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

Ahmadnia, Benyamin; Serrano, Javier; Haffari, Gholamreza

doi:10.26615/978-954-452-049-6_004

Cited by 23 publications

(16 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Phrase table combination could also be used in pivot approaches to overcome the data scarcity between src-trg language pairs [1][2][3][4]6,13,14]. The phrase table combination outperformed direct translation or other pivot approaches, namely, sentence translation and triangulation.…”

Section: Related Work 21 Phrase Table Combinationmentioning

confidence: 99%

“…The phrase table combination outperformed direct translation or other pivot approaches, namely, sentence translation and triangulation. We identified that the phrase table combination in the pivot approaches uses the same symmetrization of word alignment, i.e., gdfand [1][2][3][4]6,13,14]. This is because the gdfand is a standard symmetrization of word alignment in statistical machine translation (SMT) [7].…”

Section: Related Work 21 Phrase Table Combinationmentioning

confidence: 99%

“…Low-resource languages suffer from data scarcity, which leads to poor translation quality. One of the common techniques to improve translation quality is using a phrase table combination in pivot approaches [1][2][3][4][5][6]. The phrase table or translation model comes from a word alignment model that uses a symmetrization technique to generate phrase pairs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Phrase Table Combination Based on Symmetrization of Word Alignment for Low-Resource Languages

et al. 2021

View full text Add to dashboard Cite

Phrase table combination in pivot approaches can be an effective method to deal with low-resource language pairs. The common practice to generate phrase tables in pivot approaches is to use standard symmetrization, i.e., grow-diag-final-and. Although some researchers found that the use of non-standard symmetrization could improve bilingual evaluation understudy (BLEU) scores, the use of non-standard symmetrization has not been commonly employed in pivot approaches. In this study, we propose a strategy that uses the non-standard symmetrization of word alignment in phrase table combination. The appropriate symmetrization is selected based on the highest BLEU scores in each direct translation of source–target, source–pivot, and pivot–target of Kazakh–English (Kk–En) and Japanese–Indonesian (Ja–Id). Our experiments show that our proposed strategy outperforms the direct translation in Kk–En with absolute improvements of 0.35 (a 11.3% relative improvement) and 0.22 (a 6.4% relative improvement) BLEU points for 3-gram and 5-gram, respectively. The proposed strategy shows an absolute gain of up to 0.11 (a 0.9% relative improvement) BLEU points compared to direct translation for 3-gram in Ja–Id. Our proposed strategy using a small phrase table obtains better BLEU scores than a strategy using a large phrase table. The size of the target monolingual and feature function weight of the language model (LM) could reduce perplexity scores.

show abstract

Section: Related Work 21 Phrase Table Combinationmentioning

confidence: 99%

Section: Related Work 21 Phrase Table Combinationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Phrase Table Combination Based on Symmetrization of Word Alignment for Low-Resource Languages

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Formal and informal translations address several different characteristics. Inflection, declination and grammatical gender are important features of Spanish language [1,3].…”

Section: Introductionmentioning

confidence: 99%

Knowledge Graphs Effectiveness in Neural Machine Translation Improvement

Ahmadnia

Dorr

Kordjamshidi

2020

csci

Self Cite

View full text Add to dashboard Cite

Neural Machine Translation (NMT) systems require a massive amount of Maintaining semantic relations between words during the translation process yields more accurate target-language output from Neural Machine Translation (NMT). Although difficult to achieve from training data alone, it is possible to leverage Knowledge Graphs (KGs) to retain source-language semantic relations in the corresponding target-language translation. The core idea is to use KG entity relations as embedding constraints to improve the mapping from source to target. This paper describes two embedding constraints, both of which employ Entity Linking (EL)---assigning a unique identity to entities---to associate words in training sentences with those in the KG: (1) a monolingual embedding constraint that supports an enhanced semantic representation of the source words through access to relations between entities in a KG; and (2) a bilingual embedding constraint that forces entity relations in the source-language to be carried over to the corresponding entities in the target-language translation. The method is evaluated for English-Spanish translation exploiting Freebase as a source of knowledge. Our experimental results show that exploiting KG information not only decreases the number of unknown words in the translation but also improves translation quality.

show abstract

“…Currently, English as lingua franca has more datasets compared to other languages. Thus, pivot researchers commonly use English as a bridge between source to target (Paul et al, 2013;El Kholy et al, 2013;Ahmadnia et al, 2017;Dabre et al, 2015;Trieu, 2017). However, Paul et al, (2013) and Dabre et al, (2015) have shown that using non-English as pivot language could be a better option to improve the translation results for particular language pair.…”

Section: Introductionmentioning

confidence: 99%

DBMS-KU Interpolation for WMT19 News Translation Task

Budiwati¹,

Siagian²,

Fatyanosa³

et al. 2019

Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

View full text Add to dashboard Cite

This paper presents the participation of DBMS-KU Interpolation system in WMT19 shared task, namely, Kazakh-English language pair. We examine the use of interpolation method using a different language model order. Our Interpolation system combines a direct translation with Russian as a pivot language. We use 3-gram and 5-gram language model orders to perform the language translation in this work. To reduce noise in the pivot translation process, we prune the phrase table of source-pivot and pivot-target. Our experimental results show that our Interpolation system outperforms the Baseline in terms of BLEU-cased score by +0.5 and +0.1 points in Kazakh-English and English-Kazakh, respectively. In particular, using the 5-gram language model order in our system could obtain better BLEU-cased score than utilizing the 3-gram one. Interestingly, we found that by employing the Interpolation system could reduce the perplexity score of English-Kazakh when using 3-gram language model order.

show abstract

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

Cited by 23 publications

References 11 publications

Phrase Table Combination Based on Symmetrization of Word Alignment for Low-Resource Languages

Phrase Table Combination Based on Symmetrization of Word Alignment for Low-Resource Languages

Knowledge Graphs Effectiveness in Neural Machine Translation Improvement

DBMS-KU Interpolation for WMT19 News Translation Task

Contact Info

Product

Resources

About