Logo Logo
Hilfe
Hilfe
Switch Language to English

Dufter, Philipp; Zhao, Mengjie; Schmitt, Martin; Fraser, Alexander und Schütze, Hinrich (Juli 2018): Embedding Learning Through Multilingual Concept Induction. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Melbourne, Australia, July 15-20, 2018. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics Bd. 1 Association for Computational Linguistics. S. 1520-1530 [PDF, 453kB]

[thumbnail of P18-1141.pdf]
Vorschau
Download (453kB)

Abstract

We present a new method for estimating vector space representations of words: embedding learning by concept induction. We test this method on a highly parallel corpus and learn semantic representations of words in 1259 different languages in a single common space. An extensive experimental evaluation on crosslingual word similarity and sentiment analysis indicates that concept-based multilingual embedding learning performs better than previous approaches.

Dokument bearbeiten Dokument bearbeiten