Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation
Autor: | Aditya Siddhant, Naveen Ari, Karthik Raman, Melvin Johnson, Jason Riesa, Ankur Bapna, Henry Tsai, Orhan Firat |
---|---|
Rok vydání: | 2019 |
Předmět: |
FOS: Computer and information sciences
Cross lingual Computer Science - Computation and Language Machine translation Computer science business.industry 02 engineering and technology General Medicine computer.software_genre Translation (geometry) Sequence labeling Set (abstract data type) 020204 information systems 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Transfer of learning business computer Encoder Computation and Language (cs.CL) Natural language processing |
Zdroj: | AAAI |
DOI: | 10.48550/arxiv.1909.00437 |
Popis: | The recently proposed massively multilingual neural machine translation (NMT) system has been shown to be capable of translating over 100 languages to and from English within a single model (Aharoni, Johnson, and Firat 2019). Its improved translation performance on low resource languages hints at potential cross-lingual transfer capability for downstream tasks. In this paper, we evaluate the cross-lingual effectiveness of representations from the encoder of a massively multilingual NMT model on 5 downstream classification and sequence labeling tasks covering a diverse set of over 50 languages. We compare against a strong baseline, multilingual BERT (mBERT) (Devlin et al. 2018), in different cross-lingual transfer learning scenarios and show gains in zero-shot transfer in 4 out of these 5 tasks. |
Databáze: | OpenAIRE |
Externí odkaz: |