Publications

SFB 1102Publications
13 entries
Dutta Chowdhury, Koel; Jalota, Rricha; van Genabith, Josef; España-Bonet, Cristina

Towards Debiasing Translation Artifacts Inproceedings

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, pp. 3983-3991, Seattle, United States, July 2022, 2022.

Cross-lingual natural language processing relies on translation, either by humans or machines, at different levels, from translating training data to translating test sets. However, compared to original texts in the same language, translations possess distinct qualities referred to as translationese. Previous research has shown that these translation artifacts influence the performance of a variety of cross-lingual tasks. In this work, we propose a novel approach to reducing translationese by extending an established bias-removal technique. We use the Iterative Null-space Projection (INLP) algorithm, and show by measuring classification accuracy before and after debiasing, that translationese is reduced at both sentence and word level. We evaluate the utility of debiasing translationese on a natural language inference (NLI) task, and show that by reducing this bias, NLI accuracy improves. To the best of our knowledge, this is the first study to debias translationese as represented in latent embedding space.

@inproceedings{Chowdhury_2022_Debiasing,
title = {Towards Debiasing Translation Artifacts},
author = {Koel Dutta Chowdhury and Rricha Jalota and Josef van Genabith and Cristina Espa{\~n}a-Bonet},
url = {https://aclanthology.org/2022.naacl-main.292/},
doi = {https://doi.org/10.18653/v1/2022.naacl-main.292},
year = {2022},
date = {2022},
booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
pages = {3983-3991},
publisher = {Association for Computational Linguistics},
address = {Seattle, United States, July 2022},
abstract = {Cross-lingual natural language processing relies on translation, either by humans or machines, at different levels, from translating training data to translating test sets. However, compared to original texts in the same language, translations possess distinct qualities referred to as translationese. Previous research has shown that these translation artifacts influence the performance of a variety of cross-lingual tasks. In this work, we propose a novel approach to reducing translationese by extending an established bias-removal technique. We use the Iterative Null-space Projection (INLP) algorithm, and show by measuring classification accuracy before and after debiasing, that translationese is reduced at both sentence and word level. We evaluate the utility of debiasing translationese on a natural language inference (NLI) task, and show that by reducing this bias, NLI accuracy improves. To the best of our knowledge, this is the first study to debias translationese as represented in latent embedding space.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B6

España-Bonet, Cristina; Barrón-Cedeño, Alberto

The (Undesired) Attenuation of Human Biases by Multilinguality Inproceedings

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, pp. 2056–2077, Online and Abu Dhabi, UAE, Dec 2022, 2022.
Some human preferences are universal. The odor of vanilla is perceived as pleasant all around the world. We expect neural models trained on human texts to exhibit these kind of preferences, i.e. biases, but we show that this is not always the case. We explore 16 static and contextual embedding models in 9 languages and, when possible, compare them under similar training conditions. We introduce and release CA-WEAT, multilingual cultural aware tests to quantify biases, and compare them to previous English-centric tests. Our experiments confirm that monolingual static embeddings do exhibit human biases, but values differ across languages, being far from universal. Biases are less evident in contextual models, to the point that the original human association might be reversed. Multilinguality proves to be another variable that attenuates and even reverses the effect of the bias, specially in contextual multilingual models. In order to explain this variance among models and languages, we examine the effect of asymmetries in the training corpus, departures from isomorphism in multilingual embedding spaces and discrepancies in the testing measures between languages.

@inproceedings{espana-bonet-barron-cedeno-2022-undesired,
title = {The (Undesired) Attenuation of Human Biases by Multilinguality},
author = {Cristina Espa{\~n}a-Bonet and Alberto Barrón-Cede{\~n}o},
url = {https://aclanthology.org/2022.emnlp-main.133},
year = {2022},
date = {2022},
booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
pages = {2056–2077},
publisher = {Association for Computational Linguistics},
address = {Online and Abu Dhabi, UAE, Dec 2022},
abstract = {

Some human preferences are universal. The odor of vanilla is perceived as pleasant all around the world. We expect neural models trained on human texts to exhibit these kind of preferences, i.e. biases, but we show that this is not always the case. We explore 16 static and contextual embedding models in 9 languages and, when possible, compare them under similar training conditions. We introduce and release CA-WEAT, multilingual cultural aware tests to quantify biases, and compare them to previous English-centric tests. Our experiments confirm that monolingual static embeddings do exhibit human biases, but values differ across languages, being far from universal. Biases are less evident in contextual models, to the point that the original human association might be reversed. Multilinguality proves to be another variable that attenuates and even reverses the effect of the bias, specially in contextual multilingual models. In order to explain this variance among models and languages, we examine the effect of asymmetries in the training corpus, departures from isomorphism in multilingual embedding spaces and discrepancies in the testing measures between languages.
},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B6

Bafna, Niyati; van Genabith, Josef; España-Bonet, Cristina; Zabokrtský, Zdenêk

Combining Noisy Semantic Signals with Orthographic Cues: Cognate Induction for the Indic Dialect Continuum Inproceedings

Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL), Association for Computational Linguistics, pp. 110-131, Abu Dhabi, UAE, Dec 2022, 2022.
We present a novel method for unsupervised cognate/borrowing identification from monolingual corpora designed for low and extremely low resource scenarios, based on combining noisy semantic signals from joint bilingual spaces with orthographic cues modelling sound change. We apply our method to the North Indian dialect continuum, containing several dozens of dialects and languages spoken by more than 100 million people. Many of these languages are zero-resource and therefore natural language processing for them is non-existent. We first collect monolingual data for 26 Indic languages, 16 of which were previously zero-resource, and perform exploratory character, lexical and subword cross-lingual alignment experiments for the first time at this scale on this dialect continuum. We create bilingual evaluation lexicons against Hindi for 20 of the languages. We then apply our cognate identification method on the data, and show that our method outperforms both traditional orthography baselines as well as EM-style learnt edit distance matrices. To the best of our knowledge, this is the first work to combine traditional orthographic cues with noisy bilingual embeddings to tackle unsupervised cognate detection in a (truly) low-resource setup, showing that even noisy bilingual embeddings can act as good guides for this task. We release our multilingual dialect corpus, called HinDialect, as well as our scripts for evaluation data collection and cognate induction.

@inproceedings{bafna-etal-2022-combining,
title = {Combining Noisy Semantic Signals with Orthographic Cues: Cognate Induction for the Indic Dialect Continuum},
author = {Niyati Bafna and Josef van Genabith and Cristina Espa{\~n}a-Bonet and Zdenêk Zabokrtský},
url = {https://aclanthology.org/2022.conll-1.9},
year = {2022},
date = {2022},
booktitle = {Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL)},
pages = {110-131},
publisher = {Association for Computational Linguistics},
address = {Abu Dhabi, UAE, Dec 2022},
abstract = {

We present a novel method for unsupervised cognate/borrowing identification from monolingual corpora designed for low and extremely low resource scenarios, based on combining noisy semantic signals from joint bilingual spaces with orthographic cues modelling sound change. We apply our method to the North Indian dialect continuum, containing several dozens of dialects and languages spoken by more than 100 million people. Many of these languages are zero-resource and therefore natural language processing for them is non-existent. We first collect monolingual data for 26 Indic languages, 16 of which were previously zero-resource, and perform exploratory character, lexical and subword cross-lingual alignment experiments for the first time at this scale on this dialect continuum. We create bilingual evaluation lexicons against Hindi for 20 of the languages. We then apply our cognate identification method on the data, and show that our method outperforms both traditional orthography baselines as well as EM-style learnt edit distance matrices. To the best of our knowledge, this is the first work to combine traditional orthographic cues with noisy bilingual embeddings to tackle unsupervised cognate detection in a (truly) low-resource setup, showing that even noisy bilingual embeddings can act as good guides for this task. We release our multilingual dialect corpus, called HinDialect, as well as our scripts for evaluation data collection and cognate induction.
},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B6

Amponsah-Kaakyire, Kwabena; Pylypenko, Daria; van Genabith, Josef; España-Bonet, Cristina

Explaining Translationese: why are Neural Classifiers Better and what do they Learn? Inproceedings Forthcoming

Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, Association for Computational Linguistics, pp. 281-296, Abu Dhabi, United Arab Emirates (Hybrid), Dec 2022, 2022.

Recent work has shown that neural feature- and representation-learning, e.g. BERT, achieves superior performance over traditional manual feature engineering based approaches, with e.g. SVMs, in translationese classification tasks. Previous research did not show (i) whether the difference is because of the features, the classifiers or both, and (ii) what the neural classifiers actually learn. To address (i), we carefully design experiments that swap features between BERT- and SVM-based classifiers. We show that an SVM fed with BERT representations performs at the level of the best BERT classifiers, while BERT learning and using handcrafted features performs at the level of an SVM using handcrafted features. This shows that the performance differences are due to the features. To address (ii) we use integrated gradients and find that (a) there is indication that information captured by hand-crafted features is only a subset of what BERT learns, and (b) part of BERT’s top performance results are due to BERT learning topic differences and spurious correlations with translationese.

@inproceedings{amponsah-kaakyire-etal-2022-explaining,
title = {Explaining Translationese: why are Neural Classifiers Better and what do they Learn?},
author = {Kwabena Amponsah-Kaakyire and Daria Pylypenko and Josef van Genabith and Cristina Espa{\~n}a-Bonet},
url = {https://aclanthology.org/2022.blackboxnlp-1.23},
doi = {https://doi.org/10.48550/ARXIV.2210.13391},
year = {2022},
date = {2022-01-19},
booktitle = {Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP},
pages = {281-296},
publisher = {Association for Computational Linguistics},
address = {Abu Dhabi, United Arab Emirates (Hybrid), Dec 2022},
abstract = {Recent work has shown that neural feature- and representation-learning, e.g. BERT, achieves superior performance over traditional manual feature engineering based approaches, with e.g. SVMs, in translationese classification tasks. Previous research did not show (i) whether the difference is because of the features, the classifiers or both, and (ii) what the neural classifiers actually learn. To address (i), we carefully design experiments that swap features between BERT- and SVM-based classifiers. We show that an SVM fed with BERT representations performs at the level of the best BERT classifiers, while BERT learning and using handcrafted features performs at the level of an SVM using handcrafted features. This shows that the performance differences are due to the features. To address (ii) we use integrated gradients and find that (a) there is indication that information captured by hand-crafted features is only a subset of what BERT learns, and (b) part of BERT's top performance results are due to BERT learning topic differences and spurious correlations with translationese.},
pubstate = {forthcoming},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B6

Amponsah-Kaakyire, Kwabena; Pylypenko, Daria; España-Bonet, Cristina; van Genabith, Josef

Do not Rely on Relay Translations: Multilingual Parallel Direct Europarl Inproceedings

Proceedings of the Workshop on Modelling Translation: Translatology in the Digital Age (MoTra21), International Committee on Computational Linguistics, pp. 1-7, Iceland (Online), 2021.

Translationese data is a scarce and valuable resource. Traditionally, the proceedings of the European Parliament have been used for studying translationese phenomena since their metadata allows to distinguish between original and translated texts. However, translations are not always direct and we hypothesise that a pivot (also called ”relay”) language might alter the conclusions on translationese effects. In this work, we (i) isolate translations that have been done without an intermediate language in the Europarl proceedings from those that might have used a pivot language, and (ii) build comparable and parallel corpora with data aligned across multiple languages that therefore can be used for both machine translation and translation studies.

@inproceedings{AmposahEtal:MOTRA:2021,
title = {Do not Rely on Relay Translations: Multilingual Parallel Direct Europarl},
author = {Kwabena Amponsah-Kaakyire and Daria Pylypenko and Cristina Espa{\~n}a-Bonet and Josef van Genabith},
url = {https://aclanthology.org/2021.motra-1.1/},
year = {2021},
date = {2021},
booktitle = {Proceedings of the Workshop on Modelling Translation: Translatology in the Digital Age (MoTra21)},
pages = {1-7},
publisher = {International Committee on Computational Linguistics},
address = {Iceland (Online)},
abstract = {Translationese data is a scarce and valuable resource. Traditionally, the proceedings of the European Parliament have been used for studying translationese phenomena since their metadata allows to distinguish between original and translated texts. However, translations are not always direct and we hypothesise that a pivot (also called ”relay”) language might alter the conclusions on translationese effects. In this work, we (i) isolate translations that have been done without an intermediate language in the Europarl proceedings from those that might have used a pivot language, and (ii) build comparable and parallel corpora with data aligned across multiple languages that therefore can be used for both machine translation and translation studies.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B6

Pylypenko, Daria; Amponsah-Kaakyire, Kwabena; Dutta Chowdhury, Koel; van Genabith, Josef; España-Bonet, Cristina

Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification Inproceedings Forthcoming

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online and in the Dominican Republic, 2021.

@inproceedings{Pylypenko2021comparing,
title = {Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification},
author = {Daria Pylypenko and Kwabena Amponsah-Kaakyire and Koel Dutta Chowdhury and Josef van Genabith and Cristina Espa{\~n}a-Bonet},
year = {2021},
date = {2021},
booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
address = {Online and in the Dominican Republic},
pubstate = {forthcoming},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B6

Dutta Chowdhury, Koel; España-Bonet, Cristina; van Genabith, Josef

Tracing Source Language Interference in Translation with Graph-Isomorphism Measures Inproceedings

Proceedings of Recent Advances in Natural Language Processing (RANLP 2021), pp. 380-390, Online, 2021, ISSN 2603-2813.

Previous research has used linguistic features to show that translations exhibit traces of source language interference and that phylogenetic trees between languages can be reconstructed from the results of translations into the same language. Recent research has shown that instances of translationese (source language interference) can even be detected in embedding spaces, comparing embeddings spaces of original language data with embedding spaces resulting from translations into the same language, using a simple Eigenvectorbased divergence from isomorphism measure. To date, it remains an open question whether alternative graph-isomorphism measures can produce better results. In this paper, we (i) explore Gromov-Hausdorff distance, (ii) present a novel spectral version of the Eigenvectorbased method, and (iii) evaluate all approaches against a broad linguistic typological database (URIEL). We show that language distances resulting from our spectral isomorphism approaches can reproduce genetic trees on a par with previous work without requiring any explicit linguistic information and that the results can be extended to non-Indo-European languages. Finally, we show that the methods are robust under a variety of modeling conditions.

@inproceedings{Chowdhury2021tracing,
title = {Tracing Source Language Interference in Translation with Graph-Isomorphism Measures},
author = {Koel Dutta Chowdhury and Cristina Espa{\~n}a-Bonet and Josef van Genabith},
url = {https://aclanthology.org/2021.ranlp-1.43/},
year = {2021},
date = {2021},
booktitle = {Proceedings of Recent Advances in Natural Language Processing (RANLP 2021)},
issn = {2603-2813},
pages = {380-390},
address = {Online},
abstract = {Previous research has used linguistic features to show that translations exhibit traces of source language interference and that phylogenetic trees between languages can be reconstructed from the results of translations into the same language. Recent research has shown that instances of translationese (source language interference) can even be detected in embedding spaces, comparing embeddings spaces of original language data with embedding spaces resulting from translations into the same language, using a simple Eigenvectorbased divergence from isomorphism measure. To date, it remains an open question whether alternative graph-isomorphism measures can produce better results. In this paper, we (i) explore Gromov-Hausdorff distance, (ii) present a novel spectral version of the Eigenvectorbased method, and (iii) evaluate all approaches against a broad linguistic typological database (URIEL). We show that language distances resulting from our spectral isomorphism approaches can reproduce genetic trees on a par with previous work without requiring any explicit linguistic information and that the results can be extended to non-Indo-European languages. Finally, we show that the methods are robust under a variety of modeling conditions.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B6

Bizzoni, Yuri; Juzek, Tom; España-Bonet, Cristina; Dutta Chowdhury, Koel; van Genabith, Josef; Teich, Elke

How Human is Machine Translationese? Comparing Human and Machine Translations of Text and Speech Inproceedings

The 17th International Workshop on Spoken Language Translation, Seattle, WA, United States, 2020.

Translationese is a phenomenon present in human translations, simultaneous interpreting, and even machine translations. Some translationese features tend to appear in simultaneous interpreting with higher frequency than in human text translation, but the reasons for this are unclear. This study analyzes translationese patterns in translation, interpreting, and machine translation outputs in order to explore possible reasons.

In our analysis we (i) detail two non-invasive ways of detecting translationese and (ii) compare translationese across human and machine translations from text and speech. We find that machine translation shows traces of translationese, but does not reproduce the patterns found in human translation, offering support to the hypothesis that such patterns are due to the model (human vs. machine) rather than to the data (written vs. spoken).

@inproceedings{Bizzoni2020,
title = {How Human is Machine Translationese? Comparing Human and Machine Translations of Text and Speech},
author = {Yuri Bizzoni and Tom Juzek and Cristina Espa{\~n}a-Bonet and Koel Dutta Chowdhury and Josef van Genabith and Elke Teich},
year = {2020},
date = {2020},
booktitle = {The 17th International Workshop on Spoken Language Translation},
address = {Seattle, WA, United States},
abstract = {Translationese is a phenomenon present in human translations, simultaneous interpreting, and even machine translations. Some translationese features tend to appear in simultaneous interpreting with higher frequency than in human text translation, but the reasons for this are unclear. This study analyzes translationese patterns in translation, interpreting, and machine translation outputs in order to explore possible reasons. In our analysis we (i) detail two non-invasive ways of detecting translationese and (ii) compare translationese across human and machine translations from text and speech. We find that machine translation shows traces of translationese, but does not reproduce the patterns found in human translation, offering support to the hypothesis that such patterns are due to the model (human vs. machine) rather than to the data (written vs. spoken).},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Projects:   B6 B7

Dutta Chowdhury, Koel; España-Bonet, Cristina; van Genabith, Josef

Understanding Translationese in Multi-view Embedding Spaces Inproceedings

Proceedings of the 28th International Conference on Computational Linguistics, International Committee on Computational Linguistics, pp. 6056-6062, Barcelona, Catalonia (Online), 2020.

Recent studies use a combination of lexical and syntactic features to show that footprints of the source language remain visible in translations, to the extent that it is possible to predict the original source language from the translation. In this paper, we focus on embedding-based semantic spaces, exploiting departures from isomorphism between spaces built from original target language and translations into this target language to predict relations between languages in an unsupervised way. We use different views of the data {—} words, parts of speech, semantic tags and synsets {—} to track translationese. Our analysis shows that (i) semantic distances between original target language and translations into this target language can be detected using the notion of isomorphism, (ii) language family ties with characteristics similar to linguistically motivated phylogenetic trees can be inferred from the distances and (iii) with delexicalised embeddings exhibiting source-language interference most significantly, other levels of abstraction display the same tendency, indicating the lexicalised results to be not “just“ due to possible topic differences between original and translated texts. To the best of our knowledge, this is the first time departures from isomorphism between embedding spaces are used to track translationese.

@inproceedings{DuttaEtal:COLING:2020,
title = {Understanding Translationese in Multi-view Embedding Spaces},
author = {Koel Dutta Chowdhury and Cristina Espa{\~n}a-Bonet and Josef van Genabith},
url = {https://www.aclweb.org/anthology/2020.coling-main.532/},
doi = {https://doi.org/10.18653/v1/2020.coling-main.532},
year = {2020},
date = {2020},
booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},
pages = {6056-6062},
publisher = {International Committee on Computational Linguistics},
address = {Barcelona, Catalonia (Online)},
abstract = {Recent studies use a combination of lexical and syntactic features to show that footprints of the source language remain visible in translations, to the extent that it is possible to predict the original source language from the translation. In this paper, we focus on embedding-based semantic spaces, exploiting departures from isomorphism between spaces built from original target language and translations into this target language to predict relations between languages in an unsupervised way. We use different views of the data {---} words, parts of speech, semantic tags and synsets {---} to track translationese. Our analysis shows that (i) semantic distances between original target language and translations into this target language can be detected using the notion of isomorphism, (ii) language family ties with characteristics similar to linguistically motivated phylogenetic trees can be inferred from the distances and (iii) with delexicalised embeddings exhibiting source-language interference most significantly, other levels of abstraction display the same tendency, indicating the lexicalised results to be not “just“ due to possible topic differences between original and translated texts. To the best of our knowledge, this is the first time departures from isomorphism between embedding spaces are used to track translationese.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B6

van Genabith, Josef; España-Bonet, Cristina; Lapshinova-Koltunski, Ekaterina

Analysing Coreference in Transformer Outputs Inproceedings

Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019), Association for Computational Linguistics, pp. 1-12, Hong Kong, China, 2019.

We analyse coreference phenomena in three neural machine translation systems trained with different data settings with or without access to explicit intra- and cross-sentential anaphoric information. We compare system performance on two different genres: news and TED talks. To do this, we manually annotate (the possibly incorrect) coreference chains in the MT outputs and evaluate the coreference chain translations. We define an error typology that aims to go further than pronoun translation adequacy and includes types such as incorrect word selection or missing words. The features of coreference chains in automatic translations are also compared to those of the source texts and human translations. The analysis shows stronger potential translationese effects in machine translated outputs than in human translations.

@inproceedings{lapshinovaEtal:2019iscoMT,
title = {Analysing Coreference in Transformer Outputs},
author = {Josef van Genabith and Cristina Espa{\~n}a-Bonet andEkaterina Lapshinova-Koltunski},
url = {https://www.aclweb.org/anthology/D19-6501},
doi = {https://doi.org/10.18653/v1/D19-6501},
year = {2019},
date = {2019},
booktitle = {Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019)},
pages = {1-12},
publisher = {Association for Computational Linguistics},
address = {Hong Kong, China},
abstract = {We analyse coreference phenomena in three neural machine translation systems trained with different data settings with or without access to explicit intra- and cross-sentential anaphoric information. We compare system performance on two different genres: news and TED talks. To do this, we manually annotate (the possibly incorrect) coreference chains in the MT outputs and evaluate the coreference chain translations. We define an error typology that aims to go further than pronoun translation adequacy and includes types such as incorrect word selection or missing words. The features of coreference chains in automatic translations are also compared to those of the source texts and human translations. The analysis shows stronger potential translationese effects in machine translated outputs than in human translations.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B6

Rubino, Raphael; Degaetano-Ortlieb, Stefania; Teich, Elke; van Genabith, Josef

Modeling Diachronic Change in Scientific Writing with Information Density Inproceedings

Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, The COLING 2016 Organizing Committee, pp. 750-761, 2016.

@inproceedings{C16-1072,
title = {Modeling Diachronic Change in Scientific Writing with Information Density},
author = {Raphael Rubino and Stefania Degaetano-Ortlieb and Elke Teich and Josef van Genabith},
url = {http://aclweb.org/anthology/C16-1072},
year = {2016},
date = {2016},
booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
pages = {750-761},
publisher = {The COLING 2016 Organizing Committee},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B6

Rubino, Raphael; Lapshinova-Koltunski, Ekaterina; van Genabith, Josef

Information Density and Quality Estimation Features as Translationese Indicators for Human Translation Classification Inproceedings

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, pp. 960-970, 2016.

@inproceedings{N16-1110,
title = {Information Density and Quality Estimation Features as Translationese Indicators for Human Translation Classification},
author = {Raphael Rubino and Ekaterina Lapshinova-Koltunski and Josef van Genabith},
url = {http://aclweb.org/anthology/N16-1110},
doi = {https://doi.org/10.18653/v1/N16-1110},
year = {2016},
date = {2016},
booktitle = {Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
pages = {960-970},
publisher = {Association for Computational Linguistics},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B6

Findings of the 2016 Conference on Machine Translation Inproceedings

Proceedings of the First Conference on Machine Translation, Association for Computational Linguistics, pp. 131-198, Berlin, Germany, 2016.

@inproceedings{bojar-EtAl:2016:WMT1,
title = {Findings of the 2016 Conference on Machine Translation},
author = {Ondvrej Bojar and Rajen Chatterjee and Christian Federmann and Yvette Graham and Barry Haddow and Matthias Huck and Antonio Jimeno Yepes and Philipp Koehn and Varvara Logacheva and Christof Monz and Matteo Negri and Aurelie Neveol and Mariana Neves and Martin Popel and Matt Post and Raphael Rubino and Carolina Scarton and Lucia Specia and Marco Turchi and Karin Verspoor and Marcos Zampieri},
url = {http://www.aclweb.org/anthology/W/W16/W16-2301},
year = {2016},
date = {2016-08-01},
booktitle = {Proceedings of the First Conference on Machine Translation},
pages = {131-198},
publisher = {Association for Computational Linguistics},
address = {Berlin, Germany},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B6

Successfully