Gå til søgefeltetSpring over til navigationSpring til hovedindhold

DanTok: Domain Beats Language for Danish Social Media POS Tagging

Publikation:
Konference artikel i Proceeding eller bog/rapport kapitel
Konferencebidrag i proceedings
Forskning
Peer-review

Open Access

Resume

Language from social media remains challenging to process automatically, especially for non-English languages. In this work, we introduce the first NLP dataset for TikTok comments and the first Danish social media dataset with part-of-speech annotation. We further supply annotations for normalization, code-switching, and annotator uncertainty. As transferring models to such a highly specialized domain is non-trivial, we conduct an extensive study into which source data and modeling decisions most impact the performance. Surprisingly, transferring from in-domain data, even from a different language, outperforms in-language, out-of-domain training. These benefits nonetheless rely on the underlying language models having been at least partially pre-trained on data from the target language. Using our additional annotation layers, we further analyze how normalization, code-switching, and human uncertainty affect the tagging accuracy.

Publikation information

Produktionstype

Publikation:
Konference artikel i Proceeding eller bog/rapport kapitel
Konferencebidrag i proceedings
Forskning
Peer-review

Originalsprog

Engelsk

Sider fra-til (Antal sider)

Sider 271–279 (9 sider)

Publikationsmilepæle

  • Udgivet - 2023

Publikationsstatus

Udgivet - 2023

Publikations IDer

  • Scopus: 85217079230

Titel på værtspublikation

Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)

Metrikker

PlumX

Antal citationer
1
Hentninger
21

Adgang til dokumenter

Relateret event

Titel

Nordic Conference on Computational Linguistics

Begivenhedstype

Konference

Grad af anerkendelse

International begivenhed

Dato

22/05/2023 - 24/05/2023

Lokation

TórshavnFærøerne