A Comparison of Pivot Methods for Phrase-Based Statistical Machine Translation

By Masso Utiyama, Hitoshi Isahara. 2007

215 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Edinburgh’s Phrase-based Machine Translation Systems for WMT-14 (2014, methodology): “Given the phrase-table for Urdu-English p(ūi|ēi) and the phrase-table for English-Hindi p(ēi|h̄i), we estimated a Urdu-Hindi phrase-table p(ūi|h̄i) using the well-known convolution model (Utiyama and Isahara, 2007; Wu and Wang, 2007):”
Complete Multilingual Neural Machine Translation (2020, neutral): “An alternative approach is called bridging (Cohn and Lapata, 2007; Wu and Wang, 2007; Utiyama and Isahara, 2007).”
Zero-Resource Translation with Multi-Lingual Neural Machine Translation (2016, methodology): “Zero-resource translation has been addressed by pivot-based translation in traditional machine translation research (Wu and Wang, 2007; Utiyama and Isahara, 2007; Habash and Hu, 2009), but we explore a way to use the multi-way, multilingual neural model to translate directly from a source to target ”
Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision (2023, methodology): “Using these representations, we cast the TTS problem as a “translation” from text transcripts to acoustic tokens with semantic token representations serving as a pivot “language” (Utiyama and Isahara, 2007).”
A Teacher-Student Framework for Zero-Resource Neural Machine Translation (2017, methodology): “This idea is widely used in SMT (de Gispert and Mari˜no, 2006; Cohn and Lapata, 2007; Utiyama and Isahara, 2007; Wu and Wang, 2007; Bertoldi et al., 2008; Wu and Wang, 2009; Zahabi et al., 2013; Kholy et al., 2013).”
Paraphrasing Revisited with Neural Machine Translation (2017, methodology): “Wieting et al. (2015) take the paraphrases contained in PPDB and embed them into a low-dimensional space using a recursive neural network similar to Socher et al.”
A neural interlingua for multilingual machine translation (2018, methodology): “Various extensions of the pivot technique have been proposed over the years, see (Utiyama and Isahara, 2007), (Miura et al.”
Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations (2019, background): “…et al., 2018; Ses-torain et al., 2018), that zero-shot NMT is sensitive to training conditions, and the translation quality usually lags behind the pivot-based meth-ods which use a shared language as a bridge for translation (Utiyama and Isahara, 2007; Cheng et al., 2016; Chen et al., 2017).”
Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages (2019, methodology): “…is usually done with pivoting through English, i.e., translating French ( source ) input to English ( pivot ) ﬁrst with a French → English model which is later translated to German ( target ) with a English → German model (De Gispert and Marino, 2006; Utiyama and Isahara, 2007; Wu and Wang, 2007).”
Neural Machine Translation with Pivot Languages (2016, background): “For low-resource language pairs, a pivot language is introduced to “bridge” source and target language in statical machine translation [De Gispert and Marino, 2006; Cohn and Lapata, 2007; Utiyama and Isahara, 2007; Wu and Wang, 2007; Bertoldi et al., 2008; Zahabi et al., 2013; El Kholy et al., 2013]”
Unsupervised Pivot Translation for Distant Languages (2019, background): “Pivot Translation Pivot translation has long been studied in statistical machine translation to improve the accuracy of low/zero-resource translation (Wu and Wang, 2007; Utiyama and Isahara, 2007).”
Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora (2007, methodology): “A single translation is then selected by ﬁnding the candidate that yields the best overall score (Och and Ney, 2001; Utiyama and Isahara, 2007) or by co-training (Callison-Burch and Osborne, 2003).”
Investigations on large-scale lightly-supervised training for statistical machine translation. (2008, background): “There is some research trying to tackle this problem by using an intermediate pivot language, e.g. [1].”
Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach (2019, background): “[2018] introduce a third modal information, Chinese captions, for language pivoting [Utiyama and Isahara, 2007; Wu and Wang, 2007].”
Improving machine translation via triangulation and transliteration (2014, unknown): “We could estimate these probabilities in the same way as the phrase-translation probabilities as done in Utiyama and Isahara (2007), but we use the more principled phrase method as described in Wu and Wang (2007).”
Findings of the 2021 Conference on Machine Translation (WMT21) (2021, background): “• Pivot (Utiyama and Isahara, 2007; Wu and Wang, 2009): Collect parallel X/English and Y/English data (often much larger than X/Y data), train two translators (X-to-English + English-to-Y), and pipeline them to form an X-to-Y translator”
Improving Arabic-Chinese Statistical Machine Translation using English as Pivot Language (2009, methodology): “Most related to our work on pivoting are the following: Utiyama and Isahara (2007) studied sentence and phrase pivoting strategies using three European languages (Spanish, French and German).”
Unpaired Image Captioning by Language Pivoting (2018, background): “Recently, many works have been done in the area of pivot strategies of NMT [13, 50, 45, 4, 57, 16, 27].”
A Parallel Corpus for Evaluating Machine Translation between Arabic and European Languages (2017, methodology): “Researchers have explored ways to exploit existing resources by pivoting or bridging on a third language (Utiyama and Isahara, 2007; Habash and Hu, 2009; El Kholy et al., 2013).”