Detecting Uncertainty Cues in Hungarian Social Media Texts

Veronika Vincze


Abstract
In this paper, we aim at identifying uncertainty cues in Hungarian social media texts. We present our machine learning based uncertainty detector which is based on a rich features set including lexical, morphological, syntactic, semantic and discourse-based features, and we evaluate our system on a small set of manually annotated social media texts. We also carry out cross-domain and domain adaptation experiments using an annotated corpus of standard Hungarian texts and show that domain differences significantly affect machine learning. Furthermore, we argue that differences among uncertainty cue types may also affect the efficiency of uncertainty detection.
Anthology ID:
W16-5002
Volume:
Proceedings of the Workshop on Extra-Propositional Aspects of Meaning in Computational Linguistics (ExProM)
Month:
December
Year:
2016
Address:
Osaka, Japan
Venues:
EXprom | WS
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
11–21
Language:
URL:
https://www.aclweb.org/anthology/W16-5002
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W16-5002.pdf