Norm It! Lexical Normalization for Italian and Its Downstream Effects forDependency Parsing

Rob van der Goot; Alan  Ramponi; Tommaso Caselli; Michele  Cafagna; Lorenzo De Mattei

Norm It! Lexical Normalization for Italian and Its Downstream Effects forDependency Parsing

Rob van der Goot, Alan Ramponi, Tommaso Caselli, Michele Cafagna, Lorenzo De Mattei

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

Lexical normalization is the task of translating non-standard social media data to a standard form. Previous work has shown that this is beneficial for many downstream tasks in multiple languages. However, for Italian, there is no benchmark available for lexical normalization, despite the presence of many benchmarks for other tasks involving social media data. In this paper, we discuss the creation of a lexical normalization dataset for Italian. After two rounds of annotation, a Cohen’s kappa score of 78.64 is obtained. During this process, we also analyze the inter-annotator agreement for this task, which is only rarely done on datasets for lexical normalization,and when it is reported, the analysis usually remains shallow. Furthermore, we utilize this dataset to train a lexical normalization model and show that it can be used to improve dependency parsing of social media data. All annotated data and the code to reproduce the results are available at: http://bitbucket.org/robvanderg/normit.

Original language	English
Title of host publication	Proceedings of the Twelfth International Conference on Language Resources and Evaluation (LREC 2020)
Place of Publication	France
Publisher	European Language Resources Association (ELRA)
Publication date	May 2020
Pages	6272–6278
Publication status	Published - May 2020
Event	LREC 2020 - Marseille, France Duration: 17 May 2020 → 22 May 2020 https://lrec2020.lrec-conf.org/en/

Conference

Conference	LREC 2020
Country/Territory	France
City	Marseille
Period	17/05/2020 → 22/05/2020
Internet address	https://lrec2020.lrec-conf.org/en/

Keywords

lexical normalization
social media data
Italian language
inter-annotator agreement
dependency parsing

Access to Document

normIt (1)Final published version, 133 KBLicence: CC BY-NC

https://www.aclweb.org/anthology/2020.lrec-1.769Licence: CC BY-NC

Multi-Task Sequence Labeling Under Adverse Conditions
Plank, B. (PI) & van der Goot, R. (CoI)
Amazon.com, Inc.
01/04/2019 → 31/08/2020
Project: Other

Cite this

van der Goot, R., Ramponi, A., Caselli, T., Cafagna, M., & De Mattei, L. (2020). Norm It! Lexical Normalization for Italian and Its Downstream Effects forDependency Parsing. In Proceedings of the Twelfth International Conference on Language Resources and Evaluation (LREC 2020) (pp. 6272–6278). European Language Resources Association (ELRA). https://www.aclweb.org/anthology/2020.lrec-1.769

@inproceedings{3b5ca7c920d546c7954e8de335e1b592,

title = "Norm It! Lexical Normalization for Italian and Its Downstream Effects forDependency Parsing",

abstract = "Lexical normalization is the task of translating non-standard social media data to a standard form. Previous work has shown that this is beneficial for many downstream tasks in multiple languages. However, for Italian, there is no benchmark available for lexical normalization, despite the presence of many benchmarks for other tasks involving social media data. In this paper, we discuss the creation of a lexical normalization dataset for Italian. After two rounds of annotation, a Cohen{\textquoteright}s kappa score of 78.64 is obtained. During this process, we also analyze the inter-annotator agreement for this task, which is only rarely done on datasets for lexical normalization,and when it is reported, the analysis usually remains shallow. Furthermore, we utilize this dataset to train a lexical normalization model and show that it can be used to improve dependency parsing of social media data. All annotated data and the code to reproduce the results are available at: http://bitbucket.org/robvanderg/normit.",

keywords = "lexical normalization, social media data, Italian language, inter-annotator agreement, dependency parsing, lexical normalization, social media data, Italian language, inter-annotator agreement, dependency parsing",

author = "{van der Goot}, Rob and Alan Ramponi and Tommaso Caselli and Michele Cafagna and {De Mattei}, Lorenzo",

year = "2020",

month = may,

language = "English",

pages = "6272–6278",

booktitle = "Proceedings of the Twelfth International Conference on Language Resources and Evaluation (LREC 2020)",

publisher = "European Language Resources Association (ELRA)",

note = "LREC 2020 ; Conference date: 17-05-2020 Through 22-05-2020",

url = "https://lrec2020.lrec-conf.org/en/",

}

van der Goot, R, Ramponi, A, Caselli, T, Cafagna, M & De Mattei, L 2020, Norm It! Lexical Normalization for Italian and Its Downstream Effects forDependency Parsing. in Proceedings of the Twelfth International Conference on Language Resources and Evaluation (LREC 2020). European Language Resources Association (ELRA), France, pp. 6272–6278, LREC 2020, Marseille, France, 17/05/2020. <https://www.aclweb.org/anthology/2020.lrec-1.769>

Norm It! Lexical Normalization for Italian and Its Downstream Effects forDependency Parsing. / van der Goot, Rob; Ramponi, Alan ; Caselli, Tommaso et al.
Proceedings of the Twelfth International Conference on Language Resources and Evaluation (LREC 2020). France: European Language Resources Association (ELRA), 2020. p. 6272–6278.

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

TY - GEN

T1 - Norm It! Lexical Normalization for Italian and Its Downstream Effects forDependency Parsing

AU - van der Goot, Rob

AU - Ramponi, Alan

AU - Caselli, Tommaso

AU - Cafagna, Michele

AU - De Mattei, Lorenzo

PY - 2020/5

Y1 - 2020/5

N2 - Lexical normalization is the task of translating non-standard social media data to a standard form. Previous work has shown that this is beneficial for many downstream tasks in multiple languages. However, for Italian, there is no benchmark available for lexical normalization, despite the presence of many benchmarks for other tasks involving social media data. In this paper, we discuss the creation of a lexical normalization dataset for Italian. After two rounds of annotation, a Cohen’s kappa score of 78.64 is obtained. During this process, we also analyze the inter-annotator agreement for this task, which is only rarely done on datasets for lexical normalization,and when it is reported, the analysis usually remains shallow. Furthermore, we utilize this dataset to train a lexical normalization model and show that it can be used to improve dependency parsing of social media data. All annotated data and the code to reproduce the results are available at: http://bitbucket.org/robvanderg/normit.

AB - Lexical normalization is the task of translating non-standard social media data to a standard form. Previous work has shown that this is beneficial for many downstream tasks in multiple languages. However, for Italian, there is no benchmark available for lexical normalization, despite the presence of many benchmarks for other tasks involving social media data. In this paper, we discuss the creation of a lexical normalization dataset for Italian. After two rounds of annotation, a Cohen’s kappa score of 78.64 is obtained. During this process, we also analyze the inter-annotator agreement for this task, which is only rarely done on datasets for lexical normalization,and when it is reported, the analysis usually remains shallow. Furthermore, we utilize this dataset to train a lexical normalization model and show that it can be used to improve dependency parsing of social media data. All annotated data and the code to reproduce the results are available at: http://bitbucket.org/robvanderg/normit.

KW - lexical normalization

KW - social media data

KW - Italian language

KW - inter-annotator agreement

KW - dependency parsing

KW - lexical normalization

KW - social media data

KW - Italian language

KW - inter-annotator agreement

KW - dependency parsing

UR - https://bitbucket.org/robvanderg/normit/src

M3 - Article in proceedings

SP - 6272

EP - 6278

BT - Proceedings of the Twelfth International Conference on Language Resources and Evaluation (LREC 2020)

PB - European Language Resources Association (ELRA)

CY - France

T2 - LREC 2020

Y2 - 17 May 2020 through 22 May 2020

ER -

Norm It! Lexical Normalization for Italian and Its Downstream Effects forDependency Parsing

Abstract

Conference

Keywords

Access to Document

Fingerprint

Projects

Multi-Task Sequence Labeling Under Adverse Conditions

Cite this