TU Darmstadt / ULB / TUbiblio

Integrating Deep Linguistic Features in Factuality Prediction over Unified Datasets

Stanovsky, Gabriel ; Eckle-Kohler, Judith ; Puzikov, Yevgeniy ; Dagan, Ido ; Gurevych, Iryna (2017)
Integrating Deep Linguistic Features in Factuality Prediction over Unified Datasets.
The 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017). Vancouver, Canada (30.07.2017--04.08.2017)
Conference or Workshop Item, Bibliographie

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. Our model which we will make publicly available outperforms previous methods on all three datasets.

Item Type: Conference or Workshop Item
Erschienen: 2017
Creators: Stanovsky, Gabriel ; Eckle-Kohler, Judith ; Puzikov, Yevgeniy ; Dagan, Ido ; Gurevych, Iryna
Type of entry: Bibliographie
Title: Integrating Deep Linguistic Features in Factuality Prediction over Unified Datasets
Language: English
Date: August 2017
Publisher: Association for Computational Linguistics
Book Title: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017)
Series Volume: Volume 2: Short Papers
Event Title: The 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017)
Event Location: Vancouver, Canada
Event Dates: 30.07.2017--04.08.2017
URL / URN: http://aclweb.org/anthology/P17-2056
Corresponding Links:
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. Our model which we will make publicly available outperforms previous methods on all three datasets.

Uncontrolled Keywords: UKP_p_DIP;AIPHES
Identification Number: TUD-CS-2017-0071
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
DFG-Graduiertenkollegs
DFG-Graduiertenkollegs > Research Training Group 1994 Adaptive Preparation of Information from Heterogeneous Sources
Date Deposited: 31 Mar 2017 14:17
Last Modified: 24 Jan 2020 12:03
PPN:
Corresponding Links:
Projects: AIPHES, UKP_p_DIP
Funders: German Research Foundation (DFG), grant No.GU 798/17-1
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details