Can I read Best Practices for Learning Domain-Specific Cross-Lingual Embeddings on EtoBox?

Best Practices for Learning Domain-Specific Cross-Lingual Embeddings by Shakurova, Lena; Nyari, Beata; Li, Chao; Rotaru, Mihai is a scholarly article available to read on EtoBox.

What is Best Practices for Learning Domain-Specific Cross-Lingual Embeddings about?

Cross-lingual embeddings aim to represent words in multiple languages in a shared vector space by capturing semantic similarities across languages. They are a crucial component for scaling tasks to multiple languages by transferring knowledge from languages with rich resources to low-resource languages. A common approach to learning cross-lingual embeddings is to train monolingual embeddings separately for each language and learn a linear projection from the monolingual spaces into a shared space, where the mapping relies on a small seed dictionary. While there are high-quality generic seed dictionaries and pre-trained cross-lingual embeddings available for many language pairs, there is little research on how they perform on specialised tasks. In this paper, we investigate the best practices for constructing the seed dictionary for a specific domain. We evaluate the embeddings on the sequence labelling task of Curriculum Vitae parsing and show that the size of a bilingual dictionary, the frequency of the dictionary words in the domain corpora and the source of data (task-specific vs generic) influence the performance. We also show that the less training data is available in the low

Author

Shakurova, Lena; Nyari, Beata; Li, Chao; Rotaru, Mihai

Published

2019

Language

EN