Classification of telicity using cross-linguistic annotation projection

Annemarie Friedrich, Damyana Gateva


Abstract
This paper addresses the automatic recognition of telicity, an aspectual notion. A telic event includes a natural endpoint (“she walked home”), while an atelic event does not (“she walked around”). Recognizing this difference is a prerequisite for temporal natural language understanding. In English, this classification task is difficult, as telicity is a covert linguistic category. In contrast, in Slavic languages, aspect is part of a verb’s meaning and even available in machine-readable dictionaries. Our contributions are as follows. We successfully leverage additional silver standard training data in the form of projected annotations from parallel English-Czech data as well as context information, improving automatic telicity classification for English significantly compared to previous work. We also create a new data set of English texts manually annotated with telicity.
Anthology ID:
D17-1271
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2559–2565
Language:
URL:
https://aclanthology.org/D17-1271
DOI:
10.18653/v1/D17-1271
Bibkey:
Cite (ACL):
Annemarie Friedrich and Damyana Gateva. 2017. Classification of telicity using cross-linguistic annotation projection. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2559–2565, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Classification of telicity using cross-linguistic annotation projection (Friedrich & Gateva, EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1271.pdf
Code
 annefried/telicity