Negation and Modality in Machine Translation

Preslav Nakov


Abstract
Negation and modality are two important grammatical phenomena that have attracted recent research attention as they can contribute to extra-propositional meaning aspects, among with factuality, attribution, irony and sarcasm. These aspects go beyond analysis such as semantic role labeling, and modeling them is important as a step towards a higher level of language understanding, which is needed for practical applications such as sentiment analysis. In this talk, I will go beyond English, and I will discuss how negation and modality are expressed in other languages. I will also go beyond sentiment analysis and I will present some challenges that the two phenomena pose for machine translation (MT). In particular, I will demonstrate how contemporary MT systems fail on them, and I will discuss some possible solutions.
Anthology ID:
W16-5005
Volume:
Proceedings of the Workshop on Extra-Propositional Aspects of Meaning in Computational Linguistics (ExProM)
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Eduardo Blanco, Roser Morante, Roser Saurí
Venue:
EXprom
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
41
Language:
URL:
https://aclanthology.org/W16-5005
DOI:
Bibkey:
Cite (ACL):
Preslav Nakov. 2016. Negation and Modality in Machine Translation. In Proceedings of the Workshop on Extra-Propositional Aspects of Meaning in Computational Linguistics (ExProM), page 41, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Negation and Modality in Machine Translation (Nakov, EXprom 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/W16-5005.pdf