Logo Logo
Switch Language to German
Dufter, Philipp; Zhao, Mengjie; Schmitt, Martin; Fraser, Alexander; Schütze, Hinrich (July 2018): Embedding Learning Through Multilingual Concept Induction. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), July 15-20, 2018, Melbourne, Australia.


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.