FAUST - Feedback Analysis for User adaptive Statistical Translation


Publications and Presentations

Journal of Machine Translation

  • N-gram posterior probability confidence measures for statistical machine translation: an empirical study. A. de Gispert, G. Blackwood, G. Iglesias, and W. Byrne. Machine Translation. 2012. http://dx.doi.org/10.1007/s10590-012-9132-2

Prague Bulletin of Mathematical Linguistics


  • Lattice-based minimum error rate training using weighted finite-state transducers with tropical polynomial weights. A. Waite, G. Blackwood, and W. Byrne. In Proceedings of the 10th International Workshop on Finite State Methods and Natural Language Processing (FSMNLP 2012), Donostia-San Sebastian, Spain, July 2012. http://aclweb.org/anthology-new/W/W12/W12-6219.pdf

EACL 2012

  • Syntax-Based Word Ordering Incorporating a Large-Scale Language Model. Yue Zhang, Graeme Blackwood and Stephen Clark. Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics (EACL-12), pp.736-746, Avignon, France, 2012. [PDF]


  • Dealing with Input Noise in Statistical Machine Translation. Llu√ƒ¬≠s Formiga and Jos√ƒ¬© A.R. Rodr√ƒ¬≠guez Fonollosa. (Also as TALP Technical Report [PDF])

AMTA 2012

  • A Graph-based Strategy to Streamline Translation Quality Assessments. Daniele Pighin, Llu√ƒ¬≠s Formiga, Llu√ƒ¬≠s M√ƒ rquez. [PDF]


  • Improving English to Spanish Out-of-Domain Translations by Morphology Generalization and Generation. Llu√ƒ¬≠s Formiga, Adolfo Hernandez, Jose B. Marino, and Enric Monte. [PDF (Page 6)]

ACL 2012

  • A Graphical Interface for MT Evaluation and Error Analysis. Meritxell Gonz√ƒ¬°lez and Jes√ƒ¬ļs Gim√ƒ¬©nez and Llu√ƒ¬≠s M√ƒ rquez. [PDF]

SSST-6 (2012)

  • Using Parallel Features in Parsing of Machine-Translated Sentences for Correction of Grammatical Errors. Rudolf Rosa, OndŇ™ej Dušek, David Mareńćek, and Martin Popel [PDF]

TSD 2012

  • Dependency Relations Labeller for Czech. Rudolf Rosa, David Marecćek, and Martin Popel [PDF]

WMT 2012

  • Formemes in English-Czech Deep Syntactic MT. Ondrej Dušek, Zdenek √‚¬éabokrtsky, Martin Popel, Martin Majliš, Michal Nov√ƒ¬°k, and David Marec√‚¬ćek. [PDF]
  • DEPFIX: A System for Automatic Correction of Czech MT Outputs. Rudolf Rosa, David Marec√‚¬ćek, Ondrej Dušek. [PDF]
  • The UPC Submission to the WMT 2012 Shared Task on Quality Estimation. Daniele Pighin, Meritxell Gonz√ƒ¬°lez and Llu√ƒ¬≠s M√ƒ rquez
  • The TALP-UPC phrase-based translation systems for WMT12: Morphology simplification and domain adaptation.Lluis Formiga; Carlos A. Henr√ƒ¬¨quez Q.; Adolfo Hern√ƒ¬°ndez; Jos√ƒ¬® B. Mari√ƒ¬Īo; Enric Monte; Jos√ƒ¬® A. R. Fonollosa

LREC 2012

Workshop on Iberian Cross-Language NLP Tasks

  • Pivot strategies as an alternative for statistical machine translation tasks involving Iberian languages Carlos A. Henriquez Q., Marta R. Costa-Juss√ƒ , Rafael Banchs, Lluis Formiga and Jos√ƒ¬© B. Mari√ƒ¬Īo. Workshop on Iberian Cross-Language NLP tasks. September 2011. Huelva, Spain [PDF]

EMNLP 2011

  • Hierarchical Phrase-based Translation Representations. G. Iglesias, A. Allauzen, W. Byrne, A. de Gispert and M. Riley. Edinburgh, Scotland, July 2011 [PDF]
  • Syntax-Based Grammaticality Improvement using CCG and Guided Search.Yue Zhang and Stephen Clark. [PDF]
  • Corroborating Text Evaluation Results with Heterogeneous Measures. Enrique Amig√ƒƒ√‚¬≥, Julio Gonzalo, Jes√ƒƒ√‚¬ļs Gim√ƒƒ√‚¬©nez and Felisa Verdejo [PDF][bib]

EAMT 2011

  • Hierarchical Phrase-based Translation with Weighted Finite-State Transducers. Presented by EAMT 2010 Best Phd awardee Gonzalo Iglesias at the conference.
  • Deriving translations units using small additional corpora. Carlos A. Henriquez Q., Jos√ƒƒ√‚¬© B. Mari√ƒƒ√‚¬Īo and Rafael E. Banchs. Proceedings of the 15th Annual Conference of the European Association for Machine Tranlation, 121--128, May, 2011. Leuven, Belgium.

WMT 2011

  • Two-step translation with grammatical post-processing . David Mare√ƒƒ„√ƒ‚√‚¬ćekek, Rudolf Rosa, Ond√ƒƒ…™ej Bojar and Petra Galuš√ƒƒ„√ƒ‚√‚¬ć√ƒƒ√‚¬°kov√ƒƒ√‚¬°. Will be presented at WMT11. [PDF]
  • Influence of Parser Choice on Dependency-Based MT. Martin Popel, David Mare√ƒƒ„√ƒ‚√‚¬ćek, Nathan Green and Zden√ƒƒ„›k √ƒƒ…√ƒ‚√‚¬Ĺabokrtsk√ƒƒ√‚¬Ĺ. Will be presented at WMT11. [PDF]

ACL 2011

  • Shift-reduce CCG Parsing [PDF]
    Yue Zhang and Stephen Clark
  • Transition-based Dependency Parsing with Rich Non-local Features [PDF]
    Yue Zhang and Joakim Nivre
  • Automatic Projection of Semantic Structures: an Application to Pairwise Translation Ranking. Daniele Pighin and Llu√ƒƒ√‚¬≠s M√ƒƒ rquez. Proceedings of SSST-5, pages 1-9. [PDF],
Journal of Machine Translation
  • Linguistic Measures for Automatic Machine Translation Evaluation. Jes√ƒƒ√‚¬ļs Gim√ƒƒ√‚¬©nez and Llu√ƒƒ√‚¬≠s M√ƒƒ rquez. Machine Translation, 2010,Volume 24, Numbers 3-4, pages 209-240.[PDF]
The Prague Bulletin of Mathematical Linguistics


  • Combining Diverse Word-Alignment Symmetrizations Improves Dependency Tree Projection.David Marecek. [PDF]


  • Multiclass Classification for Morphology Generation in Statistical Machine Translation. Adolfo Hern√ƒƒ√‚¬°ndez Huerta, Enric Monte Moreno, Jos√ƒƒ√‚¬© B. Mari√ƒƒ√‚¬Īo Acebal. FALA 2010 "VI Jornadas en Tecnolog√ƒƒ√‚¬≠a del Habla" and II Iberian SLTech Workshop, pages 179-182, Vigo, Spain, 10-12 November, 2010.


  • UPC-BMIC-VDU system description for the IWSLT 2010: testing several collocation segmentations in a phrase-based SMT system. Carlos A. Henr√ƒƒ√‚¬≠quez Q., Marta R. Costa-juss√ƒƒ , Vidas Daudaravicius, Rafael E. Banchs and Jos√ƒƒ√‚¬© B. Mari√ƒƒ√‚¬Īo. Proceedings of the International Workshop on Spoken Language Translation, 189--195, December, 2010

Softissimo Initial Analysis of Translation Feedback

Baseline System Descriptions for WMT 2010

  • [UCAM] The CUED HiFST System for the WMT10 Translation Shared Task [PDF] [bib]
    Juan Pino, Gonzalo Iglesias, Adri√ƒƒ de Gispert, Graeme Blackwood, Jamie Brunning and William Byrne
  • [UPC] Using Collocation Segmentation to Augment the Phrase Table [PDF] [bib]
    Carlos A. Henr√ƒƒ√‚¬≠quez Q., Marta Ruiz Costa-juss√ƒƒ , Vidas Daudaravicius, Rafael E. Banchs and Jos√ƒƒ√‚¬© B. Mari√ƒƒ√‚¬Īo
  • [CUNI] Maximum Entropy Translation Model in Dependency-Based MT Framework [PDF] [bib]
    Zdenek Zabokrtsky, Martin Popel and David Marecek
  • [CUNI] 2010 Failures in English-Czech Phrase-based MT [PDF] [bib]
    Ondrej Bojar and Kamil Kos

Baseline System Descriptions for Metrics MaTr Challenge at WMT 2010

  • [UPC] Document-Level Automatic MT Evaluation based on Discourse Representations. [PDF] [bib]
    Elisabet Comelles, Jesus Gimenez, Lluis Marquez, Irene Castellon and Victoria Arranz.


  • [UCAM] Chart Pruning for Fast Lexicalised-Grammar Parsing. [PDF]
    Yue Zhang, Byung-Gyu Ahn, Stephen Clark, Curt Van Wyk, James R. Curran and Laura Rimell

ACL 2010

  • Data Sparseness in Machine Translation Evaluation
    Ondrej Bojar, Kamil Kos, and David Marecek

EAMT 2010

  • FAUST: Feedback Analysis for User adaptive Statistical Translation – First Year Progress.
    project overview poster
  • Robust Estimation of Feature Weights in Statistical Machine Translation.
    Cristina Espa√ƒƒ√‚¬Īa-Bonet and Llu√ƒƒ√‚¬≠s M√ƒƒ rquez

EMNLP 2010

  • A fast decoder for joint segmentation and POS tagging. [PDF]
    Yue Zhang and Stephen Clark

Language Technology Days : 22-23 March 2010, Luxembourg