User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization

Shohei Higashiyama, Masao Utiyama, Taro Watanabe, Eiichiro Sumita


Abstract
Morphological analysis (MA) and lexical normalization (LN) are both important tasks for Japanese user-generated text (UGT). To evaluate and compare different MA/LN systems, we have constructed a publicly available Japanese UGT corpus. Our corpus comprises 929 sentences annotated with morphological and normalization information, along with category information we classified for frequent UGT-specific phenomena. Experiments on the corpus demonstrated the low performance of existing MA/LN methods for non-general words and non-standard forms, indicating that the corpus would be a challenging benchmark for further research on UGT.
Anthology ID:
2021.naacl-main.438
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5532–5541
Language:
URL:
https://aclanthology.org/2021.naacl-main.438
DOI:
10.18653/v1/2021.naacl-main.438
Bibkey:
Cite (ACL):
Shohei Higashiyama, Masao Utiyama, Taro Watanabe, and Eiichiro Sumita. 2021. User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5532–5541, Online. Association for Computational Linguistics.
Cite (Informal):
User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization (Higashiyama et al., NAACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.naacl-main.438.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2021.naacl-main.438.mp4
Code
 shigashiyama/jlexnorm