An Empirical Investigation of Multi-bridge Multilingual NMT models
Domain:
natural language processingRecord type:
paper
Creator:
Kun
Host:
In this paper, we present an extensive investigation of multi-bridge, many-to-many multilingual NMT models (MB-M2M) ie., models trained on non-English language pairs in addition to English-centric language pairs. In addition to validating previous work which shows that MB-M2M models can overcome zeroshot translation problems, our analysis reveals the following results about multibridge models: (1) it is possible to extract a reasonable amount of parallel corpora between non-English languages for low-resource languages (2) with limited non-English centric data, MB-M2M models are competitive with or outperform pivot models, (3) MB-M2M models can outperform English-Any models and perform at par with Any-English models, so a single multilingual NMT system can serve all translation directions. 6 pages
Similar
Specializing Multilingual Language Models: An Empirical StudyAn empirical investigation of measures to enhance intra-Africa tradeComparison of BIM Adoption Models between Public and Private Sectors through Empirical InvestigationAssessing total factor productivity across Africa: an empirical investigationCapital Flight and Unemployment in Nigeria: An Empirical InvestigationBank Development and Unemployment in Kenya: An Empirical Investigation