Addicter: What Is Wrong with My Translations?

Open access

Addicter: What Is Wrong with My Translations?

We introduce Addicter, a tool for Automatic Detection and DIsplay of Common Translation ERrors. The tool allows to automatically identify and label translation errors and browse the test and training corpus and word alignments; usage of additional linguistic tools is also supported. The error classification is inspired by that of Vilar et al. (2006), although some of their higher-level categories are beyond the reach of the current version of our system. In addition to the tool itself we present a comparison of the proposed method to manually classified translation errors and a thorough evaluation of the generated alignments.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • Banerjee Satanjeev and Alon Lavie. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proc. of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization pages 65-72 Ann Arbor Michigan 2005.

  • Birch Alexandra and Miles Osborne. Reordering metrics for MT. In Proc. of ACL'11 pages 1027-1035 Portland Oregon USA 2011.

  • Birch Alexandra Miles Osborne and Phil Blunsom. Metrics for MT evaluation: Evaluating reordering. Machine Translation 24(1):15-26 2010.

  • Bojar Ondřej. Analyzing Error Types in English-Czech Machine Translation. Prague Bulletin of Mathematical Linguistics 95 2011.

  • Bojar Ondřej and Zdeněk Žabokrtský. CzEng 0.9: Large parallel treebank with rich annotation. Prague Bulletin of Mathematical Linguistics 92:63-83 2009.

  • Denkowski Michael and Alon Lavie. Extending the METEOR Machine Translation Evaluation Metric to the Phrase Level. In Proc. of HLT-NAACL'10 pages 250-253 2010.

  • Giménez Jesús and Lluis Màrquez. Towards heterogeneous automatic MT error analysis. In Proc. of LREC'08 Marrakech Morocco 2008.

  • Liang Percy Ben Taskar and Dan Klein. Alignment by agreement. In Proc. of HLT-NAACL'06 pages 104-111 New York City USA 2006.

  • Och Franz Josef and Hermann Ney. A systematic comparison of various statistical alignment models. Computational Linguistics 29(1):19-51 2003.

  • Popović Maja and Hermann Ney. Word error rates: decomposition over POS classes and applications for error analysis. In Proc. of WMT'07 pages 48-55 Stroudsburg PA USA 2007.

  • Popović Maja Adrià de Gispert Deepa Gupta Patrik Lambert Hermann Ney José B. Mariño Marcello Federico and Rafael Banchs. Morpho-syntactic information for automatic error analysis of statistical machine translation output. In Proc. of WMT'06 pages 1-6 New York USA 2006.

  • Popović Maja and Aljoscha Burchardt. From human to automatic error classification for machine translation output. In Proc. of EAMT'11 pages 265-272 Leuven Belgium 2011.

  • Stymne Sara. Blast: A tool for error analysis of machine translation output. In Proc. of ACL-HLT'11 pages 56-61 Portland Oregon 2011.

  • Vilar David Jia Xu Luis Fernando D'Haro and Hermann Ney. Error analysis of machine translation output. In Proc. of LREC'06 pages 697-702 Genoa Italy 2006.

  • Vogel Stephan Hermann Ney and Christoph Tillmann. HMM-based word alignment in statistical translation. In Proc. of COLING'96 pages 836-841 Copenhagen Denmark 1996.

  • Wong Billy and Chunyu Kit. The parameter-optimized ATEC metric for MT evaluation. In Proc. of the Joint WMT'10 and MetricsMATR pages 360-364 Uppsala Sweden 2010.

Journal information
Cited By
All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 178 60 0
PDF Downloads 94 41 1