arXiv Open Access 2020

Combining Pretrained High-Resource Embeddings and Subword Representations for Low-Resource Languages

Machel Reid Edison Marrese-Taylor Yutaka Matsuo

Lihat Sumber

Abstrak

The contrast between the need for large amounts of data for current Natural Language Processing (NLP) techniques, and the lack thereof, is accentuated in the case of African languages, most of which are considered low-resource. To help circumvent this issue, we explore techniques exploiting the qualities of morphologically rich languages (MRLs), while leveraging pretrained word vectors in well-resourced languages. In our exploration, we show that a meta-embedding approach combining both pretrained and morphologically-informed word embeddings performs best in the downstream task of Xhosa-English translation.

Topik & Kata Kunci

cs.CL cs.LG

Penulis (3)

Machel Reid

Edison Marrese-Taylor

Yutaka Matsuo

Format Sitasi

APA MLA BibTeX

Reid, M., Marrese-Taylor, E., Matsuo, Y. (2020). Combining Pretrained High-Resource Embeddings and Subword Representations for Low-Resource Languages. https://arxiv.org/abs/2003.04419

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2020
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓