Translation inference through multi-lingual word embedding similarity
- This paper describes our contribution to the Shared Task on Translation Inference across Dictionaries (TIAD-2019). In our approach, we construct a multi-lingual word embedding space by projecting new languages in the feature space of a language for which a pretrained embedding model exists. We use the similarity of the word embeddings to predict candidate translations. Even if our projection methodology is rather simplistic, our system outperforms the other participating systems with respect to the F1 measure for the language pairs which we predicted.
Author: | Kathrin Donandt, Christian ChiarcosORCiDGND |
---|---|
URN: | urn:nbn:de:bvb:384-opus4-1040754 |
Frontdoor URL | https://opus.bibliothek.uni-augsburg.de/opus4/104075 |
URL: | https://ceur-ws.org/Vol-2493/ |
Parent Title (English): | TIAD 2019 - TIAD-2019 Shared Task - Translation Inference Across Dictionaries: Proceedings of TIAD-2019 Shared Task – Translation Inference Across Dictionaries co-located with the 2nd Language, Data and Knowledge Conference (LDK 2019), Leipzig, Germany, May 20, 2019 |
Publisher: | CEUR-WS |
Place of publication: | Aachen |
Editor: | Jorge Garcia, Besim Kabashi, Ilan Kernerman |
Type: | Conference Proceeding |
Language: | English |
Year of first Publication: | 2019 |
Publishing Institution: | Universität Augsburg |
Release Date: | 2023/05/15 |
First Page: | 42 |
Last Page: | 53 |
Series: | CEUR Workshop Proceedings ; 2493 |
Institutes: | Philologisch-Historische Fakultät |
Philologisch-Historische Fakultät / Angewandte Computerlinguistik | |
Philologisch-Historische Fakultät / Angewandte Computerlinguistik / Lehrstuhl für Angewandte Computerlinguistik (ACoLi) | |
Dewey Decimal Classification: | 4 Sprache / 40 Sprache / 400 Sprache |
Licence (German): | CC-BY 4.0: Creative Commons: Namensnennung (mit Print on Demand) |