--- title: "Modelling pronominal anaphora in — Hardmeier 2010" description: "Standard SMT systems translate each sentence in isolation, so they cannot use earlier context." authors: ["Christian Hardmeier", "Marcello Federico"] year: 2010 venue: "Proceedings of the 7th International Workshop on Spoken Language Translation: Papers" source: "https://aclanthology.org/2010.iwslt-papers.10/" 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/hardmeier-2010-modelling-pronominal-anaphora-statistical-machine/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/hardmeier-2010-modelling-pronominal-anaphora-statistical-machine/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2010](https://md.research.elamur.ai/free/papers/2010/) / Modelling pronominal anaphora in statistical machine translation # Modelling pronominal anaphora in statistical machine translation **Authors:** [Christian Hardmeier](https://md.research.elamur.ai/free/authors/christian-hardmeier/), [Marcello Federico](https://md.research.elamur.ai/free/authors/marcello-federico/) · **Year:** 2010 · **Venue:** Proceedings of the 7th International Workshop on Spoken Language Translation: Papers · **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/2010.iwslt-papers.10/) · [PDF](https://aclanthology.org/2010.iwslt-papers.10.pdf) · [OpenAlex](https://openalex.org/W2163038970) **Citations:** 112 citations (openalex-snapshot · 2026-10-14) · [76](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary Standard SMT systems translate each sentence in isolation, so they cannot use earlier context. This is a real problem for pronouns, whose correct form often depends on an antecedent that may appear in another sentence. Hardmeier and Federico first measure the problem. They manually checked how their phrase-based WMT 2010 system rendered German anaphoric pronouns into English in 13 documents from the WMT 2009 newswire test set. Only about three in five pronouns were translated acceptably. Feminine, polite-address and reflexive forms did worst, mainly because German forms such as sie and sich are ambiguous. The authors then propose a word dependency model that scores links between pairs of words, either inside one sentence or across sentence boundaries. For English-German translation, they feed pronoun–antecedent links from the BART coreference resolver into this model, so the output pronoun can agree with how the antecedent's head was translated. This yields a small but statistically significant gain in pronoun translation recall without hurting other aspects of quality. It is an early step toward SMT that treats a text as connected discourse. ## Key points - The case study covered 13 documents (219 sentences) from the WMT 2009 German-English test set, which has 111 newswire documents. Overall, 122 of 199 anaphoric pronouns (61 %) were translated adequately by a system using 6-gram language models. - Accuracy varied strongly by pronoun type: - demonstratives: about 90 % - masculine/neuter singular and plural: about 77 % - feminine singular: 33 % - reflexive: 27 % - polite address: 25 % - The experiments ran in the English-German direction because an English coreference resolver was available. BART, trained on the ACE02-npaper corpus with separate pronoun models, links each pronoun to the syntactic head of one antecedent noun phrase. - The only prior SMT work cited is Le Nagard and Koehn's English-French approach. It left BLEU unchanged, and correct pronouns dropped slightly from 69 % to 68 %. - Planned future work includes: - easier language pairs (English-French, German-English) - manually annotated coreference to measure noise - reusing the dependency model for verb and adjective agreement *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: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/) Topics: [Coreference resolution](https://md.research.elamur.ai/free/topics/coreference-resolution/) · [Machine translation](https://md.research.elamur.ai/free/topics/machine-translation/) ## Cited by Cited by 76 papers of our library cite it (of the 140673 whose bibliographies we read); 15 of them have a page here, 61 not yet. - [Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias Throughout the Machine Learning Lifecycle*](https://md.research.elamur.ai/free/papers/cao-2021-gender-inclusive-coreference-resolution-analysis/) - [ParCor 1.0: A Parallel Pronoun-Coreference Corpus to Support Statistical MT](https://md.research.elamur.ai/free/papers/guillou-2014-parcor-1-0-parallel-pronoun/) - [Latent Anaphora Resolution for Cross-Lingual Pronoun Prediction](https://md.research.elamur.ai/free/papers/hardmeier-2013-latent-anaphora-resolution-cross-lingual/) - [BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation](https://md.research.elamur.ai/free/papers/jiang-2022-blonde-automatic-evaluation-metric-document/) - [Discourse Structure in Machine Translation Evaluation](https://md.research.elamur.ai/free/papers/joty-2017-discourse-structure-machine-translation-evaluation/) - [ParCorFull: a Parallel Corpus Annotated with Full Coreference](https://md.research.elamur.ai/free/papers/koltunski-2018-parcorfull-parallel-corpus-annotated-full/) - [文档级神经机器翻译综述](https://md.research.elamur.ai/free/papers/lv-2024-document-level-neural/) - [Translation of "It" in a Deep Syntax Framework](https://md.research.elamur.ai/free/papers/novak-2013-translation-it-deep-syntax-framework/) - [Gender Bias in Machine Translation](https://md.research.elamur.ai/free/papers/savoldi-2021-gender-bias-machine-translation/) - [Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments](https://md.research.elamur.ai/free/papers/stojanovski-2018-coreference-coherence-neural-machine-translation/) - [Zero Pronoun Resolution can Improve the Quality of J-E Translation](https://md.research.elamur.ai/free/papers/taira-2012-zero-pronoun-resolution-can-improve/) - [Embarrassingly Easy Document-Level MT Metrics: How to Convert Any Pretrained Metric into a Document-Level Metric](https://md.research.elamur.ai/free/papers/vernikos-2022-embarrassingly-easy-document-level-mt/) - [Context-Aware Neural Machine Translation Learns Anaphora Resolution](https://md.research.elamur.ai/free/papers/voita-2018-context-aware-neural-machine-translation/) - [When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion](https://md.research.elamur.ai/free/papers/voita-2019-when-good-translation-is-wrong/) - [GuoFeng: A Benchmark for Zero Pronoun Recovery and Translation](https://md.research.elamur.ai/free/papers/xu-2022-guofeng-benchmark-zero-pronoun-recovery/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{hardmeier2010modelling, title = {{Modelling pronominal anaphora in statistical machine translation}}, author = {Hardmeier, Christian and Federico, Marcello}, booktitle = {Proceedings of the 7th International Workshop on Spoken Language Translation: Papers}, year = {2010}, url = {https://aclanthology.org/2010.iwslt-papers.10/} } ``` - [← previous Modeling Morphosyntactic Agreement in Constituency-Based Parsing of Modern Hebrew](https://md.research.elamur.ai/free/papers/aclbulk-2010-tsarfaty-modeling-morphosyntactic-agreement-constituency-based/) - [next → Morphological Analysis and Generation of Arabic Nouns: A Morphemic Functional Approach](https://md.research.elamur.ai/free/papers/lingbulk-2010-altantawy-morphological-analysis-generation-arabic-nouns/) - [↑ back to papers of 2010](https://md.research.elamur.ai/free/papers/2010/) ## References 15 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. P. F. Brown, J. Cocke, S. A. Della Pietra, V. J. Della Pietra, et al., “A statistical approach to Machine Translation,” Computational linguistics, vol. 16, pp. 79–85, 1990. [find](https://scholar.google.com/scholar?q=P%2E+F%2E+Brown%2C+J%2E+Cocke%2C+S%2E+A%2E+Della+Pietra%2C+V%2E+J%2E+Della+Pietra%2C+et+al%2E%2C+%E2%80%9CA+statistical+approach+to+Machine+Translation%2C%E2%80%9D+Computational+linguistics%2C+vol%2E+16%2C+pp%2E+79%E2%80%9385%2C+1990%2E) 2. P. F. Brown, S. A. Della Pietra, V. J. Della Pietra, and R. L. Mercer, “The mathematics of Statistical Machine Translation,” Computational linguistics, vol. 19, pp. 263–311, 1993. [find](https://scholar.google.com/scholar?q=P%2E+F%2E+Brown%2C+S%2E+A%2E+Della+Pietra%2C+V%2E+J%2E+Della+Pietra%2C+and+R%2E+L%2E+Mercer%2C+%E2%80%9CThe+mathematics+of+Statistical+Machine+Translation%2C%E2%80%9D+Computational+linguistics%2C+vol%2E+19%2C+pp%2E+263%E2%80%93311%2C+1993%2E) 3. M. Strube, “Anaphora and coreference resolution, Statistical,” in Encyclopedia of language and linguistics. Elsevier, 2006, pp. 216–222. [find](https://scholar.google.com/scholar?q=M%2E+Strube%2C+%E2%80%9CAnaphora+and+coreference+resolution%2C+Statistical%2C%E2%80%9D+in+Encyclopedia+of+language+and+linguistics%2E+Elsevier%2C+2006%2C+pp%2E+216%E2%80%93222%2E) 4. C. Callison-Burch, P. Koehn, C. Monz, and J. Schroeder, “Findings of the 2009 Workshop on Statistical Machine Translation,” in Proceedings of the Fourth Workshop on Statistical Machine Translation. Athens, Greece: Association for Computational Linguistics, March 2009, pp. 1–28. [find](https://scholar.google.com/scholar?q=C%2E+Callison%2DBurch%2C+P%2E+Koehn%2C+C%2E+Monz%2C+and+J%2E+Schroeder%2C+%E2%80%9CFindings+of+the+2009+Workshop+on+Statistical+Machine+Translation%2C%E2%80%9D+in+Proceedings+of+the+Fourth+Workshop+on+Statistical+Machine+Translation%2E+At) [our card](https://md.research.elamur.ai/free/papers/burch-2009-findings-2009-workshop-statistical-machine/) 5. C. Hardmeier, A. Bisazza, and M. Federico, “FBK at WMT 2010: Word lattices for morphological reduction and chunk-based reordering,” in Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and Metrics MATR. Uppsala, Sweden: Association for Computational Linguistics, 2010. [find](https://scholar.google.com/scholar?q=C%2E+Hardmeier%2C+A%2E+Bisazza%2C+and+M%2E+Federico%2C+%E2%80%9CFBK+at+WMT+2010%3A+Word+lattices+for+morphological+reduction+and+chunk%2Dbased+reordering%2C%E2%80%9D+in+Proceedings+of+the+Joint+Fifth+Workshop+on+Statistical+Machine+Tr) 6. R. Mitkov, “Introduction: Special issue on anaphora resolution in Machine Translation and Multilingual NLP,” Machine translation, vol. 14, pp. 159–161, 1999. [find](https://scholar.google.com/scholar?q=R%2E+Mitkov%2C+%E2%80%9CIntroduction%3A+Special+issue+on+anaphora+resolution+in+Machine+Translation+and+Multilingual+NLP%2C%E2%80%9D+Machine+translation%2C+vol%2E+14%2C+pp%2E+159%E2%80%93161%2C+1999%2E) 7. R. Le Nagard and P. Koehn, “Aiding pronoun translation with co-reference resolution,” in Proceedings of Proceedings of the 7 th International Workshop on Spoken Language Translation Paris, December 2nd and 3rd, 2010 the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR. Uppsala… [find](https://scholar.google.com/scholar?q=R%2E+Le+Nagard+and+P%2E+Koehn%2C+%E2%80%9CAiding+pronoun+translation+with+co%2Dreference+resolution%2C%E2%80%9D+in+Proceedings+of+Proceedings+of+the+7+th+International+Workshop+on+Spoken+Language+Translation+Paris%2C+December+2n) [our card](https://md.research.elamur.ai/free/papers/nagard-2010-aiding-pronoun-translation-co-reference/) 8. S. Broscheit, M. Poesio, S. P. Ponzetto, K. Joseba Rodriguez, L. Romano, O. Uryupina, Y. Versley, and R. Zanoli, “BART: A multilingual anaphora resolution system,” in Proceedings of the 5th International Workshop on Semantic Evaluations (SemEval-2010), Uppsala, Sweden, 15–16 July 2010, 2010. [find](https://scholar.google.com/scholar?q=S%2E+Broscheit%2C+M%2E+Poesio%2C+S%2E+P%2E+Ponzetto%2C+K%2E+Joseba+Rodriguez%2C+L%2E+Romano%2C+O%2E+Uryupina%2C+Y%2E+Versley%2C+and+R%2E+Zanoli%2C+%E2%80%9CBART%3A+A+multilingual+anaphora+resolution+system%2C%E2%80%9D+in+Proceedings+of+the+5th+Internatio) [our card](https://md.research.elamur.ai/free/papers/broscheit-2010-bart-multilingual-anaphora-resolution-system/) 9. P. Koehn, H. Hoang, A. Birch, et al., “Moses: open source toolkit for Statistical Machine Translation,” in Annual meeting of the Association for Computational Linguistics: Demonstration session, Prague, 2007, pp. 177–180. [find](https://scholar.google.com/scholar?q=P%2E+Koehn%2C+H%2E+Hoang%2C+A%2E+Birch%2C+et+al%2E%2C+%E2%80%9CMoses%3A+open+source+toolkit+for+Statistical+Machine+Translation%2C%E2%80%9D+in+Annual+meeting+of+the+Association+for+Computational+Linguistics%3A+Demonstration+session%2C+Pragu) 10. F. J. Och and H. Ney, “Discriminative training and maximum entropy models for Statistical Machine Translation,” in Proceedings of the 40th annual meeting of the Association for Computational Linguistics, Philadelphia, 2002, pp. 295–302. [find](https://scholar.google.com/scholar?q=F%2E+J%2E+Och+and+H%2E+Ney%2C+%E2%80%9CDiscriminative+training+and+maximum+entropy+models+for+Statistical+Machine+Translation%2C%E2%80%9D+in+Proceedings+of+the+40th+annual+meeting+of+the+Association+for+Computational+Linguisti) [our card](https://md.research.elamur.ai/free/papers/och-2002-discriminative-training-maximum-entropy-models/) 11. F. J. Och, N. Ueffing, and H. Ney, “An efficient A* search algorithm for Statistical Machine Translation,” in Proceedings of the Data-Driven Machine Translation Workshop, 39th Annual Meeting of the Association for Computational Linguistics (ACL), Toulouse, 2001, pp. 55–62. [find](https://scholar.google.com/scholar?q=F%2E+J%2E+Och%2C+N%2E+Ueffing%2C+and+H%2E+Ney%2C+%E2%80%9CAn+efficient+A%2A+search+algorithm+for+Statistical+Machine+Translation%2C%E2%80%9D+in+Proceedings+of+the+Data%2DDriven+Machine+Translation+Workshop%2C+39th+Annual+Meeting+of+the+As) 12. I. H. Witten and T. C. Bell, “The zero-frequency problem: Estimating probabilities of novel events in adaptive text compression,” IEEE Transactions on Information Theory, vol. 37, pp. 1085–1094, 1991. [find](https://scholar.google.com/scholar?q=I%2E+H%2E+Witten+and+T%2E+C%2E+Bell%2C+%E2%80%9CThe+zero%2Dfrequency+problem%3A+Estimating+probabilities+of+novel+events+in+adaptive+text+compression%2C%E2%80%9D+IEEE+Transactions+on+Information+Theory%2C+vol%2E+37%2C+pp%2E+1085%E2%80%931094%2C+1991%2E) 13. F. J. Och and H. Ney, “A systematic comparison of various statistical alignment models,” Computational linguistics, vol. 29, pp. 19–51, 2003. [find](https://scholar.google.com/scholar?q=F%2E+J%2E+Och+and+H%2E+Ney%2C+%E2%80%9CA+systematic+comparison+of+various+statistical+alignment+models%2C%E2%80%9D+Computational+linguistics%2C+vol%2E+29%2C+pp%2E+19%E2%80%9351%2C+2003%2E) 14. K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu, “BLEU: a method for automatic evaluation of Machine Translation,” in Proceedings of the 40th annual meeting of the Association for Computational Linguistics. Philadelphia: ACL, 2002, pp. 311–318. [find](https://scholar.google.com/scholar?q=K%2E+Papineni%2C+S%2E+Roukos%2C+T%2E+Ward%2C+and+W%2E%2DJ%2E+Zhu%2C+%E2%80%9CBLEU%3A+a+method+for+automatic+evaluation+of+Machine+Translation%2C%E2%80%9D+in+Proceedings+of+the+40th+annual+meeting+of+the+Association+for+Computational+Linguis) [our card](https://md.research.elamur.ai/free/papers/papineni-2002-bleu-method-automatic-evaluation-machine/) 15. M. Federico, N. Bertoldi, and M. Cettolo, “IRSTLM: an open source toolkit for handling large scale language models,” in Interspeech 2008. ISCA, 2008, pp. 1618– 1621. [find](https://scholar.google.com/scholar?q=M%2E+Federico%2C+N%2E+Bertoldi%2C+and+M%2E+Cettolo%2C+%E2%80%9CIRSTLM%3A+an+open+source+toolkit+for+handling+large+scale+language+models%2C%E2%80%9D+in+Interspeech+2008%2E+ISCA%2C+2008%2C+pp%2E+1618%E2%80%93+1621%2E)