Predicting Modality in Financial Dialogue

Kilian Theil, Heiner Stuckenschmidt


Abstract
In this paper, we perform modality prediction in financial dialogue. To this end, we introduce a new dataset and develop a binary classifier to detect strong or weak modal answers depending on surface, lexical, and semantic representations of the preceding question and financial features. To do so, we contrast different algorithms, feature categories, and fusion methods. Perhaps counter-intuitively, our results indicate that the strongest features for the given task are financial uncertainty measures such as market and individual firm risk.
Anthology ID:
2020.fnp-1.35
Volume:
Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venues:
COLING | FNP
SIG:
Publisher:
COLING
Note:
Pages:
226–234
Language:
URL:
https://www.aclweb.org/anthology/2020.fnp-1.35
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.fnp-1.35.pdf