[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/lavie-2004-trainable-transfer-based-mt-approach/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [Machine translation](https://md.mova.elamur.ai/free/en/docs/papers/mtrans/) / A trainable transfer-based MT approach for languages with limited resources

# A trainable transfer-based MT approach for languages with limited resources

**Authors:** [Alon Lavie](https://md.mova.elamur.ai/free/en/docs/papers/authors/alon-lavie/), [Katharina Probst](https://md.mova.elamur.ai/free/en/docs/papers/authors/katharina-probst/), [Erik Peterson](https://md.mova.elamur.ai/free/en/docs/papers/authors/erik-peterson/), [Stephan Vogel](https://md.mova.elamur.ai/free/en/docs/papers/authors/stephan-vogel/), [Lori Levin](https://md.mova.elamur.ai/free/en/docs/papers/authors/lori-levin/), Ariadna Font-Llitjos, [Jaime Carbonell](https://md.mova.elamur.ai/free/en/docs/papers/authors/jaime-carbonell/) · **Year:** 2004 · **Venue:** Proceedings of the 9th EAMT Workshop: Broadening horizons of machine translation and its applications **Link:** [aclanthology.org/2004.eamt-1.14](https://aclanthology.org/2004.eamt-1.14/) · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) — summary only

[**0** citations](https://openalex.org/works?filter=cites:W3102676717) openalex-snapshot · 2026-10-14[Proceedings of the 9th EAMT Workshop: Broadening horizons of machine translation and its applications](https://aclanthology.org/volumes/2004.eamt-1/)[licence](https://creativecommons.org/licenses/by-nc-sa/3.0/)

- [Publisher's page](https://aclanthology.org/2004.eamt-1.14/)
- [PDF](https://aclanthology.org/2004.eamt-1.14.pdf)
- [OpenAlex](https://openalex.org/W3102676717)

**Authors (7)**

1. [Alon Lavie](https://openalex.org/A5103284923) [ORCID](https://orcid.org/0000-0001-9934-6519) · [Semantic Scholar](https://www.semanticscholar.org/author/1784914) · h 36 · 11339 citations · 264 works
2. [Katharina Probst](https://openalex.org/A5079357303) [Semantic Scholar](https://www.semanticscholar.org/author/47399304) · h 11 · 640 citations · 28 works
3. [Erik Peterson](https://openalex.org/A5091723554) [ORCID](https://orcid.org/0000-0002-2033-007X) · [Semantic Scholar](https://www.semanticscholar.org/author/2059365477) · h 35 · 7439 citations · 178 works
4. [Stephan Vogel](https://openalex.org/A5064572063) [ORCID](https://orcid.org/0000-0003-2630-4881) · [Semantic Scholar](https://www.semanticscholar.org/author/145247319) · h 45 · 6853 citations · 228 works
5. [Lori Levin](https://openalex.org/A5008257790) [ORCID](https://orcid.org/0000-0003-0831-3063) · [Semantic Scholar](https://www.semanticscholar.org/author/1686960) · h 27 · 2658 citations · 141 works
6. Ariadna Font-Llitjos
7. [Jaime Carbonell](https://openalex.org/A5109861718) [Semantic Scholar](https://www.semanticscholar.org/author/143712374) · h 64 · 25526 citations · 406 works

Citations and author metrics from openalex-snapshot (2026-10-14); authors with the same name are not always told apart.

## What it is about

An approach for languages with few resources. Bilingual speakers, who need not be linguists, translate a designed English corpus into their language and mark word alignments in a special tool. The corpus is organised in minimal pairs and in order of complexity, from noun phrases to sentences, so that rules can be learned for each level. A learning module infers hierarchical syntactic transfer rules from the aligned data, and a run-time system applies them with a target decoder. The experiment was a Hindi-to-English system built in two months from a few thousand sentence pairs. The transfer system beat a statistical baseline under this small-data condition. A hand-written grammar beat the learned one, which beat no grammar, and the learned rules only covered noun phrases and prepositional phrases. The decoder's reordering window also changed the scores.

## Ideas

- I1. Minimal-pair probes for author deltas: for each author feature (thou and you, the LORD and Jehovah), build a small set of verse pairs that differ only in that feature, and use it to test whether a delta fixes exactly that. Count the tokens fixed and the ones changed by accident.
- I2. Learn one level at a time: the paper learns noun phrases first and reports the gain per level. In the translator, learn the noun-phrase level of the encoder first and report its residual separately before any clause-level rules.
- I3. Reordering window sweep: `en/src/lin.rs` orders words with Markov chains over classes, and a window over candidate orders could be swept like the paper's. Report the score per window, run twice, and check the result is identical.

## For Mova

The minimal-pair elicitation is a cheap way to test deltas, and the level-by-level learning is a control for the claim that a rule is learned. The reordering sweep is a measurable knob in the linearizer. The paper's reliance on a few thousand elicited pairs is a design point Mova can match with the Bible pairs for the test of the author deltas. Its scores are from a different language pair and are not used.

Topics: [Machine translation](https://md.mova.elamur.ai/free/en/docs/papers/topics/machine-translation/)

## Cite

The paper itself, not this card. BibTeX from the library's record of the work.

```
@inproceedings{lavie2004trainable,
  title = {{A trainable transfer-based MT approach for languages with limited resources}},
  author = {Lavie, Alon and Probst, Katharina and Peterson, Erik and Vogel, Stephan and Levin, Lori and Font-Llitjos, Ariadna and Carbonell, Jaime},
  booktitle = {Proceedings of the 9th EAMT Workshop: Broadening horizons of machine translation and its applications},
  year = {2004},
  url = {https://aclanthology.org/2004.eamt-1.14/}
}
```

- [← previous Rapid prototyping of a transfer-based Hebrew-to-English machine translation system](https://md.mova.elamur.ai/free/en/docs/papers/lavie-2004-rapid-prototyping-transfer-based-hebrew/)
- [next → A Fast and Portable Realizer for Text Generation Systems](https://md.mova.elamur.ai/free/en/docs/papers/lavoie-1997-fast-portable-realizer-text-generation/)
- [↑ back to Machine translation](https://md.mova.elamur.ai/free/en/docs/papers/mtrans/)

## References

16 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Allen, J. 1995. Natural Language Understanding, Second Edition, Benjamin Cummings. [find](https://scholar.google.com/scholar?q=Allen%2C+J%2E+1995%2E+Natural+Language+Understanding%2C+Second+Edition%2C+Benjamin+Cummings%2E)
2. Brown, P., Cocke, J., Della Pietra, V., Della Pietra, S., Jelinek, F., Lafferty, J., Mercer, R., and Roossin, P. 1990. A Statistical Approach to Machine Translation. Computational Linguistics 16(2), 79-85. [↗](https://doi.org/10.5555/92858.92860)
3. Brown, P., Della Pietra, V., Della Pietra, S., and Mercer, R. 1993. The Mathematics of Statistical Machine Translation: Parameter Estimation. Computational Linguistics 19(2), 263-311. [find](https://scholar.google.com/scholar?q=Brown%2C+P%2E%2C+Della+Pietra%2C+V%2E%2C+Della+Pietra%2C+S%2E%2C+and+Mercer%2C+R%2E+1993%2E+The+Mathematics+of+Statistical+Machine+Translation%3A+Parameter+Estimation%2E+Computational+Linguistics+19%282%29%2C+263%2D311%2E)
4. Brown, R. 1997. Automated Dictionary Extraction for Knowledge-free Example-based Translation. In Proceedings of International Conference on Theoretical and Methodological Issues in Machine Translation (TMI-1997); 111-118. [find](https://scholar.google.com/scholar?q=Brown%2C+R%2E+1997%2E+Automated+Dictionary+Extraction+for+Knowledge%2Dfree+Example%2Dbased+Translation%2E+In+Proceedings+of+International+Conference+on+Theoretical+and+Methodological+Issues+in+Machine+Translation)
5. Doddington, G. 2002. Automatic Evaluation of Machine Translation Quality using N-gram Cooccurrence Statistics. In Proceedings of Human Language Technologies Conference (HLT-2002); 128-132. [find](https://scholar.google.com/scholar?q=Doddington%2C+G%2E+2002%2E+Automatic+Evaluation+of+Machine+Translation+Quality+using+N%2Dgram+Cooccurrence+Statistics%2E+In+Proceedings+of+Human+Language+Technologies+Conference+%28HLT%2D2002%29%3B+128%2D132%2E)
6. Och, F. J. and Ney, H. Discriminative Training and Maximum Entropy Models for Statistical Machine Translation. In Proceedings of 40 th Annual Meeting of the Association for Computational Linguistics (ACL-2002). Philadelphia, PA. [find](https://scholar.google.com/scholar?q=Och%2C+F%2E+J%2E+and+Ney%2C+H%2E+Discriminative+Training+and+Maximum+Entropy+Models+for+Statistical+Machine+Translation%2E+In+Proceedings+of+40+th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28)
7. Papineni, K., Roukos, S., Ward, T. and Zhu, W. 2002. BLEU: a Method for Automatic Evaluation of Machine Translation. . In Proceedings of 40 th Annual Meeting of the Association for Computational Linguistics (ACL-2002). Philadelphia, PA. [find](https://scholar.google.com/scholar?q=Papineni%2C+K%2E%2C+Roukos%2C+S%2E%2C+Ward%2C+T%2E+and+Zhu%2C+W%2E+2002%2E+BLEU%3A+a+Method+for+Automatic+Evaluation+of+Machine+Translation%2E+%2E+In+Proceedings+of+40+th+Annual+Meeting+of+the+Association+for+Computational+Lingu) [our card](https://md.mova.elamur.ai/free/en/docs/papers/papineni-2002-bleu-method-automatic-evaluation-machine/)
8. Papineni, K., Roukos, S., and Ward, T. 1998. Maximum Likelihood and Discriminative Training of Direct Translation Models. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP-98). 189-192. [find](https://scholar.google.com/scholar?q=Papineni%2C+K%2E%2C+Roukos%2C+S%2E%2C+and+Ward%2C+T%2E+1998%2E+Maximum+Likelihood+and+Discriminative+Training+of+Direct+Translation+Models%2E+In+Proceedings+of+the+International+Conference+on+Acoustics%2C+Speech%2C+and+Signa)
9. Peterson, E. 2002. Adapting a Transfer Engine for Rapid Machine Translation Development. M.S. Thesis, Georgetown University. [find](https://scholar.google.com/scholar?q=Peterson%2C+E%2E+2002%2E+Adapting+a+Transfer+Engine+for+Rapid+Machine+Translation+Development%2E+M%2ES%2E+Thesis%2C+Georgetown+University%2E)
10. Probst, K., Brown, R., Carbonell, J., Lavie, A., Levin, L., and Peterson, E. 2001. Design and Implementation of Controlled Elicitation for Machine Translation of Low-Density Languages. In Workshop MT2010 at Machine Translation Summit VIII. [find](https://scholar.google.com/scholar?q=Probst%2C+K%2E%2C+Brown%2C+R%2E%2C+Carbonell%2C+J%2E%2C+Lavie%2C+A%2E%2C+Levin%2C+L%2E%2C+and+Peterson%2C+E%2E+2001%2E+Design+and+Implementation+of+Controlled+Elicitation+for+Machine+Translation+of+Low%2DDensity+Languages%2E+In+Workshop+MT2)
11. Probst, K. and Levin, L. 2002. Challenges in Automated Elicitation of a Controlled Bilingual Corpus. In Theoretical and Methodological Issues in Machine Translation 2002 (TMI-02). [find](https://scholar.google.com/scholar?q=Probst%2C+K%2E+and+Levin%2C+L%2E+2002%2E+Challenges+in+Automated+Elicitation+of+a+Controlled+Bilingual+Corpus%2E+In+Theoretical+and+Methodological+Issues+in+Machine+Translation+2002+%28TMI%2D02%29%2E)
12. Probst, K., Levin, L., Peterson, E., Lavie, A., and Carbonell, J. 2003. MT for Resource-Poor Languages using Elicitation-based Learning of Syntactic Transfer Rules. Machine Translation. To appear. [find](https://scholar.google.com/scholar?q=Probst%2C+K%2E%2C+Levin%2C+L%2E%2C+Peterson%2C+E%2E%2C+Lavie%2C+A%2E%2C+and+Carbonell%2C+J%2E+2003%2E+MT+for+Resource%2DPoor+Languages+using+Elicitation%2Dbased+Learning+of+Syntactic+Transfer+Rules%2E+Machine+Translation%2E+To+appear%2E)
13. Sato, S. and Nagao, M. 1990. Towards Memory-based Translation. In Proceedings of COLING-90. 247-252. [find](https://scholar.google.com/scholar?q=Sato%2C+S%2E+and+Nagao%2C+M%2E+1990%2E+Towards+Memory%2Dbased+Translation%2E+In+Proceedings+of+COLING%2D90%2E+247%2D252%2E)
14. Vogel, S. and Tribble, A. 2002. Improving Statistical Machine Translation for a Speech-to-Speech Translation task. In Proceedings of the 7 th International Conference on Spoken Language Processing (ICSLP-02). [find](https://scholar.google.com/scholar?q=Vogel%2C+S%2E+and+Tribble%2C+A%2E+2002%2E+Improving+Statistical+Machine+Translation+for+a+Speech%2Dto%2DSpeech+Translation+task%2E+In+Proceedings+of+the+7+th+International+Conference+on+Spoken+Language+Processing+%28IC)
15. Vogel, S., Zhang, Y., Tribble, A., Huang, F., Venugopal, A., Zhao, B., and Waibel, A. 2003. The CMU Statistical Translation System. In Proceedings of MT Summit IX, New Orleans, LA.; 402-409. [find](https://scholar.google.com/scholar?q=Vogel%2C+S%2E%2C+Zhang%2C+Y%2E%2C+Tribble%2C+A%2E%2C+Huang%2C+F%2E%2C+Venugopal%2C+A%2E%2C+Zhao%2C+B%2E%2C+and+Waibel%2C+A%2E+2003%2E+The+CMU+Statistical+Translation+System%2E+In+Proceedings+of+MT+Summit+IX%2C+New+Orleans%2C+LA%2E%3B+402%2D409%2E)
16. Yamada, K. and Knight, K. 2001. A Syntax-based Statistical Translation Model. In Proceedings of the 39th Meeting of the Association for Computational Linguistics (ACL-01). [find](https://scholar.google.com/scholar?q=Yamada%2C+K%2E+and+Knight%2C+K%2E+2001%2E+A+Syntax%2Dbased+Statistical+Translation+Model%2E+In+Proceedings+of+the+39th+Meeting+of+the+Association+for+Computational+Linguistics+%28ACL%2D01%29%2E) [our card](https://md.mova.elamur.ai/free/en/docs/papers/yamada-2001-syntax-based-statistical-translation-model/)