TU Darmstadt / ULB / TUbiblio

Language Transfer Learning for Supervised Lexical Substitution

Hintz, Gerold and Biemann, Chris (2016):
Language Transfer Learning for Supervised Lexical Substitution.
In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, [Online-Edition: http://www.aclweb.org/anthology/P16-1012],
[Conference or Workshop Item]

Abstract

We propose a framework for lexical substitution that is able to perform transfer learning across languages. Datasets for this task are available in at least three languages (English, Italian, and German). Previous work has addressed each of these tasks in isolation. In contrast, we regard the union of three shared tasks as a combined multilingual dataset. We show that a supervised system can be trained effectively, even if training and evaluation data are from different languages. Successful transfer learning between languages suggests that the learned model is in fact independent of the underlying language. We combine state-of-the-art unsupervised features obtained from syntactic word embeddings and distributional thesauri in a supervised delexicalized ranking system. Our system improves over state of the art in the full lexical substitution task in all three languages.

Item Type: Conference or Workshop Item
Erschienen: 2016
Creators: Hintz, Gerold and Biemann, Chris
Title: Language Transfer Learning for Supervised Lexical Substitution
Language: German
Abstract:

We propose a framework for lexical substitution that is able to perform transfer learning across languages. Datasets for this task are available in at least three languages (English, Italian, and German). Previous work has addressed each of these tasks in isolation. In contrast, we regard the union of three shared tasks as a combined multilingual dataset. We show that a supervised system can be trained effectively, even if training and evaluation data are from different languages. Successful transfer learning between languages suggests that the learned model is in fact independent of the underlying language. We combine state-of-the-art unsupervised features obtained from syntactic word embeddings and distributional thesauri in a supervised delexicalized ranking system. Our system improves over state of the art in the full lexical substitution task in all three languages.

Title of Book: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics
Uncontrolled Keywords: AIPHES_area_b3
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Sprachtechnologie
DFG-Graduiertenkollegs
DFG-Graduiertenkollegs > Research Training Group 1994 Adaptive Preparation of Information from Heterogeneous Sources
Date Deposited: 30 Dec 2016 17:45
Official URL: http://www.aclweb.org/anthology/P16-1012
Identification Number: TUD-CS-2016-0169
Related URLs:
Export:

Optionen (nur für Redakteure)

View Item View Item