---
title: "Statistical Machine Translation with Scarce — Nießen 2004"
description: "Most statistical MT systems built on the IBM models treat each inflected word form as an unrelated token."
authors: ["Sonja Nießen", "Hermann Ney"]
year: 2004
venue: "Computational Linguistics"
source: "https://aclanthology.org/J04-2003/"
doi: "10.1162/089120104323093285"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/en-2004-statistical-machine-translation-scarce-resources/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/en-2004-statistical-machine-translation-scarce-resources/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2004](https://md.research.elamur.ai/free/papers/2004/) / Statistical Machine Translation with Scarce Resources Using Morpho-syntactic Information

# Statistical Machine Translation with Scarce Resources Using Morpho-syntactic Information

**Authors:** [Sonja Nießen](https://md.research.elamur.ai/free/authors/sonja-niesen/), [Hermann Ney](https://md.research.elamur.ai/free/authors/hermann-ney/) · **Year:** 2004 · **Venue:** Computational Linguistics · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/J04-2003/) · [PDF](https://aclanthology.org/J04-2003.pdf) · [DOI 10.1162/089120104323093285](https://doi.org/10.1162/089120104323093285) · [OpenAlex](https://openalex.org/W2132248251)

**Citations:** 159 citations (openalex-snapshot · 2026-10-14) · [38](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Most statistical MT systems built on the IBM models treat each inflected word form as an unrelated token. This wastes bilingual data, especially when the source language is highly inflected, as German is. Nießen and Ney study how morphological and syntactic knowledge can make up for small parallel corpora.

German and English text is processed with constraint-grammar analyzers (gertwol/gercg, engtwol/engcg). Ambiguous readings are reduced using sentence context, preference rules and a filter that keeps only tags relevant to translation. The analysis is then used in two ways:
- **Restructuring:** German sentences are reordered toward English word order by handling question inversion and rejoining separated verb prefixes.
- **Hierarchical lexicon models:** words are grouped into equivalence classes at several levels of abstraction, so translations learned for one inflected form carry over to related forms. The tags also help resolve categorial ambiguity.

Conventional dictionaries supplement the limited corpus. On German–English Verbmobil and Nespole! data, the combined approach preserves nearly all translation quality with a small fraction of the training data. This is useful for low-resource language pairs with rich morphology.

## Key points
- Combining the methods allowed training on less than 10% of the original bilingual corpus at a cost of only 1.6% in translation quality.
- Experiments use two German–English tasks: Verbmobil (appointment scheduling and travel arrangements) and Nespole!.
- On Verbmobil, German word forms initially have 2.85 readings on average and English forms 1.86. Context-based disambiguation cuts this to 1.20 and 1.02, and selecting relevant tags reduces it further to 1.06 and 1.01.
- Two structural differences between the languages are targeted by sentence-level transformations: question inversion and separated verb prefixes.
- Monolingual resources (morphological analyzers, target-language model data) and one-entry-per-word dictionaries are used to compensate for scarce parallel text, with dedicated handling for disambiguation without context.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Machine translation](https://md.research.elamur.ai/free/shelves/machine-translation/) · [Natural language processing](https://md.research.elamur.ai/free/shelves/nlp/)

Topics: [Machine translation](https://md.research.elamur.ai/free/topics/machine-translation/)

## Cited by

Cited by

38 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 37 not yet.

- [Hebrew Morphological Preprocessing for Statistical Machine Translation](https://md.research.elamur.ai/free/papers/lingbulk-2012-singh-hebrew-morphological-preprocessing-statistical-machine/)

## Cite

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

```bibtex
@article{niesen2004statistical,
  title = {{Statistical Machine Translation with Scarce Resources Using Morpho-syntactic Information}},
  author = {Nießen, Sonja and Ney, Hermann},
  journal = {Computational Linguistics},
  year = {2004},
  doi = {10.1162/089120104323093285},
  url = {https://doi.org/10.1162/089120104323093285}
}
```

- [← previous SMOR: A German Computational Morphology Covering Derivation, Composition and Inflection](https://md.research.elamur.ai/free/papers/schmid-2004-smor-german-computational-morphology-covering/)
- [next → SVMTool: A general POS Tagger Generator Based on Support Vector Machines](https://md.research.elamur.ai/free/papers/gimenez-2004-svmtool-general-pos-tagger-generator/)
- [↑ back to papers of 2004](https://md.research.elamur.ai/free/papers/2004/)

## References

30 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Al-Onaizan, Yaser, Ulrich Germann, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Daniel Marcu, and Kenji Yamada. 2000. Translating with scarce resources. In Proceedings of the 17th National Conference on Artificial Intelligence (AAAI), pages 672–678, Austin, TX, August. [find](https://scholar.google.com/scholar?q=Al%2DOnaizan%2C+Yaser%2C+Ulrich+Germann%2C+Ulf+Hermjakob%2C+Kevin+Knight%2C+Philipp+Koehn%2C+Daniel+Marcu%2C+and+Kenji+Yamada%2E+2000%2E+Translating+with+scarce+resources%2E+In+Proceedings+of+the+17th+National+Conference+o)
2. Berger, Adam L., Peter F. Brown, Stephen A. Della Pietra, Vincent J. Della Pietra, J. R. Gillett, and A. S. Kehler. 1996. Language translation apparatus and method of using context-based translation models. United States Patent, Patent Number 5510981, April. [find](https://scholar.google.com/scholar?q=Berger%2C+Adam+L%2E%2C+Peter+F%2E+Brown%2C+Stephen+A%2E+Della+Pietra%2C+Vincent+J%2E+Della+Pietra%2C+J%2E+R%2E+Gillett%2C+and+A%2E+S%2E+Kehler%2E+1996%2E+Language+translation+apparatus+and+method+of+using+context%2Dbased+translation+m)
3. Brown, Peter F., Stephen A. Della Pietra, Vincent J. Della Pietra, and M. J. Goldsmith. 1993. But dictionaries are data too. In Proceedings of the ARPA Human Language Technology Workshop ’93, pages 202–205, Princeton, NJ, March. [find](https://scholar.google.com/scholar?q=Brown%2C+Peter+F%2E%2C+Stephen+A%2E+Della+Pietra%2C+Vincent+J%2E+Della+Pietra%2C+and+M%2E+J%2E+Goldsmith%2E+1993%2E+But+dictionaries+are+data+too%2E+In+Proceedings+of+the+ARPA+Human+Language+Technology+Workshop+%E2%80%9993%2C+pages+20)
4. Brown, Peter F., John Cocke, Stephen A. Della Pietra, Vincent J. Della Pietra, Frederick Jelinek, John D. Lafferty, Robert L. Mercer, and Paul S. Roossin. 1990. A statistical approach to machine translation. Computational Linguistics, 16(2):79–85. [↗](https://doi.org/10.5555/92858.92860)
5. Brown, Peter F., John Cocke, Stephen A. Della Pietra, Vincent J. Della Pietra, Frederick Jelinek, Robert L. Mercer, and Paul S. Roossin. 1988. A statistical approach to language translation. In Proceedings of COLING 1988: The 12th International Conference on Computational Linguistics, pages 71–76, Budapest, August. [find](https://scholar.google.com/scholar?q=Brown%2C+Peter+F%2E%2C+John+Cocke%2C+Stephen+A%2E+Della+Pietra%2C+Vincent+J%2E+Della+Pietra%2C+Frederick+Jelinek%2C+Robert+L%2E+Mercer%2C+and+Paul+S%2E+Roossin%2E+1988%2E+A+statistical+approach+to+language+translation%2E+In+Procee) [our card](https://md.research.elamur.ai/free/papers/brown-1988-statistical-approach-language-translation/)
6. Brown, Peter F., Stephen A. Della Pietra, Vincent J. Della Pietra, John D. Lafferty, and Robert L. Mercer. 1992. Analysis, statistical transfer, and synthesis in machine translation. In Proceedings of TMI 1992: Fourth International Conference on Theoretical and Methodological Issues in MT, pages 83–100, Montreal, Quebec, Canada, June. [find](https://scholar.google.com/scholar?q=Brown%2C+Peter+F%2E%2C+Stephen+A%2E+Della+Pietra%2C+Vincent+J%2E+Della+Pietra%2C+John+D%2E+Lafferty%2C+and+Robert+L%2E+Mercer%2E+1992%2E+Analysis%2C+statistical+transfer%2C+and+synthesis+in+machine+translation%2E+In+Proceedings+of)
7. Brown, Peter F., Stephen A. Della Pietra, Vincent J. Della Pietra, and Robert L. Mercer. 1993. Mathematics of statistical machine translation: Parameter estimation. Computational Linguistics, 19(2):263–311. [find](https://scholar.google.com/scholar?q=Brown%2C+Peter+F%2E%2C+Stephen+A%2E+Della+Pietra%2C+Vincent+J%2E+Della+Pietra%2C+and+Robert+L%2E+Mercer%2E+1993%2E+Mathematics+of+statistical+machine+translation%3A+Parameter+estimation%2E+Computational+Linguistics%2C+19%282%29%3A26)
8. Darroch, J. N. and D. Ratcliff. 1972. Generalized iterative scaling for log-linear models. Annals of Mathematical Statistics, 43:1470–1480. [↗](https://doi.org/10.1214/aoms/1177692379)
9. Della Pietra, Stephen A., Vincent J. Della Pietra, and John D. Lafferty. 1995. Inducing features of random fields. Technical Report CMU-CS-95-144, Carnegie Mellon University, Pittsburgh, PA. [find](https://scholar.google.com/scholar?q=Della+Pietra%2C+Stephen+A%2E%2C+Vincent+J%2E+Della+Pietra%2C+and+John+D%2E+Lafferty%2E+1995%2E+Inducing+features+of+random+fields%2E+Technical+Report+CMU%2DCS%2D95%2D144%2C+Carnegie+Mellon+University%2C+Pittsburgh%2C+PA%2E)
10. Foster, George. 2000. A maximum entropy/minimum divergence translation model. In Proceedings of ACL 2000: The 38th Annual Meeting of the Association for Computational Linguistics, pages 37–44, Hong Kong, October. [find](https://scholar.google.com/scholar?q=Foster%2C+George%2E+2000%2E+A+maximum+entropy%2Fminimum+divergence+translation+model%2E+In+Proceedings+of+ACL+2000%3A+The+38th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+37%E2%80%9344%2C+Hong+Ko)
11. Garc´ıa-Varea, Ismael and Francisco Casacuberta. 2001. Search algorithms for statistical machine translation based on dynamic programming and pruning techniques. In Proceedings of the MT Summit VIII, pages 115–120, Santiago de Compostela, Spain, September. [find](https://scholar.google.com/scholar?q=Garc%C2%B4%C4%B1a%2DVarea%2C+Ismael+and+Francisco+Casacuberta%2E+2001%2E+Search+algorithms+for+statistical+machine+translation+based+on+dynamic+programming+and+pruning+techniques%2E+In+Proceedings+of+the+MT+Summit+VIII%2C+)
12. Germann, Ulrich, Michael Jahr, Kevin Knight, Daniel Marcu, and Kenji Yamada. 2001. Fast decoding and optimal decoding for machine translation. In Proceedings of ACL-EACL 2001: The 39th Annual Meeting of the Association for Computational Linguistics (joint with EACL 2001), pages 228–235, Toulouse, France, July. [↗](https://doi.org/10.21236/ada459945) [our card](https://md.research.elamur.ai/free/papers/germann-2001-fast-decoding-optimal-decoding-machine/)
13. Kanevsky, Dimitri, Salim Roukos, and Jan Sedivy. 1997. Statistical language model for inflected languages. United States Patent, Patent Number 5835888. [find](https://scholar.google.com/scholar?q=Kanevsky%2C+Dimitri%2C+Salim+Roukos%2C+and+Jan+Sedivy%2E+1997%2E+Statistical+language+model+for+inflected+languages%2E+United+States+Patent%2C+Patent+Number+5835888%2E)
14. Karlsson, Fred. 1990. Constraint grammar as a framework for parsing running text. In Proceedings of COLING 1990: The 13th International Conference on Computational Linguistics, volume 3, pages 168–173, Helsinki, August. [find](https://scholar.google.com/scholar?q=Karlsson%2C+Fred%2E+1990%2E+Constraint+grammar+as+a+framework+for+parsing+running+text%2E+In+Proceedings+of+COLING+1990%3A+The+13th+International+Conference+on+Computational+Linguistics%2C+volume+3%2C+pages+168%E2%80%93173)
15. Koehn, Philipp and Kevin Knight. 2001. Knowledge sources for word-level translation models. In Lillian Lee and Donna Harman, editors, Proceedings of EMNLP 2001: Conference on Empirical Methods in Natural Language Processing, pages 27–35, Pittsburgh, PA, June. [find](https://scholar.google.com/scholar?q=Koehn%2C+Philipp+and+Kevin+Knight%2E+2001%2E+Knowledge+sources+for+word%2Dlevel+translation+models%2E+In+Lillian+Lee+and+Donna+Harman%2C+editors%2C+Proceedings+of+EMNLP+2001%3A+Conference+on+Empirical+Methods+in+Natu)
16. Larson, Martha, Daniel Willett, Joachim Köhler, and Gerhard Rigoll. 2000. Compound splitting and lexical unit recombination for improved performance of a speech recognition system for German parliamentary speeches. In Proceedings ICSLP 2000: Sixth International Conference on Spoken Language Processing, volume 3, pages 945–948, Beijing, February. [find](https://scholar.google.com/scholar?q=Larson%2C+Martha%2C+Daniel+Willett%2C+Joachim+Ko%CC%88hler%2C+and+Gerhard+Rigoll%2E+2000%2E+Compound+splitting+and+lexical+unit+recombination+for+improved+performance+of+a+speech+recognition+system+for+German+parliame)
17. Lavie, Alon, Chad Langley, Alex Waibel, Fabio Pianesi, Gianni Lazzari, Paolo Coletti, Loredana Taddei, and Franco Balducci. 2001. Architecture and design considerations in NESPOLE! A speech translation system for e-commerce applications. In James Allan, editor, Proceedings of HLT 2001: First International Conference on Human Language Technology Research, pages 31–39, San Diego, March. [find](https://scholar.google.com/scholar?q=Lavie%2C+Alon%2C+Chad+Langley%2C+Alex+Waibel%2C+Fabio+Pianesi%2C+Gianni+Lazzari%2C+Paolo+Coletti%2C+Loredana+Taddei%2C+and+Franco+Balducci%2E+2001%2E+Architecture+and+design+considerations+in+NESPOLE%21+A+speech+translatio)
18. Maltese, G., and F. Mancini. 1992. An automatic technique to include grammatical and morphological information in a trigram-based statistical language model. In Proceedings of ICASSP 1992: International Conference on Acoustics, Speech and Signal Processing, pages 157–160, San Francisco, March. [find](https://scholar.google.com/scholar?q=Maltese%2C+G%2E%2C+and+F%2E+Mancini%2E+1992%2E+An+automatic+technique+to+include+grammatical+and+morphological+information+in+a+trigram%2Dbased+statistical+language+model%2E+In+Proceedings+of+ICASSP+1992%3A+Internation)
19. NESPOLE! (NEgotiating through SPOken Language in e-commerce). 2000 Project homepage. Available at [http://nespole.itc.it/](http://nespole.itc.it/). [↗](http://nespole.itc.it/)
20. Ney, Hermann, Sonja Nießen, Franz Josef Och, Hassan Sawaf, Christoph Tillmann, and Stephan Vogel. 2000. Algorithms for statistical translation of spoken language. IEEE Transactions on Speech and Audio Processing, 8(1):24–36. [↗](https://doi.org/10.1109/89.817451)
21. Nießen, Sonja and Gregor Leusch. 2000. EvalTrans, a tool for semi-automatic evaluation of machine translation. In Proceedings of LREC 2000, Athens. Tool is available at [http://www-i6.Informatik](http://www-i6.Informatik). RWTH-Aachen.DE/˜niessen/Evaluation/. [↗](http://www-i6.Informatik)
22. Nießen, Sonja and Hermann Ney. 2000. Improving SMT quality with morpho-syntactic analysis. In Proceedings of COLING 2000: The 18th International Conference on Computational Linguistics, pages 1081–1085, Saarbrücken, Germany, July. [find](https://scholar.google.com/scholar?q=Nie%C3%9Fen%2C+Sonja+and+Hermann+Ney%2E+2000%2E+Improving+SMT+quality+with+morpho%2Dsyntactic+analysis%2E+In+Proceedings+of+COLING+2000%3A+The+18th+International+Conference+on+Computational+Linguistics%2C+pages+1081%E2%80%93108)
23. Nießen, Sonja and Hermann Ney. 2001. Morpho-syntactic analysis for reordering in statistical machine translation. In Proceedings of MT Summit VIII, pages 247–252, Santiago de Compostela, Spain, September. [find](https://scholar.google.com/scholar?q=Nie%C3%9Fen%2C+Sonja+and+Hermann+Ney%2E+2001%2E+Morpho%2Dsyntactic+analysis+for+reordering+in+statistical+machine+translation%2E+In+Proceedings+of+MT+Summit+VIII%2C+pages+247%E2%80%93252%2C+Santiago+de+Compostela%2C+Spain%2C+Septem)
24. Nießen, Sonja, Stephan Vogel, Hermann Ney, and Christoph Tillmann. 1998. A DP based search algorithm for statistical machine translation. In Proceedings of COLING-ACL 1998: The 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics, pages 960–967, Montreal, Quebec, Canada, August. [find](https://scholar.google.com/scholar?q=Nie%C3%9Fen%2C+Sonja%2C+Stephan+Vogel%2C+Hermann+Ney%2C+and+Christoph+Tillmann%2E+1998%2E+A+DP+based+search+algorithm+for+statistical+machine+translation%2E+In+Proceedings+of+COLING%2DACL+1998%3A+The+36th+Annual+Meeting+of+)
25. Och, Franz Josef. 2002. Machine Translation: From Single-Word Models to Alignment Templates. Ph.D. thesis, Computer Science Department, RWTH–University of Technology, Aachen, Germany. [find](https://scholar.google.com/scholar?q=Och%2C+Franz+Josef%2E+2002%2E+Machine+Translation%3A+From+Single%2DWord+Models+to+Alignment+Templates%2E+Ph%2ED%2E+thesis%2C+Computer+Science+Department%2C+RWTH%E2%80%93University+of+Technology%2C+Aachen%2C+Germany%2E)
26. Och, Franz Josef, Christoph Tillmann, and Hermann Ney. 1999. Improved alignment models for statistical machine translation. In Proceedings of EMNLP 1999: Conference on Empirical Methods in Natural Language Processing, pages 20–28, University of Maryland, College Park, June. [find](https://scholar.google.com/scholar?q=Och%2C+Franz+Josef%2C+Christoph+Tillmann%2C+and+Hermann+Ney%2E+1999%2E+Improved+alignment+models+for+statistical+machine+translation%2E+In+Proceedings+of+EMNLP+1999%3A+Conference+on+Empirical+Methods+in+Natural+Lan) [our card](https://md.research.elamur.ai/free/papers/och-1999-improved-alignment-models-statistical-machine/)
27. Och, Franz Josef and Hans Weber. 1998. Improving statistical natural language translation with categories and rules. In Proceedings of COLING-ACL 1998: The 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics, pages 985–989, Montreal, Quebec, Canada, August. [find](https://scholar.google.com/scholar?q=Och%2C+Franz+Josef+and+Hans+Weber%2E+1998%2E+Improving+statistical+natural+language+translation+with+categories+and+rules%2E+In+Proceedings+of+COLING%2DACL+1998%3A+The+36th+Annual+Meeting+of+the+Association+for+C)
28. Papineni, Kishore, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2001. Bleu: A method for automatic evaluation of machine translation. Technical Report RC22176 (W0109-022), IBM Research Division, Yorktown Heights, NY, September. [find](https://scholar.google.com/scholar?q=Papineni%2C+Kishore%2C+Salim+Roukos%2C+Todd+Ward%2C+and+Wei%2DJing+Zhu%2E+2001%2E+Bleu%3A+A+method+for+automatic+evaluation+of+machine+translation%2E+Technical+Report+RC22176+%28W0109%2D022%29%2C+IBM+Research+Division%2C+Yorktow) [our card](https://md.research.elamur.ai/free/papers/papineni-2002-bleu-method-automatic-evaluation-machine/)
29. Ratnaparkhi, Adwait. 1997. A simple introduction to maximum entropy models for natural language processing. Technical Report 97–08, Institute for Research in Cognitive Science, University of Pennsylvania, Philadelphia, May. [find](https://scholar.google.com/scholar?q=Ratnaparkhi%2C+Adwait%2E+1997%2E+A+simple+introduction+to+maximum+entropy+models+for+natural+language+processing%2E+Technical+Report+97%E2%80%9308%2C+Institute+for+Research+in+Cognitive+Science%2C+University+of+Pennsylva)
30. Tillmann, Christoph and Hermann Ney. 2000. Word re-ordering and DP-based search in statistical machine translation. In Proceedings of COLING 2000: The 18th International Conference on Computational Linguistics, pages 850–856, Saarbrücken, Germany, August. [find](https://scholar.google.com/scholar?q=Tillmann%2C+Christoph+and+Hermann+Ney%2E+2000%2E+Word+re%2Dordering+and+DP%2Dbased+search+in+statistical+machine+translation%2E+In+Proceedings+of+COLING+2000%3A+The+18th+International+Conference+on+Computational+Li)