PoS Tagging, Lemmatization and Dependency Parsing of West Frisian

Wilbert Heeringa; Gosse Bouma; Martha Hofman; Jelle Brouwer; Eduard Drenth; Jan Wijffels; Hans Van de Velde

PoS Tagging, Lemmatization and Dependency Parsing of West Frisian

Wilbert Heeringa, Gosse Bouma, Martha Hofman, Jelle Brouwer, Eduard Drenth, Jan Wijffels, Hans Van de Velde

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

67 Downloads (Pure)

Abstract

We present a lemmatizer/PoS tagger/dependency parser for West Frisian using a corpus of 44,714 words in 3,126 sentences that were annotated according to the guidelines of Universal Dependencies version 2. PoS tags were assigned to words by using a Dutch PoS tagger that was applied to a Dutch word-by-word translation, or to sentences of a Dutch parallel text. Best results were obtained when using word-by-word translations that were created by using the previous version of the Frisian translation program Oersetter. Morphologic and syntactic annotations were generated on the basis of a Dutch word-by-word translation as well. The performance of the lemmatizer/tagger/annotator when it was trained using default parameters was compared to the performance that was obtained when using the parameter values that were used for training the LassySmall UD 2.5 corpus. We study the effects of different hyperparameter settings on the accuracy of the annotation pipeline. The Frisian lemmatizer/PoS tagger/dependency parser is released as a web app and as a web service.

Original language	English
Title of host publication	Proceedings of the 13th Language and Resources Evaluation Conference (LREC 2022)
Editors	Nicoletta Calzolari
Place of Publication	Marseille
Publisher	European Language Resources Association (ELRA)
Pages	4789-4798
Number of pages	10
Publication status	Published - 21-Jun-2022
Event	The 13th Conference on Language Resources and Evaluation - Palais du Pharo, Marseille, France Duration: 20-Jun-2022 → 25-Jun-2022 https://lrec2022.lrec-conf.org/en/

Conference

Conference	The 13th Conference on Language Resources and Evaluation
Abbreviated title	LREC 2022
Country/Territory	France
City	Marseille
Period	20/06/2022 → 25/06/2022
Internet address	https://lrec2022.lrec-conf.org/en/

Keywords

pos tagging
dependency relations
Frysk
corpus

Access to Document

PoS Tagging, Lemmatization and Dependency Parsing of West FrisianFinal publisher's version, 273 KBLicence: CC BY-NC

Handle.net

Persistent link

Cite this

@inproceedings{dff035fced6947e8af857474a0193450,

title = "PoS Tagging, Lemmatization and Dependency Parsing of West Frisian",

abstract = "We present a lemmatizer/PoS tagger/dependency parser for West Frisian using a corpus of 44,714 words in 3,126 sentences that were annotated according to the guidelines of Universal Dependencies version 2. PoS tags were assigned to words by using a Dutch PoS tagger that was applied to a Dutch word-by-word translation, or to sentences of a Dutch parallel text. Best results were obtained when using word-by-word translations that were created by using the previous version of the Frisian translation program Oersetter. Morphologic and syntactic annotations were generated on the basis of a Dutch word-by-word translation as well. The performance of the lemmatizer/tagger/annotator when it was trained using default parameters was compared to the performance that was obtained when using the parameter values that were used for training the LassySmall UD 2.5 corpus. We study the effects of different hyperparameter settings on the accuracy of the annotation pipeline. The Frisian lemmatizer/PoS tagger/dependency parser is released as a web app and as a web service.",

keywords = "pos tagging, dependency relations, Frysk, corpus",

author = "Wilbert Heeringa and Gosse Bouma and Martha Hofman and Jelle Brouwer and Eduard Drenth and Jan Wijffels and {Van de Velde}, Hans",

year = "2022",

month = jun,

day = "21",

language = "English",

pages = "4789--4798",

editor = "Nicoletta Calzolari",

booktitle = "Proceedings of the 13th Language and Resources Evaluation Conference (LREC 2022)",

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

note = "The 13th Conference on Language Resources and Evaluation, LREC 2022 ; Conference date: 20-06-2022 Through 25-06-2022",

url = "https://lrec2022.lrec-conf.org/en/",

}

Heeringa, W, Bouma, G, Hofman, M, Brouwer, J, Drenth, E, Wijffels, J & Van de Velde, H 2022, PoS Tagging, Lemmatization and Dependency Parsing of West Frisian. in N Calzolari (ed.), Proceedings of the 13th Language and Resources Evaluation Conference (LREC 2022). European Language Resources Association (ELRA), Marseille , pp. 4789-4798, The 13th Conference on Language Resources and Evaluation, Marseille, France, 20/06/2022.

PoS Tagging, Lemmatization and Dependency Parsing of West Frisian. / Heeringa, Wilbert; Bouma, Gosse; Hofman, Martha et al.
Proceedings of the 13th Language and Resources Evaluation Conference (LREC 2022). ed. / Nicoletta Calzolari. Marseille : European Language Resources Association (ELRA), 2022. p. 4789-4798.

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

TY - GEN

T1 - PoS Tagging, Lemmatization and Dependency Parsing of West Frisian

AU - Heeringa, Wilbert

AU - Bouma, Gosse

AU - Hofman, Martha

AU - Brouwer, Jelle

AU - Drenth, Eduard

AU - Wijffels, Jan

AU - Van de Velde, Hans

PY - 2022/6/21

Y1 - 2022/6/21

N2 - We present a lemmatizer/PoS tagger/dependency parser for West Frisian using a corpus of 44,714 words in 3,126 sentences that were annotated according to the guidelines of Universal Dependencies version 2. PoS tags were assigned to words by using a Dutch PoS tagger that was applied to a Dutch word-by-word translation, or to sentences of a Dutch parallel text. Best results were obtained when using word-by-word translations that were created by using the previous version of the Frisian translation program Oersetter. Morphologic and syntactic annotations were generated on the basis of a Dutch word-by-word translation as well. The performance of the lemmatizer/tagger/annotator when it was trained using default parameters was compared to the performance that was obtained when using the parameter values that were used for training the LassySmall UD 2.5 corpus. We study the effects of different hyperparameter settings on the accuracy of the annotation pipeline. The Frisian lemmatizer/PoS tagger/dependency parser is released as a web app and as a web service.

AB - We present a lemmatizer/PoS tagger/dependency parser for West Frisian using a corpus of 44,714 words in 3,126 sentences that were annotated according to the guidelines of Universal Dependencies version 2. PoS tags were assigned to words by using a Dutch PoS tagger that was applied to a Dutch word-by-word translation, or to sentences of a Dutch parallel text. Best results were obtained when using word-by-word translations that were created by using the previous version of the Frisian translation program Oersetter. Morphologic and syntactic annotations were generated on the basis of a Dutch word-by-word translation as well. The performance of the lemmatizer/tagger/annotator when it was trained using default parameters was compared to the performance that was obtained when using the parameter values that were used for training the LassySmall UD 2.5 corpus. We study the effects of different hyperparameter settings on the accuracy of the annotation pipeline. The Frisian lemmatizer/PoS tagger/dependency parser is released as a web app and as a web service.

KW - pos tagging

KW - dependency relations

KW - Frysk

KW - corpus

M3 - Conference contribution

SP - 4789

EP - 4798

BT - Proceedings of the 13th Language and Resources Evaluation Conference (LREC 2022)

A2 - Calzolari, Nicoletta

PB - European Language Resources Association (ELRA)

CY - Marseille

T2 - The 13th Conference on Language Resources and Evaluation

Y2 - 20 June 2022 through 25 June 2022

ER -

PoS Tagging, Lemmatization and Dependency Parsing of West Frisian

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this