Learning Contextualised Cross-lingual Word Embeddings for Extremely Low-Resource Languages Using Parallel Corpora.
Year: 2020
Type: preprint
Abstract: We propose a new approach for learning contextualised cross-lingual word embeddings based only on a small parallel corpus (e.g. a few hundred sentence pairs). Our method obtains word embeddings via an LSTM-based encoder-decoder model that performs bidirectional translation and reconstruction of the input sentence. Through sharing model parameters among different languages, our model jointly trains the word embeddings in a common multilingual space. We also propose a simple method to combine word and subword embeddings to make use of orthographic similarities across different languages. We base our experiments on real-world data from endangered languages, namely Yongning Na, Shipibo-Konibo and Griko. Our experiments on bilingual lexicon induction and word alignment tasks show that our model outperforms existing methods by a large margin for most language pairs. These results demonstrate that, contrary to common belief, an encoder-decoder translation model is beneficial for learning cross-lingual representations, even in extremely low-resource scenarios.
Source: arXiv (Cornell University)
Authors: Takashi Wada, Tomoharu Iwata, Yūji Matsumoto, Timothy Baldwin, Jey Han Lau
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3096841893