Messenger RNA

Translation (biology)

Metric (unit)

Machine translation

Example-based machine translation

Gene

Image (mathematics)

Similarity (geometry)

Semantic similarity

Machine learning

Machine translation software usability

Evaluation of machine translation

Artificial intelligence

Composite material

Economics

Chemistry

Materials science

Natural language processing

Range (aeronautics)

Operations management

Computer science

Biochemistry

BLEU

While most neural machine translation (NMT)systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can significantly improve final translation accuracy. However, training with BLEU has some limitations: it doesn’t assign partial credit, it has a limited range of output values, and it can penalize semantically correct hypotheses if they differ lexically from the reference. In this paper, we introduce an alternative reward function for optimizing NMT systems that is based on recent work in semantic similarity. We evaluate on four disparate languages trans-lated to English, and find that training with our proposed metric results in better translations as evaluated by BLEU, semantic similarity, and human evaluation, and also that the optimization procedure converges faster. Analysis suggests that this is because the proposed metric is more conducive to optimization, assigning partial credit and providing more diversity in scores than BLEU

Beyond BLEU:Training Neural Machine Translation with Semantic Similarity