages = "2145–2163",

editor = "Paola Merlo and Jorg Tiedemann and Reut Tsarfaty",

booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics",

note = "16th Conference of the European Chapter of the Association for Computational Linguistics , EACL 2021 ; Conference date: 19-04-2021 Through 23-04-2021",

url = "https://2021.eacl.org/",

}

Allaway, E & McKeown, K 2021, A unified feature representation for lexical connotations. in P Merlo, J Tiedemann & R Tsarfaty (eds), Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics. Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, pp. 2145–2163, 16th Conference of the European Chapter of the Association for Computational Linguistics , 19/04/21. https://doi.org/10.18653/v1/2021.eacl-main.184

A unified feature representation for lexical connotations. / Allaway, Emily; McKeown, Kathleen.
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics. ed. / Paola Merlo; Jorg Tiedemann; Reut Tsarfaty. Association for Computational Linguistics, 2021. p. 2145–2163 (Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A unified feature representation for lexical connotations

AU - Allaway, Emily

AU - McKeown, Kathleen

PY - 2021/4/23

Y1 - 2021/4/23

N2 - Ideological attitudes and stance are often expressed through subtle meanings of words and phrases. Understanding these connotations is critical to recognizing the cultural and emotional perspectives of the speaker. In this paper, we use distant labeling to create a new lexical resource representing connotation aspects for nouns and adjectives. Our analysis shows that it aligns well with human judgments. Additionally, we present a method for creating lexical representations that capture connotations within the embedding space and show that using the embeddings provides a statistically significant improvement on the task of stance detection when data is limited.

AB - Ideological attitudes and stance are often expressed through subtle meanings of words and phrases. Understanding these connotations is critical to recognizing the cultural and emotional perspectives of the speaker. In this paper, we use distant labeling to create a new lexical resource representing connotation aspects for nouns and adjectives. Our analysis shows that it aligns well with human judgments. Additionally, we present a method for creating lexical representations that capture connotations within the embedding space and show that using the embeddings provides a statistically significant improvement on the task of stance detection when data is limited.

U2 - 10.18653/v1/2021.eacl-main.184

DO - 10.18653/v1/2021.eacl-main.184

M3 - Conference contribution

T3 - Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics

SP - 2145

EP - 2163

BT - Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics

A2 - Merlo, Paola

A2 - Tiedemann, Jorg

A2 - Tsarfaty, Reut

PB - Association for Computational Linguistics

T2 - 16th Conference of the European Chapter of the Association for Computational Linguistics

Y2 - 19 April 2021 through 23 April 2021

ER -

Allaway E, McKeown K. A unified feature representation for lexical connotations. In Merlo P, Tiedemann J, Tsarfaty R, editors, Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics. 2021. p. 2145–2163. (Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics). doi: 10.18653/v1/2021.eacl-main.184

A unified feature representation for lexical connotations

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this