--- title: "Clause Restructuring for Statistical Machine — Collins 2005" description: "Phrase-based statistical MT handles local reordering reasonably well, but it struggles when source and target languages differ systematically in…" authors: ["Michael Collins", "Philipp Koehn", "Ivona Kučerová"] year: 2005 venue: "Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05)" source: "https://aclanthology.org/P05-1066/" doi: "10.3115/1219840.1219906" 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/collins-2005-clause-restructuring-statistical-machine-translation/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/collins-2005-clause-restructuring-statistical-machine-translation/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2005](https://md.research.elamur.ai/free/papers/2005/) / Clause Restructuring for Statistical Machine Translation # Clause Restructuring for Statistical Machine Translation **Authors:** [Michael Collins](https://md.research.elamur.ai/free/authors/michael-collins/), [Philipp Koehn](https://md.research.elamur.ai/free/authors/philipp-koehn/), Ivona Kučerová · **Year:** 2005 · **Venue:** Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05) · **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/P05-1066/) · [PDF](https://aclanthology.org/P05-1066.pdf) · [DOI 10.3115/1219840.1219906](https://doi.org/10.3115/1219840.1219906) · [OpenAlex](https://openalex.org/W2162245945) **Citations:** 585 citations (openalex-snapshot · 2026-10-14) · [333](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary Phrase-based statistical MT handles local reordering reasonably well, but it struggles when source and target languages differ systematically in clause-level word order. German and English are a hard case because of verb-second matrix clauses, verb-final subordinate clauses and clause-final infinitives. The authors propose a preprocessing approach. They parse each German sentence and apply a small set of hand-written, linguistically motivated transformations to the tree, producing a German word sequence that follows English order more closely. This reordering is applied to both the training data and the test input. The modified text is then fed to an unchanged phrase-based system (Koehn et al., 2003). On German-to-English Europarl translation, Bleu rose from 25.2% to 26.8%, a statistically significant gain. Human judgements also favoured the reordered output. The work shows that explicit syntax can help a strong phrase-based system without redesigning the decoder or the model. ## Key points - The task is German→English translation on the Europarl corpus. The underlying system is the phrase-based model of Koehn et al. (2003), and the German parser was provided by Amit Dubey. - Bleu improved from 25.2% (baseline) to 26.8% (with clause restructuring), and the difference is statistically significant. - The rules target several German phenomena: - finite verbs in second position in main clauses and in final position in subordinate clauses; - infinitival verbs at the end of their VP; - subjects appearing after the finite verb; - the placement of negation (*nicht* vs. *not*). - Human evaluation: - One annotator judged the reordered system better on 40 of 100 sampled sentences. - In a larger per-sentence comparison over 1785 test sentences, about 52.85% improved, 36.4% got worse and 10.75% stayed the same. - Xia and McCord (2004) learned over 56,000 reordering rules automatically. This paper uses only a handful of manual transformations and reports comparable gains, though on a different language pair. ## Interesting ideas - **Reorder the source, keep the translator unchanged.** Syntax enters only as a preprocessing step applied to both training and test data, so any existing system can benefit without modifying its internals. This could carry over to other pipelines where reworking the core model is expensive. - **Few general rules instead of many local ones.** The parser produces flat German VPs and clauses, which yield a huge number of distinct context-free productions. A single rule such as "move the infinitival verb to the front of the VP" covers all of them, whereas production-level rules would need a separate transformation for each. This matters for any language with free word order and flat treebank structures, which is relevant to Ukrainian. - **Linguistic analysis as a design source.** The transformations follow directly from a description of how German clause structure differs from English. A short contrastive grammar sketch can be turned into effective, interpretable engineering rules before trying data-driven alternatives. - **Pairwise human judgements with sign-test-style statistics.** Besides Bleu, the authors count per-sentence better/worse/equal judgements and compute confidence intervals. They also question whether bootstrap tests are valid for Bleu. This is a useful complement whenever automatic metric gains are small. *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 333 papers of our library cite it (of the 140673 whose bibliographies we read); 23 of them have a page here, 310 not yet. - [Improving Cross-lingual Transfer through Subtree-aware Word Reordering](https://md.research.elamur.ai/free/papers/arviv-2023-improving-cross-lingual-transfer-through/) - [Hierarchical Phrase-Based Translation](https://md.research.elamur.ai/free/papers/chiang-2007-hierarchical-phrase-based-translation/) - [Crossroads between contrastive linguistics, translation studies and machine translation: TC3-II](https://md.research.elamur.ai/free/papers/czulo-2017-crossroads-between-contrastive-linguistics/) - [Neural Syntactic Preordering for Controlled Paraphrase Generation](https://md.research.elamur.ai/free/papers/goyal-2020-neural-syntactic-preordering-controlled-paraphrase/) - [Anaphora Models and Reordering for Phrase-Based SMT](https://md.research.elamur.ai/free/papers/hardmeier-2014-anaphora-models-reordering-phrase-based/) - [Statistical Syntax-Directed Translation with Extended Domain of Locality](https://md.research.elamur.ai/free/papers/huang-2006-statistical-syntax-directed-translation-extended/) - [Semantics-Based Machine Translation with Hyperedge Replacement Grammars](https://md.research.elamur.ai/free/papers/jones-2012-semantics-based-machine-translation-hyperedge/) - [Edinburgh System Description for the 2005 IWSLT Speech Translation Evaluation](https://md.research.elamur.ai/free/papers/koehn-2005-edinburgh-system-description-2005-iwslt/) - [Manual and Automatic Evaluation of Machine Translation between European Languages](https://md.research.elamur.ai/free/papers/koehn-2006-manual-automatic-evaluation-machine-translation/) - [Experiments in Domain Adaptation for Statistical Machine Translation](https://md.research.elamur.ai/free/papers/koehn-2007-experiments-domain-adaptation-statistical-machine/) - [Factored Translation Models](https://md.research.elamur.ai/free/papers/koehn-2007-factored-translation-models/) - [Soft Syntactic Constraints for Hierarchical Phrased-Based Translation](https://md.research.elamur.ai/free/papers/marton-2008-soft-syntactic-constraints-hierarchical-phrased/) - [Forest-based Translation Rule Extraction](https://md.research.elamur.ai/free/papers/mi-2008-forest-based-translation-rule-extraction/) - [Forest-Based Translation](https://md.research.elamur.ai/free/papers/mi-2008-forest-based-translation/) - [Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations](https://md.research.elamur.ai/free/papers/noord-2017-neural-semantic-parsing-character-based/) - [Cross-lingual Word Clusters for Direct Transfer of Linguistic Structure](https://md.research.elamur.ai/free/papers/tackstrom-2012-cross-lingual-word-clusters-direct/) - [Modeling Coverage for Neural Machine Translation](https://md.research.elamur.ai/free/papers/tu-2016-modeling-coverage-neural-machine-translation/) - [The Galactic Dependencies Treebanks: Getting More Data by Synthesizing New Languages](https://md.research.elamur.ai/free/papers/ud-2016-wang-galactic-dependencies-treebanks-getting-more/) - [Chinese Syntactic Reordering for Statistical Machine Translation](https://md.research.elamur.ai/free/papers/wang-2007-chinese-syntactic-reordering-statistical-machine/) - [One Model to Learn Both: Zero Pronoun Prediction and Translation](https://md.research.elamur.ai/free/papers/wang-2019-one-model-learn-both-zero/) - [GuoFeng: A Benchmark for Zero Pronoun Recovery and Translation](https://md.research.elamur.ai/free/papers/xu-2022-guofeng-benchmark-zero-pronoun-recovery/) - [Bridging the Gap between Training and Inference for Neural Machine Translation](https://md.research.elamur.ai/free/papers/zhang-2019-bridging-gap-between-training-inference/) - [Handling Syntactic Divergence in Low-resource Machine Translation](https://md.research.elamur.ai/free/papers/zhou-2019-handling-syntactic-divergence-low-resource/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{collins2005clause, title = {{Clause Restructuring for Statistical Machine Translation}}, author = {Collins, Michael and Koehn, Philipp and Kučerová, Ivona}, booktitle = {Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05)}, year = {2005}, doi = {10.3115/1219840.1219906}, url = {https://doi.org/10.3115/1219840.1219906} } ``` - [← previous Choosing an Optimal Architecture for Segmentation and POS-Tagging of Modern Hebrew](https://md.research.elamur.ai/free/papers/aclbulk-2005-haim-choosing-optimal-architecture-segmentation-pos/) - [next → Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking](https://md.research.elamur.ai/free/papers/narrative-2005-charniak-coarse-fine-n-best-parsing/) - [↑ back to papers of 2005](https://md.research.elamur.ai/free/papers/2005/) ## References 13 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Alshawi, H. (1996). Head automata and bilingual tiling: Translation with minimal representations (invited talk). In Proceedings of ACL 1996. [find](https://scholar.google.com/scholar?q=Alshawi%2C+H%2E+%281996%29%2E+Head+automata+and+bilingual+tiling%3A+Translation+with+minimal+representations+%28invited+talk%29%2E+In+Proceedings+of+ACL+1996%2E) 2. Berger, A. L., Pietra, S. A. D., and Pietra, V. J. D. (1996). A maximum entropy approach to natural language processing. Computational Linguistics, 22(1):39–69. [find](https://scholar.google.com/scholar?q=Berger%2C+A%2E+L%2E%2C+Pietra%2C+S%2E+A%2E+D%2E%2C+and+Pietra%2C+V%2E+J%2E+D%2E+%281996%29%2E+A+maximum+entropy+approach+to+natural+language+processing%2E+Computational+Linguistics%2C+22%281%29%3A39%E2%80%9369%2E) [our card](https://md.research.elamur.ai/free/papers/berger-1996-maximum-entropy-approach-natural-language/) 3. Brown, P. F., Pietra, S. A. D., Pietra, V. J. D., and Mercer, R. L. (1993). The mathematics of statistical machine translation. Computational Linguistics, 19(2):263–313. [find](https://scholar.google.com/scholar?q=Brown%2C+P%2E+F%2E%2C+Pietra%2C+S%2E+A%2E+D%2E%2C+Pietra%2C+V%2E+J%2E+D%2E%2C+and+Mercer%2C+R%2E+L%2E+%281993%29%2E+The+mathematics+of+statistical+machine+translation%2E+Computational+Linguistics%2C+19%282%29%3A263%E2%80%93313%2E) 4. Charniak, E., Knight, K., and Yamada, K. (2003). Syntax-based language models for statistical machine translation. In Proceedings of the MT Summit IX. [find](https://scholar.google.com/scholar?q=Charniak%2C+E%2E%2C+Knight%2C+K%2E%2C+and+Yamada%2C+K%2E+%282003%29%2E+Syntax%2Dbased+language+models+for+statistical+machine+translation%2E+In+Proceedings+of+the+MT+Summit+IX%2E) 5. Dubey, A. and Keller, F. (2003). Parsing german with sister-head dependencies. In Proceedings of ACL 2003. [find](https://scholar.google.com/scholar?q=Dubey%2C+A%2E+and+Keller%2C+F%2E+%282003%29%2E+Parsing+german+with+sister%2Dhead+dependencies%2E+In+Proceedings+of+ACL+2003%2E) 6. Efron, B. and Tibshirani, R. J. (1993). An Introduction to the Bootstrap. Springer-Verlag. [find](https://scholar.google.com/scholar?q=Efron%2C+B%2E+and+Tibshirani%2C+R%2E+J%2E+%281993%29%2E+An+Introduction+to+the+Bootstrap%2E+Springer%2DVerlag%2E) 7. Galley, M., Hopkins, M., Knight, K., and Marcu, D. (2004). What’s in a translation rule? In Proceedings of HLT-NAACL 2004. [find](https://scholar.google.com/scholar?q=Galley%2C+M%2E%2C+Hopkins%2C+M%2E%2C+Knight%2C+K%2E%2C+and+Marcu%2C+D%2E+%282004%29%2E+What%E2%80%99s+in+a+translation+rule%3F+In+Proceedings+of+HLT%2DNAACL+2004%2E) [our card](https://md.research.elamur.ai/free/papers/galley-2004-what-s-translation-rule/) 8. Gildea, D. (2003). Loosely tree-based alignment for machine translation. In Proceedings of ACL 2003. [find](https://scholar.google.com/scholar?q=Gildea%2C+D%2E+%282003%29%2E+Loosely+tree%2Dbased+alignment+for+machine+translation%2E+In+Proceedings+of+ACL+2003%2E) [our card](https://md.research.elamur.ai/free/papers/gildea-2003-loosely-tree-based-alignment-machine/) 9. Graehl, J. and Knight, K. (2004). Training tree transducers. In Proceedings of HLT-NAACL 2004. [find](https://scholar.google.com/scholar?q=Graehl%2C+J%2E+and+Knight%2C+K%2E+%282004%29%2E+Training+tree+transducers%2E+In+Proceedings+of+HLT%2DNAACL+2004%2E) [our card](https://md.research.elamur.ai/free/papers/graehl-2004-training-tree-transducers/) 10. Koehn, P. (2004). Statistical significance tests for machine translation evaluation. In Lin, D. and Wu, D., editors, Proceedings of EMNLP 2004. [find](https://scholar.google.com/scholar?q=Koehn%2C+P%2E+%282004%29%2E+Statistical+significance+tests+for+machine+translation+evaluation%2E+In+Lin%2C+D%2E+and+Wu%2C+D%2E%2C+editors%2C+Proceedings+of+EMNLP+2004%2E) 11. Koehn, P. and Knight, K. (2003). Feature-rich statistical translation of noun phrases. In Hinrichs, E. and Roth, D., editors, Proceedings of ACL 2003, pages 311–318. [find](https://scholar.google.com/scholar?q=Koehn%2C+P%2E+and+Knight%2C+K%2E+%282003%29%2E+Feature%2Drich+statistical+translation+of+noun+phrases%2E+In+Hinrichs%2C+E%2E+and+Roth%2C+D%2E%2C+editors%2C+Proceedings+of+ACL+2003%2C+pages+311%E2%80%93318%2E) 12. Koehn, P., Och, F. J., and Marcu, D. (2003). Statistical phrase based translation. In Proceedings of HLT-NAACL 2003. [find](https://scholar.google.com/scholar?q=Koehn%2C+P%2E%2C+Och%2C+F%2E+J%2E%2C+and+Marcu%2C+D%2E+%282003%29%2E+Statistical+phrase+based+translation%2E+In+Proceedings+of+HLT%2DNAACL+2003%2E) 13. Lehmann, E. L. (1986). Testing Statistical Hypotheses (Second Edition). Springer-Verlag. [find](https://scholar.google.com/scholar?q=Lehmann%2C+E%2E+L%2E+%281986%29%2E+Testing+Statistical+Hypotheses+%28Second+Edition%29%2E+Springer%2DVerlag%2E)