Alexandre Helle
Alexandre Helle has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Manuel Herranz
PANGEANIC
3 shared publications Francisco Casacuberta
PRHLT Research Center Universitat Politècnica de València
2 shared publicationsMiguel Domingo
PRHLT Research Center Universitat Politècnica de València
2 shared publications- Amando Estela
Pangeanic / B.I Europa -PangeaMT Technologies Division
1 shared publication - Francisco Casacuberta
Universitat Politècnica de València
1 shared publication Laurent Bié
Pangeanic / B.I Europa -PangeaMT Technologies Division
1 shared publication
Latest Publications
- Top Cited Papers
- 26 February 2023
- Published by Springer Nature
- p. 545-554
How Much Does Tokenization Affect Neural Machine Translation?
- 26 February 2023
- Published by Springer Nature
- p. 545-554
Top Cited PapersHow Much Does Tokenization Affect Neural Machine Translation?
- Open Access
Incremental Adaptation of NMT for Professional Post-editors: A User Study
A common use of machine translation in the industry is providing initial translation hypotheses, which are later supervised and post-edited by a human expert. During this revision process, new bilingual data are continuously generated. Machine translation systems can benefit from these new data, incrementally updating the underlying models under an online learning paradigm. We conducted a user study on this scenario, for a neural machine translation system. The experimentation was carried out by professional translators, with a vast experience in machine translation post-editing. The results showed a reduction in the required amount of human effort needed when post-editing the outputs of the system, improvements in the translation quality and a positive perception of the adaptive system by the users.
Open AccessIncremental Adaptation of NMT for Professional Post-editors: A User Study
A common use of machine translation in the industry is providing initial translation hypotheses, which are later supervised and post-edited by a human expert. During this revision process, new bilingual data are continuously generated. Machine translation systems can benefit from these new data, incrementally updating the underlying models under an online learning paradigm. We conducted a user study on this scenario, for a neural machine translation system. The experimentation was carried out by professional translators, with a vast experience in machine translation post-editing. The results showed a reduction in the required amount of human effort needed when post-editing the outputs of the system, improvements in the translation quality and a positive perception of the adaptive system by the users.
- Open Access
How Much Does Tokenization Affect Neural Machine Translation?
Tokenization or segmentation is a wide concept that covers simple processes such as separating punctuation from words, or more sophisticated processes such as applying morphological knowledge. Neural Machine Translation (NMT) requires a limited-size vocabulary for computational cost and enough examples to estimate word embeddings. Separating punctuation and splitting tokens into words or subwords has proven to be helpful to reduce vocabulary and increase the number of examples of each word, improving the translation quality. Tokenization is more challenging when dealing with languages with no separator between words. In order to assess the impact of the tokenization in the quality of the final translation on NMT, we experimented on five tokenizers over ten language pairs. We reached the conclusion that the tokenization significantly affects the final translation quality and that the best tokenizer differs for different language pairs.
Open AccessHow Much Does Tokenization Affect Neural Machine Translation?
Tokenization or segmentation is a wide concept that covers simple processes such as separating punctuation from words, or more sophisticated processes such as applying morphological knowledge. Neural Machine Translation (NMT) requires a limited-size vocabulary for computational cost and enough examples to estimate word embeddings. Separating punctuation and splitting tokens into words or subwords has proven to be helpful to reduce vocabulary and increase the number of examples of each word, improving the translation quality. Tokenization is more challenging when dealing with languages with no separator between words. In order to assess the impact of the tokenization in the quality of the final translation on NMT, we experimented on five tokenizers over ten language pairs. We reached the conclusion that the tokenization significantly affects the final translation quality and that the best tokenizer differs for different language pairs.