NUIG at TIAD 2021: Cross-lingual word embeddings for translation inference
Ahmadi, Sina Ojha, Atul Kr. Banerjee, Shubhanker McCrae, John P.
Ahmadi, Sina
Ojha, Atul Kr.
Banerjee, Shubhanker
McCrae, John P.
Loading...
Repository DOI
Publication Date
2021-09-01
Type
Conference Paper
Downloads
Citation
Ahmadi, Sina, Ojha, Atul Kr., Banerjee, Shubhanker, & McCrae, John P. (2021). NUIG at TIAD 2021: Cross-lingual word embeddings for translation inference. Paper presented at the 3rd Conference on Language, Data and Knowledge (LDK 2021), Zaragoza, Spain, 01- 04 September. https://doi.org/10.13025/nxqc-n767
Abstract
Inducing new translation pairs across dictionaries is an important task that facilitates processing and maintaining lexicographical data. This paper describes our submissions to the Translation Inference Across Dictionaries (TIAD) shared task of 2021. Our systems mainly rely on the MUSE and VecMap cross-lingual word embedding mapping to create new translation pairs between English, French and Portuguese data. We also create two regression models based on the graph analysis features. Our systems perform above the baseline systems.
Funder
Publisher
Publisher DOI
Rights
CC BY-NC-ND 3.0 IE