Improving Document Clustering by Removing Unnatural Language

Myungha Jang, Jinho D. Choi, James Allan


Abstract
Technical documents contain a fair amount of unnatural language, such as tables, formulas, and pseudo-code. Unnatural language can bean important factor of confusing existing NLP tools. This paper presents an effective method of distinguishing unnatural language from natural language, and evaluates the impact of un-natural language detection on NLP tasks such as document clustering. We view this problem as an information extraction task and build a multiclass classification model identifying unnatural language components into four categories. First, we create a new annotated corpus by collecting slides and papers in various for-mats, PPT, PDF, and HTML, where unnatural language components are annotated into four categories. We then explore features available from plain text to build a statistical model that can handle any format as long as it is converted into plain text. Our experiments show that re-moving unnatural language components gives an absolute improvement in document cluster-ing by up to 15%. Our corpus and tool are publicly available
Anthology ID:
W17-4416
Volume:
Proceedings of the 3rd Workshop on Noisy User-generated Text
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Leon Derczynski, Wei Xu, Alan Ritter, Tim Baldwin
Venue:
WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
122–130
Language:
URL:
https://aclanthology.org/W17-4416
DOI:
10.18653/v1/W17-4416
Bibkey:
Cite (ACL):
Myungha Jang, Jinho D. Choi, and James Allan. 2017. Improving Document Clustering by Removing Unnatural Language. In Proceedings of the 3rd Workshop on Noisy User-generated Text, pages 122–130, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Improving Document Clustering by Removing Unnatural Language (Jang et al., WNUT 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-4416.pdf