---
title: "FrameNet Translation Using Bilingual — Mouton 2010"
description: "Semantic Role Labeling depends on lexical resources such as FrameNet, which exist mostly for English."
authors: ["Claire Mouton", "Gaël de Chalendar", "Benoit Richert"]
year: 2010
venue: "Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)"
source: "https://aclanthology.org/L10-1336/"
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/mouton-2010-framenet-translation-bilingual-dictionaries-evaluation/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/mouton-2010-framenet-translation-bilingual-dictionaries-evaluation/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2010](https://md.research.elamur.ai/free/papers/2010/) / FrameNet Translation Using Bilingual Dictionaries with Evaluation on the English-French Pair

# FrameNet Translation Using Bilingual Dictionaries with Evaluation on the English-French Pair

**Authors:** Claire Mouton, [Gaël de Chalendar](https://md.research.elamur.ai/free/authors/gael-de-chalendar/), Benoit Richert · **Year:** 2010 · **Venue:** Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10) · **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/L10-1336/) · [PDF](https://aclanthology.org/L10-1336.pdf) · [OpenAlex](https://openalex.org/W15009557)

**Citations:** 8 citations (openalex-snapshot · 2026-10-14) · [4](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Semantic Role Labeling depends on lexical resources such as FrameNet, which exist mostly for English. French had little, and the prior automatic French FrameNet (FrameNet.Fr, by Padó and Pitel) was built by projecting annotations through aligned parallel corpora. The authors instead translate FrameNet lexical units (LUs) with bilingual dictionaries: the collaborative Wiktionary (French and English editions) and SCI-FRAN-EuRADic, distributed by ELDA. The frame structure is kept as is.

Because English polysemy produces many wrong LU-frame assignments, they define six filtering scores. These draw on translation redundancy, Wiktionary sense distinctions, and properties of FrameNet such as how many frames a source word belongs to and how large a frame is.

They also add nouns that have no English counterpart in FrameNet. For this they use a multi-represented k-NN classifier over semantic spaces built from syntactic dependencies.

Evaluated on ten French frames, the dictionary-based resources beat FrameNet.Fr in both size and precision. The method requires only bilingual dictionaries, so it could in principle be applied to other languages.

## Key points
- Before filtering, Wiktionary produced 19,912 French LU-frame pairs from 27,109 translation pairs, and EuRADic produced 57,787.
- Filtering yields two kinds of resource:
  - a high-precision version (about 95% accuracy, around 58% of Berkeley FrameNet's size);
  - a balanced version (F0.5 = 67%, 34,121 LU-frame pairs, nearly three times FrameNet's LU count).
- Intersecting the Wiktionary and EuRADic outputs gives a resource twice the size of FrameNet.Fr, with 82% precision versus 77%.
- The noun enrichment (EFN.1) contributed 7,581 new LU-frame attributions.
- The final combined resource has 15,132 LU-frame pairs with an estimated precision of 86%.

*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/) · [Machine translation](https://md.research.elamur.ai/free/shelves/machine-translation/)

Topics: [Semantic role labeling](https://md.research.elamur.ai/free/topics/semantic-role-labeling/)

## Cited by

Cited by

4 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 2 not yet.

- [Developing a French FrameNet: Methodology and First results](https://md.research.elamur.ai/free/papers/candito-2014-developing-french-framenet-methodology-first/)
- [FrameNet on the Way to Babel: Creating a Bilingual FrameNet Using Wiktionary as Interlingual Connection](https://md.research.elamur.ai/free/papers/hartmann-2013-framenet-way-babel-creating-bilingual/)

## Cite

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

```bibtex
@inproceedings{mouton2010framenet,
  title = {{FrameNet Translation Using Bilingual Dictionaries with Evaluation on the English-French Pair}},
  author = {Mouton, Claire and Chalendar, Gaël de and Richert, Benoit},
  booktitle = {Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)},
  year = {2010},
  doi = {10.63317/52bn2e87kt5q},
  url = {https://doi.org/10.63317/52bn2e87kt5q}
}
```

- [← previous Fine-Grain Morphological Analyzer and Part-of-Speech Tagger for Arabic Text](https://md.research.elamur.ai/free/papers/lingbulk-2010-sawalha-fine-grain-morphological-analyzer-part/)
- [next → Generating Entailment Rules from FrameNet](https://md.research.elamur.ai/free/papers/aharon-2010-generating-entailment-rules-framenet/)
- [↑ back to papers of 2010](https://md.research.elamur.ai/free/papers/2010/)

## References

13 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Collin F. Baker, Charles J. Fillmore, and John B. Lowe. 1998. The berkeley framenet project. In Proceedings of the COLING-ACL, pages 86–90. [find](https://scholar.google.com/scholar?q=Collin+F%2E+Baker%2C+Charles+J%2E+Fillmore%2C+and+John+B%2E+Lowe%2E+1998%2E+The+berkeley+framenet+project%2E+In+Proceedings+of+the+COLING%2DACL%2C+pages+86%E2%80%9390%2E) [our card](https://md.research.elamur.ai/free/papers/lex-1998-baker-berkeley-framenet/)
2. Romaric Besançon and Gaël de Chalendar. 2005. L’analyseur syntaxique de lima dans la campagne d’évaluation easy. In Proceedings of TALN 05. [find](https://scholar.google.com/scholar?q=Romaric+Besanc%CC%A7on+and+Gae%CC%88l+de+Chalendar%2E+2005%2E+L%E2%80%99analyseur+syntaxique+de+lima+dans+la+campagne+d%E2%80%99e%CC%81valuation+easy%2E+In+Proceedings+of+TALN+05%2E)
3. Ana Fernandez, Gloria Vazquez, Patrick Saint-Dizier, Farah Benamara, and Mouna Kamel. 2002. The VOLEM project: a framework for the construction of advanced multilingual lexicons. In Proc. of the Language Engineering Conference., pages 89–98. [find](https://scholar.google.com/scholar?q=Ana+Fernandez%2C+Gloria+Vazquez%2C+Patrick+Saint%2DDizier%2C+Farah+Benamara%2C+and+Mouna+Kamel%2E+2002%2E+The+VOLEM+project%3A+a+framework+for+the+construction+of+advanced+multilingual+lexicons%2E+In+Proc%2E+of+the+Langu)
4. Charles J. Fillmore. 2006. Frame semantics. Cognitive Linguistics: Basic Readings, pages 185–238. [find](https://scholar.google.com/scholar?q=Charles+J%2E+Fillmore%2E+2006%2E+Frame+semantics%2E+Cognitive+Linguistics%3A+Basic+Readings%2C+pages+185%E2%80%93238%2E)
5. Gregory Grefenstette. 2007. Conquering language : Using nlp on a massive scale to build high dimensional language models from the web. In Proc. of the 8th CICLing Conference, pages 35–49, Mexico. [find](https://scholar.google.com/scholar?q=Gregory+Grefenstette%2E+2007%2E+Conquering+language+%3A+Using+nlp+on+a+massive+scale+to+build+high+dimensional+language+models+from+the+web%2E+In+Proc%2E+of+the+8th+CICLing+Conference%2C+pages+35%E2%80%9349%2C+Mexico%2E)
6. Paul Kingsbury and Martha Palmer. 2002. From treebank to propbank. In Proceedings of the 3rd International Conference on Language Resources and Evaluation (LREC-2002), pages 1989–1993. [find](https://scholar.google.com/scholar?q=Paul+Kingsbury+and+Martha+Palmer%2E+2002%2E+From+treebank+to+propbank%2E+In+Proceedings+of+the+3rd+International+Conference+on+Language+Resources+and+Evaluation+%28LREC%2D2002%29%2C+pages+1989%E2%80%931993%2E) [our card](https://md.research.elamur.ai/free/papers/kingsbury-2002-treebank-propbank/)
7. Hans-Peter Kriegel, Alexey Pryakhin, and Matthias Schubert, 2005. Database Systems for Advanced Applications, chapter Multi-represented kNN-Classification for Large Class Sets. Springer Berlin / Heidelberg. [find](https://scholar.google.com/scholar?q=Hans%2DPeter+Kriegel%2C+Alexey+Pryakhin%2C+and+Matthias+Schubert%2C+2005%2E+Database+Systems+for+Advanced+Applications%2C+chapter+Multi%2Drepresented+kNN%2DClassification+for+Large+Class+Sets%2E+Springer+Berlin+%2F+Heide)
8. Claire Mouton, Guillaume Pitel, Gaël de Chalendar, and Anne Vilnat. 2009. Unsupervised word sense induction from multiple semantic spaces with locality sensitive hashing. In Proceedings of RANLP 2009, Borovets, Bulgaria, September. [find](https://scholar.google.com/scholar?q=Claire+Mouton%2C+Guillaume+Pitel%2C+Gae%CC%88l+de+Chalendar%2C+and+Anne+Vilnat%2E+2009%2E+Unsupervised+word+sense+induction+from+multiple+semantic+spaces+with+locality+sensitive+hashing%2E+In+Proceedings+of+RANLP+2009)
9. Sebastian Padó and Mirella Lapata. 2005. Cross-lingual bootstrapping for semantic lexicons: The case of framenet. In Proceedings of AAAI-05, pages 1087–1092, Pittsburgh, PA. [find](https://scholar.google.com/scholar?q=Sebastian+Pado%CC%81+and+Mirella+Lapata%2E+2005%2E+Cross%2Dlingual+bootstrapping+for+semantic+lexicons%3A+The+case+of+framenet%2E+In+Proceedings+of+AAAI%2D05%2C+pages+1087%E2%80%931092%2C+Pittsburgh%2C+PA%2E)
10. Sebastian Padó and Guillaume Pitel. 2007. Annotation précise du français en sémantique de rôles par projection cross-linguistique. In Actes de la 14e conférence sur le Traitement Automatique des Langues Naturelles, page 271. [find](https://scholar.google.com/scholar?q=Sebastian+Pado%CC%81+and+Guillaume+Pitel%2E+2007%2E+Annotation+pre%CC%81cise+du+franc%CC%A7ais+en+se%CC%81mantique+de+ro%CC%82les+par+projection+cross%2Dlinguistique%2E+In+Actes+de+la+14e+confe%CC%81rence+sur+le+Traitement+Automatique+des)
11. Marco Pennacchiotti, Diego De Cao, Roberto Basili, Danilo Croce, and Michael Roth. 2008. Automatic induction of FrameNet lexical units. In Proceedings of Empirical Methods in Natural Language Processing (EMNLP), Honolulu, Hawaii, USA. [find](https://scholar.google.com/scholar?q=Marco+Pennacchiotti%2C+Diego+De+Cao%2C+Roberto+Basili%2C+Danilo+Croce%2C+and+Michael+Roth%2E+2008%2E+Automatic+induction+of+FrameNet+lexical+units%2E+In+Proceedings+of+Empirical+Methods+in+Natural+Language+Processi) [our card](https://md.research.elamur.ai/free/papers/pennacchiotti-2008-automatic-induction-framenet-lexical-units/)
12. Benoı̂t Sagot and Darja Fišer. 2008. Combining multiple resources to build reliable wordnets. In Proceedings of the 11th international conference on Text, Speech and Dialogue, pages 61 – 68, Brno, Czech Republic. [find](https://scholar.google.com/scholar?q=Beno%C4%B1%CC%82t+Sagot+and+Darja+Fis%CC%8Cer%2E+2008%2E+Combining+multiple+resources+to+build+reliable+wordnets%2E+In+Proceedings+of+the+11th+international+conference+on+Text%2C+Speech+and+Dialogue%2C+pages+61+%E2%80%93+68%2C+Brno%2C+Cz)
13. Karin Kipper Schuler. 2005. VerbNet: A broad-coverage, comprehensive verb lexicon. Univ. of Pennsylvania-Electronic Dissertations. [↗](https://doi.org/10.5281/zenodo.8100881)