Publikationendatenbank
show results
Autor:
Stanovsky, Gabriel;
Eckle-Kohler, Judith;
Puzikov, Yevgeniy;
Dagan, Ido;
Gurevych, Iryna:
Titel:
Integrating deep linguistics features in factuality prediction over unified datasets
Quelle:
In: Association for Computational Linguistics (Hrsg.): The 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017)
Stroudsburg, PA :
Association for Computational Linguistics
(2017)
, 352-357
URL des Volltextes:
https://aclanthology.info/pdf/P/P17/P17-2056.pdf
Sprache:
Englisch
Dokumenttyp:
4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Schlagwörter:
Computerlinguistik,
Modell,
Methode,
Daten,
Sprache,
Wort,
Semantik
Abstract(original):
Previous models for the assessment of commitment towards a predicate in a sentence (also known as factuality prediction) were trained and tested against a specific annotated dataset, subsequently limiting the generality of their results. In this work we propose an intuitive method for mapping three previously annotated corpora onto a single factuality scale, thereby enabling models to be tested across these corpora. In addition, we design a novel model for factuality prediction by first extending a previous rule-based factuality prediction system and applying it over an abstraction of dependency trees, and then using the output of this system in a supervised classifier. We show that this model outperforms previous methods on all three datasets. We make both the unified factuality corpus and our new model publicly available. (DIPF/Orig.)
DIPF-Abteilung:
Informationszentrum Bildung
Notizen:
