---
title: "Latent Anaphora Resolution for — Hardmeier 2013"
description: "The paper defines cross-lingual pronoun prediction as a task."
authors: ["Christian Hardmeier", "Jörg Tiedemann", "Joakim Nivre"]
year: 2013
venue: "Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/D13-1037/"
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-2013-latent-anaphora-resolution-cross-lingual/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/hardmeier-2013-latent-anaphora-resolution-cross-lingual/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2013](https://md.research.elamur.ai/free/papers/2013/) / Latent Anaphora Resolution for Cross-Lingual Pronoun Prediction

# Latent Anaphora Resolution for Cross-Lingual Pronoun Prediction

**Authors:** [Christian Hardmeier](https://md.research.elamur.ai/free/authors/christian-hardmeier/), [Jörg Tiedemann](https://md.research.elamur.ai/free/authors/jorg-tiedemann/), [Joakim Nivre](https://md.research.elamur.ai/free/authors/joakim-nivre/) · **Year:** 2013 · **Venue:** Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · **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/D13-1037/) · [PDF](https://aclanthology.org/D13-1037.pdf) · [OpenAlex](https://openalex.org/W2101951467)

**Citations:** 35 citations (openalex-snapshot · 2026-10-14) · [23](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
The paper defines cross-lingual pronoun prediction as a task. The input is an English text containing one of the subject pronouns he, she, it or they, its human French translation, and automatic GIZA++ word alignments. The system must predict which French word the pronoun is aligned to. The correct French form often depends on the gender and number of the antecedent, so the task implicitly requires anaphora resolution. It also matters for how SMT systems handle pronouns.

The authors first build a pipeline: the BART toolkit resolves English anaphora, and a classifier uses the local context plus the French words aligned to antecedent candidates. A neural network outperforms a maximum-entropy baseline, especially on rare classes.

They then let the network infer anaphoric links itself as latent variables, trained with backpropagation on word-aligned parallel text only. This model performs about as well as, or slightly better than, the BART-based pipeline, without any coreference-annotated training data. The result shows that bitexts can act as indirect supervision for learning pronominal anaphora, which is valuable for languages without coreference resources.

## Key points
- There are six output classes: il, elle, ils, elles, ce/c', and OTHER. OTHER dominates the data, at 40.9% in TED and 38.0% in News.
- Two data sets were used:
  - TED subtitles from WIT 3: about 2.6M tokens, split into 63,228 training and 7,824 test examples.
  - News-commentary v6 from the WMT 2011 data: about 2.8M tokens, split into 27,900 training and 3,117 test examples.
- The MegaM maximum-entropy baseline used BART links, with a ranker trained on ACE02-npaper.
  - It reached 0.685 accuracy on TED and 0.576 on News.
  - Recall for elles was only 0.164 on TED and 0.062 on News.
  - A neural network with the same BART links reached 0.700 on TED and 0.576 on News, raising the elles F-score to 0.434 and 0.193.
- The authors treat elles as a benchmark class because it is rare (1,909 TED and 1,077 News training occurrences) and cannot be predicted without knowing the antecedent. The final latent-anaphora model achieves nearly balanced precision and recall on it.
- The final system adds two extensions: morphological features looked up in the Lefff dictionary, and extra BART features covering finer-grained distance measures and head part of speech.

*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/)

## Cited by

Cited by

23 papers of our library cite it (of the 140673 whose bibliographies we read); 4 of them have a page here, 19 not yet.

- [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/)
- [Anaphora Models and Reordering for Phrase-Based SMT](https://md.research.elamur.ai/free/papers/hardmeier-2014-anaphora-models-reordering-phrase-based/)
- [Transferring Coreference Resolvers with Posterior Regularization](https://md.research.elamur.ai/free/papers/martins-2015-transferring-coreference-resolvers-posterior-regularization/)
- [Context-Aware Neural Machine Translation Learns Anaphora Resolution](https://md.research.elamur.ai/free/papers/voita-2018-context-aware-neural-machine-translation/)

## Cite

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

```bibtex
@inproceedings{hardmeier2013latent,
  title = {{Latent Anaphora Resolution for Cross-Lingual Pronoun Prediction}},
  author = {Hardmeier, Christian and Tiedemann, Jörg and Nivre, Joakim},
  booktitle = {Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing},
  year = {2013},
  doi = {10.18653/v1/d13-1037},
  url = {https://doi.org/10.18653/v1/d13-1037}
}
```

- [← previous Joint Coreference Resolution and Named-Entity Linking with Multi-Pass Sieves](https://md.research.elamur.ai/free/papers/hajishirzi-2013-joint-coreference-resolution-named-entity/)
- [next → Learning Latent Personas of Film Characters](https://md.research.elamur.ai/free/papers/bamman-2013-learning-latent-personas-film-characters/)
- [↑ back to papers of 2013](https://md.research.elamur.ai/free/papers/2013/)

## References

24 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Yoshua Bengio, Réjean Ducharme, Pascal Vincent, and Christian Janvin. 2003. A neural probabilistic language model. Journal of Machine Learning Research, 3:1137–1155. [find](https://scholar.google.com/scholar?q=Yoshua+Bengio%2C+R%C3%A9jean+Ducharme%2C+Pascal+Vincent%2C+and+Christian+Janvin%2E+2003%2E+A+neural+probabilistic+language+model%2E+Journal+of+Machine+Learning+Research%2C+3%3A1137%E2%80%931155%2E)
2. Samuel Broscheit, Massimo Poesio, Simone Paolo Ponzetto, Kepa Joseba Rodriguez, Lorenza Romano, Olga Uryupina, Yannick Versley, and Roberto Zanoli. 2010. BART: A multilingual anaphora resolution system. In Proceedings of the 5th International Workshop on Semantic Evaluations (SemEval-2010), Uppsala,… [find](https://scholar.google.com/scholar?q=Samuel+Broscheit%2C+Massimo+Poesio%2C+Simone+Paolo+Ponzetto%2C+Kepa+Joseba+Rodriguez%2C+Lorenza+Romano%2C+Olga+Uryupina%2C+Yannick+Versley%2C+and+Roberto+Zanoli%2E+2010%2E+BART%3A+A+multilingual+anaphora+resolution+syste) [our card](https://md.research.elamur.ai/free/papers/broscheit-2010-bart-multilingual-anaphora-resolution-system/)
3. Mauro Cettolo, Christian Girardi, and Marcello Federico. 2012. WIT 3 : Web inventory of transcribed and translated talks. In Proceedings of the 16th Conference of the European Association for Machine Translation (EAMT), pages 261–268, Trento, Italy. [find](https://scholar.google.com/scholar?q=Mauro+Cettolo%2C+Christian+Girardi%2C+and+Marcello+Federico%2E+2012%2E+WIT+3+%3A+Web+inventory+of+transcribed+and+translated+talks%2E+In+Proceedings+of+the+16th+Conference+of+the+European+Association+for+Machine+)
4. Eugene Charniak and Micha Elsner. 2009. EM works for pronoun anaphora resolution. In Proceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009), pages 148–156, Athens, Greece. [find](https://scholar.google.com/scholar?q=Eugene+Charniak+and+Micha+Elsner%2E+2009%2E+EM+works+for+pronoun+anaphora+resolution%2E+In+Proceedings+of+the+12th+Conference+of+the+European+Chapter+of+the+ACL+%28EACL+2009%29%2C+pages+148%E2%80%93156%2C+Athens%2C+Greece%2E) [our card](https://md.research.elamur.ai/free/papers/charniak-2009-em-works-pronoun-anaphora-resolution/)
5. Colin Cherry and Shane Bergsma. 2005. An Expectation Maximization approach to pronoun resolution. In Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005), pages 88– 95, Ann Arbor, Michigan. [find](https://scholar.google.com/scholar?q=Colin+Cherry+and+Shane+Bergsma%2E+2005%2E+An+Expectation+Maximization+approach+to+pronoun+resolution%2E+In+Proceedings+of+the+Ninth+Conference+on+Computational+Natural+Language+Learning+%28CoNLL%2D2005%29%2C+pages+) [our card](https://md.research.elamur.ai/free/papers/cherry-2005-expectation-maximization-approach-pronoun-resolution/)
6. Michael Collins. 1999. Head-Driven Statistical Models for Natural Language Parsing. Ph.D. thesis, University of Pennsylvania. [find](https://scholar.google.com/scholar?q=Michael+Collins%2E+1999%2E+Head%2DDriven+Statistical+Models+for+Natural+Language+Parsing%2E+Ph%2ED%2E+thesis%2C+University+of+Pennsylvania%2E)
7. Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. Natural language processing (almost) from scratch. Journal of Machine Learning Research, 12:2461–2505. [find](https://scholar.google.com/scholar?q=Ronan+Collobert%2C+Jason+Weston%2C+L%C3%A9on+Bottou%2C+Michael+Karlen%2C+Koray+Kavukcuoglu%2C+and+Pavel+Kuksa%2E+2011%2E+Natural+language+processing+%28almost%29+from+scratch%2E+Journal+of+Machine+Learning+Research%2C+12%3A2461%E2%80%932) [our card](https://md.research.elamur.ai/free/papers/collobert-2011-natural-language-processing-almost-scratch/)
8. José de Souza and Constantin Orăsan. 2011. Can projected chains in parallel corpora help coreference resolution? In Iris Hendrickx, Sobha Lalitha Devi, António Branco, and Ruslan Mitkov, editors, Anaphora Processing and Applications, volume 7099 of Lecture Notes in Computer Science, pages 59–69. Sp… [find](https://scholar.google.com/scholar?q=Jos%C3%A9+de+Souza+and+Constantin+Ora%CC%86san%2E+2011%2E+Can+projected+chains+in+parallel+corpora+help+coreference+resolution%3F+In+Iris+Hendrickx%2C+Sobha+Lalitha+Devi%2C+Ant%C3%B3nio+Branco%2C+and+Ruslan+Mitkov%2C+editors%2C+Ana)
9. Liane Guillou. 2012. Improving pronoun translation for statistical machine translation. In Proceedings of the Student Research Workshop at the 13th Conference of the European Chapter of the Association for Computational Linguistics, pages 1–10, Avignon, France. [find](https://scholar.google.com/scholar?q=Liane+Guillou%2E+2012%2E+Improving+pronoun+translation+for+statistical+machine+translation%2E+In+Proceedings+of+the+Student+Research+Workshop+at+the+13th+Conference+of+the+European+Chapter+of+the+Associatio)
10. Christian Hardmeier and Marcello Federico. 2010. Modelling pronominal anaphora in statistical machine translation. In Proceedings of the seventh International Workshop on Spoken Language Translation (IWSLT), pages 283–289, Paris, France. [find](https://scholar.google.com/scholar?q=Christian+Hardmeier+and+Marcello+Federico%2E+2010%2E+Modelling+pronominal+anaphora+in+statistical+machine+translation%2E+In+Proceedings+of+the+seventh+International+Workshop+on+Spoken+Language+Translation+%28) [our card](https://md.research.elamur.ai/free/papers/hardmeier-2010-modelling-pronominal-anaphora-statistical-machine/)
11. Christian Hardmeier. 2012. Discourse in statistical machine translation: A survey and a case study. Discours, 11. [find](https://scholar.google.com/scholar?q=Christian+Hardmeier%2E+2012%2E+Discourse+in+statistical+machine+translation%3A+A+survey+and+a+case+study%2E+Discours%2C+11%2E)
12. Dan Klein and Christopher D. Manning. 2003. Accurate unlexicalized parsing. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pages 423–430, Sapporo, Japan. [find](https://scholar.google.com/scholar?q=Dan+Klein+and+Christopher+D%2E+Manning%2E+2003%2E+Accurate+unlexicalized+parsing%2E+In+Proceedings+of+the+41st+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+423%E2%80%93430%2C+Sapporo%2C+Japan%2E) [our card](https://md.research.elamur.ai/free/papers/aclbulk-2003-klein-accurate-unlexicalized-parsing/)
13. Hai-Son Le, Alexandre Allauzen, and François Yvon. 2012. Continuous space translation models with neural networks. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 39–48, Montréal, Canada. [find](https://scholar.google.com/scholar?q=Hai%2DSon+Le%2C+Alexandre+Allauzen%2C+and+Fran%C3%A7ois+Yvon%2E+2012%2E+Continuous+space+translation+models+with+neural+networks%2E+In+Proceedings+of+the+2012+Conference+of+the+North+American+Chapter+of+the+Associatio)
14. Ronan Le Nagard and Philipp Koehn. 2010. Aiding pronoun translation with co-reference resolution. In Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, pages 252–261, Uppsala, Sweden. [find](https://scholar.google.com/scholar?q=Ronan+Le+Nagard+and+Philipp+Koehn%2E+2010%2E+Aiding+pronoun+translation+with+co%2Dreference+resolution%2E+In+Proceedings+of+the+Joint+Fifth+Workshop+on+Statistical+Machine+Translation+and+MetricsMATR%2C+pages+2) [our card](https://md.research.elamur.ai/free/papers/nagard-2010-aiding-pronoun-translation-co-reference/)
15. Ruslan Mitkov and Catalina Barbu. 2003. Using bilingual corpora to improve pronoun resolution. Languages in Contrast, 4(2):201–211. [find](https://scholar.google.com/scholar?q=Ruslan+Mitkov+and+Catalina+Barbu%2E+2003%2E+Using+bilingual+corpora+to+improve+pronoun+resolution%2E+Languages+in+Contrast%2C+4%282%29%3A201%E2%80%93211%2E)
16. Franz Josef Och and Hermann Ney. 2003. A systematic comparison of various statistical alignment models. Computational linguistics, 29:19–51. [find](https://scholar.google.com/scholar?q=Franz+Josef+Och+and+Hermann+Ney%2E+2003%2E+A+systematic+comparison+of+various+statistical+alignment+models%2E+Computational+linguistics%2C+29%3A19%E2%80%9351%2E)
17. Hoifung Poon and Pedro Domingos. 2008. Joint unsupervised coreference resolution with Markov Logic. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 650– 659, Honolulu, Hawaii. [find](https://scholar.google.com/scholar?q=Hoifung+Poon+and+Pedro+Domingos%2E+2008%2E+Joint+unsupervised+coreference+resolution+with+Markov+Logic%2E+In+Proceedings+of+the+2008+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+650) [our card](https://md.research.elamur.ai/free/papers/poon-2008-joint-unsupervised-coreference-resolution-markov/)
18. Oana Postolache, Dan Cristea, and Constantin Orăsan. 2006. Transferring coreference chains through word alignment. In Proceedings of the 5th Conference on International Language Resources and Evaluation (LREC-2006), pages 889–892, Genoa. [find](https://scholar.google.com/scholar?q=Oana+Postolache%2C+Dan+Cristea%2C+and+Constantin+Ora%CC%86san%2E+2006%2E+Transferring+coreference+chains+through+word+alignment%2E+In+Proceedings+of+the+5th+Conference+on+International+Language+Resources+and+Evaluat) [our card](https://md.research.elamur.ai/free/papers/postolache-2006-transferring-coreference-chains-through-word/)
19. Altaf Rahman and Vincent Ng. 2012. Translation-based projection for multilingual coreference resolution. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 720– 730, Montréal, Canada. [find](https://scholar.google.com/scholar?q=Altaf+Rahman+and+Vincent+Ng%2E+2012%2E+Translation%2Dbased+projection+for+multilingual+coreference+resolution%2E+In+Proceedings+of+the+2012+Conference+of+the+North+American+Chapter+of+the+Association+for+Comp) [our card](https://md.research.elamur.ai/free/papers/rahman-2012-translation-based-projection-multilingual-coreference/)
20. Benoît Sagot, Lionel Clément, Éric Villemonte de La Clergerie, and Pierre Boullier. 2006. The Lefff 2 syntactic lexicon for French: architecture, acquisition, use. In Proceedings of the 5th Conference on International Language Resources and Evaluation (LREC-2006), pages 1348–1351, Genoa. [find](https://scholar.google.com/scholar?q=Beno%C3%AEt+Sagot%2C+Lionel+Cl%C3%A9ment%2C+%C3%89ric+Villemonte+de+La+Clergerie%2C+and+Pierre+Boullier%2E+2006%2E+The+Lefff+2+syntactic+lexicon+for+French%3A+architecture%2C+acquisition%2C+use%2E+In+Proceedings+of+the+5th+Conference)
21. Holger Schwenk. 2007. Continuous space language models. Computer Speech and Language, 21(3):492–518. [find](https://scholar.google.com/scholar?q=Holger+Schwenk%2E+2007%2E+Continuous+space+language+models%2E+Computer+Speech+and+Language%2C+21%283%29%3A492%E2%80%93518%2E)
22. Wee Meng Soon, Hwee Tou Ng, and Daniel Chung Yong Lim. 2001. A machine learning approach to coreference resolution of noun phrases. Computational linguistics, 27(4):521–544. [find](https://scholar.google.com/scholar?q=Wee+Meng+Soon%2C+Hwee+Tou+Ng%2C+and+Daniel+Chung+Yong+Lim%2E+2001%2E+A+machine+learning+approach+to+coreference+resolution+of+noun+phrases%2E+Computational+linguistics%2C+27%284%29%3A521%E2%80%93544%2E) [our card](https://md.research.elamur.ai/free/papers/soon-2001-machine-learning-approach-coreference-resolution/)
23. Roland Stuckardt. 2007. Applying backpropagation networks to anaphor resolution. In António Branco, editor, Anaphora: Analysis, Algorithms and Applications. 6th Discourse Anaphora and Anaphor Resolution Colloquium, DAARC 2007, number 4410 in Lecture Notes in Artificial Intelligence, pages 107–124, B… [find](https://scholar.google.com/scholar?q=Roland+Stuckardt%2E+2007%2E+Applying+backpropagation+networks+to+anaphor+resolution%2E+In+Ant%C3%B3nio+Branco%2C+editor%2C+Anaphora%3A+Analysis%2C+Algorithms+and+Applications%2E+6th+Discourse+Anaphora+and+Anaphor+Resoluti)
24. Kateřina Veselovská, Ngu.y Giang Linh, and Michal Novák. 2012. Using Czech-English parallel corpora in automatic identification of it. In Proceedings of the 5th Workshop on Building and Using Comparable Corpora, pages 112–120, Istanbul, Turkey. [find](https://scholar.google.com/scholar?q=Kater%CC%8Cina+Veselovsk%C3%A1%2C+Ngu%2Ey+Giang+Linh%2C+and+Michal+Nov%C3%A1k%2E+2012%2E+Using+Czech%2DEnglish+parallel+corpora+in+automatic+identification+of+it%2E+In+Proceedings+of+the+5th+Workshop+on+Building+and+Using+Compara)