Integrating deep linguistics features in factuality prediction over unified datasets.

Autor/inn/en	Stanovsky, Gabriel; Eckle-Kohler, Judith; Puzikov, Yevgeniy; Dagan, Ido; Gurevych, Iryna
Institution	Association for Computational Linguistics
Titel	Integrating deep linguistics features in factuality prediction over unified datasets.
Quelle	Aus: The 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017): Proceedings of the conference, vol. 2 (short papers), July 30 - August 4, 2017, Vancouver, Canada. Stroudsburg, PA: Association for Computational Linguistics (2017) S. 352-357 PDF als Volltext kostenfreie Datei Link als defekt meldenVerfügbarkeit
Sprache	englisch
Dokumenttyp	online; Sammelwerksbeitrag
DOI	10.18653/v1/P17-2056
Schlagwörter	Methode; Semantik; Sprache; Wort; Computerlinguistik; Daten; Modell
Abstract	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.).
Erfasst von	DIPF \| Leibniz-Institut für Bildungsforschung und Bildungsinformation, Frankfurt am Main
Update	2023/1