Farsi - German statistical machine translation through bridge language

Bakhshaei, Somayeh; Khadivi, Shahram; Riahi, Noushin

doi:10.1109/istel.2010.5734087

Cited by 9 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use Verbmobil (Bakhshaei et al, 2010), an English-Persian data set, this data set can show the effectiveness of the model on scarce data resources. The detailed information of the data set is provided in 1.…”

Section: Datasetmentioning

confidence: 99%

A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings

Bastan¹,

Khadivi²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Neural Machine Translation (NMT) models are strong enough to convey semantic and syntactic information from the source language to the target language. However, these models are suffering from the need for a large amount of data to learn the parameters. As a result, for languages with scarce data, these models are at risk of underperforming. We propose to augment attention based neural network with reordering information to alleviate the lack of data. This augmentation improves the translation quality for both English to Persian and Persian to English by up to 6% BLEU absolute over the baseline models.

show abstract

Section: Datasetmentioning

confidence: 99%

A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings

Bastan¹,

Khadivi²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Pivot-based model training. In phrasebased MT, there have been many efforts to combine phrase/word level features of source-pivot and pivot-target into a source→target system (Utiyama and Isahara, 2007;Wu and Wang, 2007;Bakhshaei et al, 2010;Zahabi et al, 2013;Zhu et al, 2014;Miura et al, 2015). In NMT, Sestorain et al (2018) applies the NMT prediction score and a language model score to each synthetic example as gradient weights.…”

Section: Related Workmentioning

confidence: 99%

“…In phrasebased MT, there have been many efforts to combine phrase/word level features of source-pivot and pivot-target into a source→target system (Utiyama and Isahara, 2007;Wu and Wang, 2007;Bakhshaei et al, 2010;Zahabi et al, 2013;Zhu et al, 2014;Miura et al, 2015). In NMT, Our work is based on transfer learning (Zoph et al, 2016) and belongs to the third category: model training.…”

Section: Pivot-based Model Trainingmentioning

confidence: 99%

Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages

Kim¹,

Petrov²,

Petrushkov³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

View full text Add to dashboard Cite

We present effective pre-training strategies for neural machine translation (NMT) using parallel corpora involving a pivot language, i.e., source-pivot and pivot-target, leading to a significant improvement in source→target translation. We propose three methods to increase the relation among source, pivot, and target languages in the pre-training: 1) step-wise training of a single model for different language pairs, 2) additional adapter component to smoothly connect pre-trained encoder and decoder, and 3) cross-lingual encoder training via autoencoding of the pivot language. Our methods greatly outperform multilingual models up to +2.6% BLEU in WMT 2019 French→German and German→Czech tasks. We show that our improvements are valid also in zero-shot/zeroresource scenarios.

show abstract

“…In another study, Bakhshaei et al (2010) used English as a bridging language while translating from Persian to German and concluded that using the pivot technique in phrase-level combination outperforms direct translation system. Furthermore, Al-Hunaity et al (2010) presented a comparison between two common pivot strategies; phrase translation and sentence translation in order to enhance Danish-Arabic SMT system.…”

Section: Previous Workmentioning

confidence: 99%

Persian–Spanish Low-Resource Statistical Machine Translation Through English as Pivot Language

Ahmadnia

Serrano

Haffari

2017

RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning

View full text Add to dashboard Cite

This paper is an attempt to exclusively focus on investigating the pivot language technique in which a bridging language is utilized to increase the quality of the Persian-Spanish low-resource Statistical Machine Translation (SMT). In this case, English is used as the bridging language, and the Persian-English SMT is combined with the English-Spanish one, where the relatively large corpora of each may be used in support of the Persian-Spanish pairing. Our results indicate that the pivot language technique outperforms the direct SMT processes currently in use between Persian and Spanish. Furthermore, we investigate the sentence translation pivot strategy and the phrase translation in turn, and demonstrate that, in the context of the Persian-Spanish SMT system, the phrase-level pivoting outperforms the sentence-level pivoting. Finally we suggest a method called combination model in which the standard direct model and the best triangulation pivoting model are blended in order to reach a high-quality translation.

show abstract

Farsi - German statistical machine translation through bridge language

Cited by 9 publications

References 5 publications

A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings

A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings

Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages

Persian–Spanish Low-Resource Statistical Machine Translation Through English as Pivot Language

Contact Info

Product

Resources

About