Multimodal Machine Translation with Embedding Prediction
| Autor: | Mamoru Komachi, Hayahide Yamagishi, Tosho Hirasawa, Yukio Matsumura |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
050101 languages & linguistics Computer Science - Computation and Language Machine translation Computer science business.industry 05 social sciences Context (language use) 02 engineering and technology computer.software_genre Translation (geometry) Word problem (mathematics education) 0202 electrical engineering electronic engineering information engineering Embedding 020201 artificial intelligence & image processing 0501 psychology and cognitive sciences Artificial intelligence business Computation and Language (cs.CL) computer Word (computer architecture) Natural language Natural language processing BLEU |
| Zdroj: | NAACL-HLT (Student Research Workshop) Scopus-Elsevier |
| DOI: | 10.18653/v1/n19-3012 |
| Popis: | Multimodal machine translation is an attractive application of neural machine translation (NMT). It helps computers to deeply understand visual objects and their relations with natural languages. However, multimodal NMT systems suffer from a shortage of available training data, resulting in poor performance for translating rare words. In NMT, pretrained word embeddings have been shown to improve NMT of low-resource domains, and a search-based approach is proposed to address the rare word problem. In this study, we effectively combine these two approaches in the context of multimodal NMT and explore how we can take full advantage of pretrained word embeddings to better translate rare words. We report overall performance improvements of 1.24 METEOR and 2.49 BLEU and achieve an improvement of 7.67 F-score for rare word translation. Comment: 6 pages; NAACL 2019 Student Research Workshop |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|