Improving Pivot-Based Statistical Machine Translation by Pivoting the Co-occurrence Count of Phrase Pairs

Zhu, Xiaoning; He, Zuyuan; Wu, Hua; Zhu, Conghui; Wang, Haifeng; Zhao, Tiejun

doi:10.3115/v1/d14-1174

Cited by 18 publications

(17 citation statements)

References 12 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Up to this point, representative pivot translation methods in SMT have been explained. Other related research studies in pivot translation are primarily based on the triangulation for PBMT and focuse on discussions to further improve accuracy (Zhu, He, Wu, Zhu, Wang, and Zhao 2014;Levinboim and Chiang 2015;Dabre, Cromieres, Kurohashi, and Bhattacharyya 2015). The process of correctly estimating the translation probability is a problem in triangulation.…”

Section: Related Workmentioning

confidence: 99%

Syntactic Matching Methods in Pivot Translation

Miura

Neubig

Sudoh

et al. 2018

Journal of Natural Language Processing

View full text Add to dashboard Cite

The pivot translation is useful method for translating between languages that contain little or no parallel data by utilizing equivalents in an intermediate language such as English. Commonly, phrase-based or tree-based pivot translation methods merge source-pivot and pivot-target translation models into a source-target model. This tactic is known as triangulation. However, the combination is based on the surface forms of constituent words, and it often produces incorrect source-target phrase pairs because of interlingual differences and semantic ambiguities in the pivot language. The translation accuracy is thus degraded. This paper proposes a triangulation approach that utilizes syntactic subtrees in the pivot language to avoid incorrect phrase combinations by distinguishing pivot language words by their syntactic roles. The results of the experiments conducted on the United Nations Parallel Corpus demonstrate that the proposed method is superior to other pivot translation approaches in all tested combinations of languages.

show abstract

Section: Related Workmentioning

confidence: 99%

Syntactic Matching Methods in Pivot Translation

Miura

Neubig

Sudoh

et al. 2018

Journal of Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…Nakayama and Nishida (2016) show that using multimedia information as pivot also benefits zero-resource translation. However, pivot-based approaches usually need to divide the decoding process into two steps, which is not only more computationally expensive, but also potentially suffers from the error propagation problem (Zhu et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

“…The above two-step decoding process potentially suffers from the error propagation problem (Zhu et al, 2013): the translation errors made in the first step (i.e., source-to-pivot translation) will affect the second step (i.e., pivot-to-target translation). Therefore, it is necessary to explore methods to directly model source-to-target translation without parallel corpora available.…”

Section: Introductionmentioning

confidence: 99%

A Teacher-Student Framework for Zero-Resource Neural Machine Translation

Chen¹,

Liu²,

Cheng³

et al. 2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

While end-to-end neural machine translation (NMT) has made remarkable progress recently, it still suffers from the data scarcity problem for low-resource language pairs and domains. In this paper, we propose a method for zero-resource NMT by assuming that parallel sentences have close probabilities of generating a sentence in a third language. Based on the assumption, our method is able to train a source-to-target NMT model ("student") without parallel corpora available guided by an existing pivot-to-target NMT model ("teacher") on a source-pivot parallel corpus. Experimental results show that the proposed method significantly improves over a baseline pivot-based model by +3.0 BLEU points across various language pairs.

show abstract

“…For example, Cui et al (2013) develop an effective approach to optimize phrase scoring and corpus weighting jointly using graph-based random walk. Zhu et al (2013) apply a random walk method to discover implicit relations between the phrases of different languages. Aiming to better evaluate translation quality at the document level, Gong and Li (2013) run PageRank algorithm to assign weights to words in translation evaluation.…”

Section: Related Workmentioning

confidence: 99%

Graph-Based Collective Lexical Selection for Statistical Machine Translation

Xiong

Huang

et al. 2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Lexical selection is of great importance to statistical machine translation. In this paper, we propose a graph-based framework for collective lexical selection. The framework is established on a translation graph that captures not only local associations between source-side content words and their target translations but also targetside global dependencies in terms of relatedness among target items. We also introduce a random walk style algorithm to collectively identify translations of sourceside content words that are strongly related in translation graph. We validate the effectiveness of our lexical selection framework on Chinese-English translation. Experiment results with large-scale training data show that our approach significantly improves lexical selection.

show abstract

Improving Pivot-Based Statistical Machine Translation by Pivoting the Co-occurrence Count of Phrase Pairs

Cited by 18 publications

References 12 publications

Syntactic Matching Methods in Pivot Translation

Syntactic Matching Methods in Pivot Translation

A Teacher-Student Framework for Zero-Resource Neural Machine Translation

Graph-Based Collective Lexical Selection for Statistical Machine Translation

Contact Info

Product

Resources

About