Work

Survey of Low-Resource Machine Translation

Year: 2022

Type: article

Abstract: We present a survey covering the state of the art in low-resource machine translation (MT) research. There are currently around 7,000 languages spoken in the world and almost all language pairs lack significant resources for training machine translation models. There has been increasing interest in research addressing the challenge of producing useful translation models when very little translated training data is available. We present a summary of this topical research field and provide a description of the techniques evaluated by researchers in several recent shared tasks in low-resource MT.

Source: Computational Linguistics

DOI: 10.1162/coli_a_00446

Authors: Barry Haddow, Rachel Bawden, Antonio Valerio Miceli Barone, Jindřich Helcl, Alexandra Birch

Institutions: University of Edinburgh, Institut national de recherche en sciences et technologies du numérique

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funders: European Commission, Agence Nationale de la Recherche, Engineering and Physical Sciences Research Council

Awards: G3010527862, MTStretch: Low-resource Machine Translation, G434337789, PaRis Artificial Intelligence Research InstitutE, Global Under-Resourced MEedia Translation