The DOI matches its Crossref record.
Can we translate letters?
Open accessAbstract
Current statistical machine translation systems handle the translation process as the transformation of a string of symbols into another string of symbols. Normally the symbols dealt with are the words in different languages, sometimes with some additional information included, like morphological data. In this work we try to push the approach to the limit, working not on the level of words, but treating both the source and target sentences as a string of letters. We try to find out if a nearly unmodified state-of-the-art translation system is able to cope with the problem and whether it is capable to further generalize translation rules, for example at the level of word suffixes and translation of unseen words. Experiments are carried out for the translation of Catalan to Spanish.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Character-based translation with phrase-based models proved especially successful for closely related languages.
“Character-based translation has also been investigated with phrase-based models, which proved especially successful for closely related languages (Vilar et al., 2007;Tiedemann, 2009;Neubig et al., 2012).”
From Neural Machine Translation of Rare Words with Subword Units (2016) · cites this paper as Vilar et al., 2007
Section 2.1 describes a letter-based phrase-based model, and the Introduction says the approach requires related languages. But the Conclusions characterize its performance as “quite acceptable,” not especially successful, and say the word-based approach performs better. The reported gains come from combining the two approaches, particularly when training data is scarce. Page numbers are not available in the supplied copy. (LLM, conf=0.85)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
No references could be resolved yet.
Research works printed but not linked: 11
- Yaser Al-Onaizan and Kevin Knight. 2002. Machine transliteration of names in arabic text. In Proceed- ings of the ACL-02 workshop on Computational ap- proaches to semitic languages, pages 1-13, Morris- town, NJ, USA. Association for Computational Lin- guistics.
- Max Bisani and Hermann Ney. 2002. Investigations on joint-multigram models for grapheme-to-phoneme conversion. In Proceedings of the 7th International Conference on Spoken Language Processing, vol- ume 1, pages 105-108, Denver, CO, September.
- Peter F. Brown, Stephen A. Della Pietra, Vincent J. Della Pietra, and Robert L. Mercer. 1993. The mathemat- ics of statistical machine translation: Parameter esti- mation. Computational Linguistics, 19(2):263-311, June.
- D. Conejero, J. Gimnez, V. Arranz, A. Bonafonte, N. Pas- cual, N. Castell, and A. Moreno. 2003. Lexica and corpora for speech-to-speech translation: A trilingual approach. In European Conf. on Speech Commu- nication and Technology, pages 1593-1596, Geneva, Switzerland, September.
- Arne Mauser, Richard Zens, Evgeny Matusov, Saša Hasan, and Hermann Ney. 2006. The RWTH Statisti- cal Machine Translation System for the IWSLT 2006 Evaluation. In Proc. of the International Workshop on Spoken Language Translation, pages 103-110, Kyoto, Japan.
- Franz Josef Och and Hermann Ney. 2002. Discrimina- tive training and maximum entropy models for statis- tical machine translation. In Proc. of the 40th Annual Meeting of the Association for Computational Linguis- tics (ACL), pages 295-302, Philadelphia, PA, July.
- Franz Josef Och and Hermann Ney. 2003. A system- atic comparison of various statistical alignment mod- els. Computational Linguistics, 29(1):19-51, March.
- Maja Popović and Hermann Ney. 2004. Towards the Use of Word Stems and Suffixes for Statistical Ma- chine Translation. In 4th International Conference on Language Resources and Evaluation (LREC), pages 1585-1588, Lisbon, Portugal, May.
- Maja Popović and Hermann Ney. 2005. Exploiting Phrasal Lexica and Additional Morpho-syntactic Lan- guage Resources for Statistical Machine Translation with Scarce Training Data. In 10th Annual Conference of the European Association for Machine Translation (EAMT), pages 212-218, Budapest, Hungary, May.
- William H. Press, Saul A. Teukolsky, William T. Vetter- ling, and Brian P. Flannery. 2002. Numerical Recipes in C++. Cambridge University Press, Cambridge, UK.
- Wade Shen, Richard Zens, Nicola Bertoldi, and Marcello Federico. 2006. The JHU Workshop 2006 IWSLT System. In Proc. of the International Workshop on Spoken Language Translation, pages 59-63, Kyoto, Japan.
Cited by
Sorted by citations
Neural Machine Translation of Rare Words with Subword Units
Sennrich, R., Haddow, B., & Birch, A. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1162 · Cited by 974
Metadata
- Authors
- Vilar, D., Peter, J.-T., & Ney, H.
- Affiliations
- RWTH Aachen University (DE)
- Venue
- Proceedings of the Second Workshop on Statistical Machine Translation - StatMT '07
- Published
- 2007
- Pages
- 33-39
- OpenAlex
- W2116599427
- Cited by
- 87
- References
- 0
- Citations by year
- 2024: 1 · 2023: 1 · 2022: 1 · 2021: 5 · 2020: 4 · 2019: 7 · 2018: 3 · 2017: 6 · 2016: 13 · 2015: 7 · 2014: 7 · 2013: 7 · 2012: 9
- FWCI
- 2.61
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Conference on Machine Translation (WMT) (publishedVersion)
- RWTH Publications (RWTH Aachen) (submittedVersion)
- Funders
- Deutsche Forschungsgemeinschaft
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- statistical machine translation, unseen words, translation rules, Catalan-Spanish translation, morphological data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
