Abstract
This paper presents the comparison of how using different neural network based language modeling tools for selecting the best candidate fragments affects the final output translation quality in a hybrid multi-system machine translation setup. Experiments were conducted by comparing perplexity and BLEU scores on common test cases using the same training data set. A 12-gram statistical language model was selected as a baseline to oppose three neural network based models of different characteristics. The models were integrated in a hybrid system that depends on the perplexity score of a sentence fragment to produce the best fitting translations. The results show a correlation between language model perplexity and BLEU scores as well as overall improvements in BLEU.- Anthology ID:
- W16-4502
- Volume:
- Proceedings of the Sixth Workshop on Hybrid Approaches to Translation (HyTra6)
- Month:
- December
- Year:
- 2016
- Address:
- Osaka, Japan
- Venue:
- HyTra
- SIG:
- Publisher:
- The COLING 2016 Organizing Committee
- Note:
- Pages:
- 8–15
- Language:
- URL:
- https://aclanthology.org/W16-4502
- DOI:
- Cite (ACL):
- Matīss Rikters. 2016. Neural Network Language Models for Candidate Scoring in Hybrid Multi-System Machine Translation. In Proceedings of the Sixth Workshop on Hybrid Approaches to Translation (HyTra6), pages 8–15, Osaka, Japan. The COLING 2016 Organizing Committee.
- Cite (Informal):
- Neural Network Language Models for Candidate Scoring in Hybrid Multi-System Machine Translation (Rikters, HyTra 2016)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/W16-4502.pdf