Detecting Non-literal Translations by Fine-tuning Cross-lingual Pre-trained Language Models

Human-generated non-literal translations reflect the richness of human languages and are sometimes indispensable to ensure adequacy and fluency. Non-literal translations are difficult to produce even for human translators, especially for foreign language learners, and machine translations are still on the way to simulate human ones on this aspect. In order to foster the study on appropriate and creative non-literal translations, automatically detecting them in parallel corpora is an important step, which can benefit downstream NLP tasks or help to construct materials to teach translation. This article demonstrates that generic sentence representations produced by a pre-trained cross-lingual language model could be fine-tuned to solve this task. We show that there exists a moderate positive correlation between the prediction probability of being human translation and the non-literal translations’ proportion in a sentence. The fine-tuning experiments show an accuracy of 80.16% when predicting the presence of non-literal translations in a sentence and an accuracy of 85.20% when distinguishing literal and non-literal translations at phrase level. We further conduct a linguistic error analysis and propose directions for future work.

[1]  Min Zhang,et al.  Towards Better Word Alignment in Transformer , 2020, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[2]  Alexandre Allauzen,et al.  Towards Recognizing Phrase Translation Processes: Experiments on English-French , 2019, POLIBITS.

[3]  Matt Post,et al.  A Call for Clarity in Reporting BLEU Scores , 2018, WMT.

[4]  Lijun Wu,et al.  Achieving Human Parity on Automatic Chinese to English News Translation , 2018, ArXiv.

[5]  François Yvon,et al.  Fixing Translation Divergences in Parallel Corpora for Neural MT , 2018, EMNLP.

[6]  Nizar Habash,et al.  DUSTer: a method for unraveling cross-language divergences for statistical word-level alignment , 2002, AMTA.

[7]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

[8]  Oi Yee Kwong,et al.  Detecting Free Translation in Parallel Corpora from Attention Scores , 2018, PACLIC.

[9]  Daniel Marcu,et al.  Statistical Phrase-Based Translation , 2003, NAACL.

[10]  Guillaume Lample,et al.  XNLI: Evaluating Cross-lingual Sentence Representations , 2018, EMNLP.

[11]  Holger Schwenk,et al.  Supervised Learning of Universal Sentence Representations from Natural Language Inference Data , 2017, EMNLP.

[12]  Jörg Tiedemann,et al.  Parallel Data, Tools and Interfaces in OPUS , 2012, LREC.

[13]  Michel Paillard,et al.  Approche linguistique des problèmes de traduction anglais -- français , 1989 .

[14]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[15]  J. Vinay,et al.  Stylistique Comparée du Français et de l'Anglais: Méthode de Traduction , 1958 .

[16]  Yiming Yang,et al.  XLNet: Generalized Autoregressive Pretraining for Language Understanding , 2019, NeurIPS.

[17]  Chris Callison-Burch,et al.  Paraphrasing with Bilingual Parallel Corpora , 2005, ACL.

[18]  Marine Carpuat,et al.  Detecting Cross-Lingual Semantic Divergence for Neural Machine Translation , 2017, NMT@ACL.

[19]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[20]  Maja Popovic,et al.  chrF: character n-gram F-score for automatic MT evaluation , 2015, WMT@EMNLP.

[21]  Myle Ott,et al.  fairseq: A Fast, Extensible Toolkit for Sequence Modeling , 2019, NAACL.

[22]  Zheng Zhang,et al.  A Sustainable and Open Access Knowledge Organization Model to Preserve Cultural Heritage and Language Diversity , 2019, Inf..

[23]  Myle Ott,et al.  Scaling Neural Machine Translation , 2018, WMT.

[24]  Michael Carl,et al.  Why Translation Is Difficult: A Corpus-Based Study of Non-Literality in Post-Editing and From-Scratch Translation , 2017 .

[25]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[26]  Rico Sennrich,et al.  Neural Machine Translation of Rare Words with Subword Units , 2015, ACL.

[27]  Christian Hardmeier,et al.  Discovery of Discourse-Related Language Contrasts through Alignment Discrepancies in English-German Translation , 2017, DiscoMT@EMNLP.

[28]  Yann Dauphin,et al.  Convolutional Sequence to Sequence Learning , 2017, ICML.

[29]  Nianwen Xue,et al.  Translation Divergences in Chinese–English Machine Translation: An Empirical Investigation , 2017, CL.

[30]  Chris Quirk,et al.  MT Detection in Web-Scraped Parallel Corpora , 2011, MTSUMMIT.

[31]  lucía molina,et al.  Translation techniques revisited. A dynamic and functionalist approach , 2004 .

[32]  Philipp Koehn,et al.  Europarl: A Parallel Corpus for Statistical Machine Translation , 2005, MTSUMMIT.

[33]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[34]  Yuming Zhai.  Reconnaissance des procédés de traduction sous-phrastiques: des ressources aux validations. (Recognition of sub-sentential translation techniques: from resources to validation) , 2019 .

[35]  Jan Hauke,et al.  Comparison of Values of Pearson's and Spearman's Correlation Coefficients on the Same Sets of Data , 2011 .

[36]  Marine Carpuat,et al.  Identifying Semantic Divergences in Parallel Text without Annotations , 2018, NAACL.

[37]  Malvina Nissim,et al.  Adding Semantics to Data-Driven Paraphrasing , 2015, ACL.

[38]  Azzeddine Mazroui,et al.  Enhancing Machine Translation by Integrating Linguistic Knowledge in the Word Alignment Module , 2020, 2020 International Conference on Intelligent Systems and Computer Vision (ISCV).

[39]  Hermann Ney,et al.  A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.

[40]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[41]  Lars Ahrenberg,et al.  Comparing Machine Translation and Human Translation: A Case Study , 2017 .

[42]  Serge Sharoff,et al.  Sentence Level Human Translation Quality Estimation with Attention-based Neural Networks , 2020, LREC.

[43]  Sara Stymne,et al.  Discourse-Related Language Contrasts in English-Croatian Human and Machine Translation , 2018, WMT.

[44]  Yuki Arase,et al.  Transfer Fine-Tuning: A BERT Case Study , 2019, EMNLP/IJCNLP.

[45]  Andy Way,et al.  What Level of Quality can Neural Machine Translation Attain on Literary Text? , 2018, ArXiv.

[46]  Guillaume Lample,et al.  Cross-lingual Language Model Pretraining , 2019, NeurIPS.

[47]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.