TU Darmstadt / ULB / TUbiblio

Prediction of Frame-to-Frame Relations in the FrameNet Hierarchy with Frame Embeddings

Botschen, Teresa and Mousselly-Sergieh, Hatem and Gurevych, Iryna :
Prediction of Frame-to-Frame Relations in the FrameNet Hierarchy with Frame Embeddings.
[Online-Edition: http://www.aclweb.org/anthology/W17-2618]
Proceedings of th 2nd Workshop on Representation Learning for NLP (RepL4NLP, held in conjunction with ACL 2017)
[Conference or Workshop Item] , (2017)

Official URL: http://www.aclweb.org/anthology/W17-2618

Abstract

Automatic completion of frame-to-frame (F2F) relations in the FrameNet (FN) hierarchy has received little attention, although they incorporate meta-level commonsense knowledge and are used in downstream approaches. We address the problem of sparsely annotated F2F relations. First, we examine whether the manually defined F2F relations emerge from text by learning text-based frame embeddings. Our analysis reveals insights about the difficulty of reconstructing F2F relations purely from text. Second, we present different systems for predicting F2F relations; our best-performing one uses the FN hierarchy to train on and to ground embeddings in. A comparison of systems and embeddings exposes the crucial influence of knowledge-based embeddings to a system’s performance in predicting F2F relations.

Item Type: Conference or Workshop Item
Erschienen: 2017
Creators: Botschen, Teresa and Mousselly-Sergieh, Hatem and Gurevych, Iryna
Title: Prediction of Frame-to-Frame Relations in the FrameNet Hierarchy with Frame Embeddings
Language: English
Abstract:

Automatic completion of frame-to-frame (F2F) relations in the FrameNet (FN) hierarchy has received little attention, although they incorporate meta-level commonsense knowledge and are used in downstream approaches. We address the problem of sparsely annotated F2F relations. First, we examine whether the manually defined F2F relations emerge from text by learning text-based frame embeddings. Our analysis reveals insights about the difficulty of reconstructing F2F relations purely from text. Second, we present different systems for predicting F2F relations; our best-performing one uses the FN hierarchy to train on and to ground embeddings in. A comparison of systems and embeddings exposes the crucial influence of knowledge-based embeddings to a system’s performance in predicting F2F relations.

Title of Book: Proceedings of th 2nd Workshop on Representation Learning for NLP (RepL4NLP, held in conjunction with ACL 2017)
Uncontrolled Keywords: reviewed;UKP_reviewed;AIPHES_area_c3
Divisions: Department of Computer Science
Department of Computer Science > Ubiquitous Knowledge Processing
DFG-Graduiertenkollegs
DFG-Graduiertenkollegs > Research Training Group 1994 Adaptive Preparation of Information from Heterogeneous Sources
Event Location: Vancouver, Canada
Date Deposited: 31 May 2017 14:55
Official URL: http://www.aclweb.org/anthology/W17-2618
Identification Number: TUD-CS-2017-0123
Export:

Optionen (nur für Redakteure)

View Item View Item