TU Darmstadt / ULB / TUbiblio

Token-Level Metaphor Detection using Neural Networks

Do Dinh, Erik-Lân and Gurevych, Iryna (2016):
Token-Level Metaphor Detection using Neural Networks.
In: Proceedings of The Fourth Workshop on Metaphor in NLP held in conjunction with NAACL 2016, Association for Computational Linguistics, San Diego, CA, USA, [Online-Edition: http://www.aclweb.org/anthology/W16-1104],
[Conference or Workshop Item]

Abstract

Automatic metaphor detection usually relies on various features, incorporating e.g. selectional preference violations or concreteness ratings to detect metaphors in text. These features rely on background corpora, hand-coded rules or additional, manually created resources, all specific to the language the system is being used on. We present a novel approach to metaphor detection using a neural network in combination with word embeddings, a method that has already proven to yield promising results for other natural language processing tasks. We show that foregoing manual feature engineering by solely relying on word embeddings trained on large corpora produces comparable results to other systems, while removing the need for additional resources.

Item Type: Conference or Workshop Item
Erschienen: 2016
Creators: Do Dinh, Erik-Lân and Gurevych, Iryna
Title: Token-Level Metaphor Detection using Neural Networks
Language: English
Abstract:

Automatic metaphor detection usually relies on various features, incorporating e.g. selectional preference violations or concreteness ratings to detect metaphors in text. These features rely on background corpora, hand-coded rules or additional, manually created resources, all specific to the language the system is being used on. We present a novel approach to metaphor detection using a neural network in combination with word embeddings, a method that has already proven to yield promising results for other natural language processing tasks. We show that foregoing manual feature engineering by solely relying on word embeddings trained on large corpora produces comparable results to other systems, while removing the need for additional resources.

Title of Book: Proceedings of The Fourth Workshop on Metaphor in NLP held in conjunction with NAACL 2016
Publisher: Association for Computational Linguistics
Uncontrolled Keywords: Knowledge Discovery in Scientific Literature;UKP_reviewed;Metaphor,Classification,Neural Network,Word Embeddings
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Event Location: San Diego, CA, USA
Date Deposited: 31 Dec 2016 14:29
Official URL: http://www.aclweb.org/anthology/W16-1104
Identification Number: TUD-CS-2016-0075
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item