Do Dinh, Erik-Lân ; Gurevych, Iryna (2016)
Token-Level Metaphor Detection using Neural Networks.
San Diego, CA, USA
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (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.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2016 |
| Autor(en): | Do Dinh, Erik-Lân ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | Token-Level Metaphor Detection using Neural Networks |
| Sprache: | Englisch |
| Publikationsjahr: | Juni 2016 |
| Verlag: | Association for Computational Linguistics |
| Buchtitel: | Proceedings of The Fourth Workshop on Metaphor in NLP held in conjunction with NAACL 2016 |
| Veranstaltungsort: | San Diego, CA, USA |
| URL / URN: | http://www.aclweb.org/anthology/W16-1104 |
| Kurzbeschreibung (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. |
| Freie Schlagworte: | Knowledge Discovery in Scientific Literature;UKP_reviewed;Metaphor,Classification,Neural Network,Word Embeddings |
| ID-Nummer: | TUD-CS-2016-0075 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 31 Dez 2016 14:29 |
| Letzte Änderung: | 24 Jan 2020 12:03 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum