---
title: "Using Sense-labeled Discourse Connectives for — Meyer 2012"
description: "Phrase-based SMT systems often mistranslate discourse connectives such as since , while or though."
authors: ["Thomas Meyer", "Andrei Popescu-Belis"]
year: 2012
venue: "Proceedings of the Joint Workshop on Exploiting Synergies between Information Retrieval and Machine Translation (ESIRMT) and Hybrid Approaches to Machine Translation (HyTra)"
source: "https://aclanthology.org/W12-0117/"
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/meyer-2012-sense-labeled-discourse-connectives-statistical/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/meyer-2012-sense-labeled-discourse-connectives-statistical/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2012](https://md.research.elamur.ai/free/papers/2012/page/2/) / Using Sense-labeled Discourse Connectives for Statistical Machine Translation

# Using Sense-labeled Discourse Connectives for Statistical Machine Translation

**Authors:** [Thomas Meyer](https://md.research.elamur.ai/free/authors/thomas-meyer/), [Andrei Popescu-Belis](https://md.research.elamur.ai/free/authors/andrei-popescu-belis/) · **Year:** 2012 · **Venue:** Proceedings of the Joint Workshop on Exploiting Synergies between Information Retrieval and Machine Translation (ESIRMT) and Hybrid Approaches to Machine Translation (HyTra) · **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/W12-0117/) · [PDF](https://aclanthology.org/W12-0117.pdf) · [OpenAlex](https://openalex.org/W112038384)

**Citations:** 59 citations (openalex-snapshot · 2026-10-14) · [34](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Phrase-based SMT systems often mistranslate discourse connectives such as *since*, *while* or *though*. The correct target-language word depends on which discourse relation (contrast, concession, cause, time, etc.) the connective signals in its context. The authors test whether resolving this ambiguity before translation helps English-to-French SMT.

They first build one Maximum Entropy classifier per connective for 13 ambiguous English connectives, trained on Penn Discourse Treebank (PDTB) data using second-level sense labels. Features include syntactic information, WordNet relations, temporal expressions and candidate translations. The classifiers reach state-of-the-art F1 of about 0.6–0.8.

They then feed the sense labels into Moses in three ways:
- editing the phrase table,
- training on Europarl with hand-labeled connectives,
- training on Europarl with automatically labeled connectives.

The modified systems translate connectives more accurately without lowering BLEU. A combined system that applies labels only when the classifier is highly confident improves BLEU by 0.2–0.4 points. The authors describe this as the first attempt to join connective disambiguation and SMT, showing that discourse-level information can benefit translation.

## Key points
- **Disambiguation data:** PDTB (sections 02–21 for training, section 23 for testing). The 13 connectives covered are while, since, although, after, however, meanwhile, then, still, yet, indeed, rather, nevertheless and nonetheless.
- **Europarl annotation:** Five connectives (although, even though, since, though, while) were manually labeled on Europarl via translation spotting. Annotators marked each connective's French equivalent, and these equivalents were then grouped into sense labels.
- **SMT setup:** Moses phrase-based decoder with a 5-gram French language model built on Europarl v5 (346,803 training sentences). Systems were tuned with MERT on the News Commentary 2009 development set and tested on News Commentary and UN corpus sentences.
- **Evaluation:** Gains in connective translation were counted manually on small test sets of 35 and 62 sentences.
- **Threshold-based combination:** For *since*, a confidence threshold of 0.85 gave +0.39 BLEU (p = 0.005). For *although*, the difference had p = 0.12.

*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: [Discourse analysis](https://md.research.elamur.ai/free/topics/discourse-analysis/) · [Machine translation](https://md.research.elamur.ai/free/topics/machine-translation/)

## Cited by

Cited by

34 papers of our library cite it (of the 140673 whose bibliographies we read); 13 of them have a page here, 21 not yet.

- [Annotating the meaning of discourse connectives by looking at their translation: The translation-spotting technique](https://md.research.elamur.ai/free/papers/cartoni-2013-annotating-meaning-discourse-connectives-looking/)
- [Structured Dialogue Discourse Parsing](https://md.research.elamur.ai/free/papers/chi-2022-structured-dialogue-discourse-parsing/)
- [TransS-Driven Joint Learning Architecture for Implicit Discourse Relation Recognition](https://md.research.elamur.ai/free/papers/he-2020-transs-driven-joint-learning-architecture/)
- [Disambiguating Explicit Discourse Connectives without Oracles](https://md.research.elamur.ai/free/papers/johannsen-2013-disambiguating-explicit-discourse-connectives-without/)
- [Discourse Structure in Machine Translation Evaluation](https://md.research.elamur.ai/free/papers/joty-2017-discourse-structure-machine-translation-evaluation/)
- [New perspectives on cohesion and coherence: Implications for translation](https://md.research.elamur.ai/free/papers/kunz-2017-new-perspectives-cohesion-coherence/)
- [Cross-lingual Discourse Relation Analysis: A corpus study and a semi-supervised classification system](https://md.research.elamur.ai/free/papers/li-2014-cross-lingual-discourse-relation-analysis/)
- [Machine Translation of Labeled Discourse Connectives](https://md.research.elamur.ai/free/papers/meyer-2012-machine-translation-labeled-discourse-connectives/)
- [Machine Translation with Many Manually Labeled Discourse Connectives](https://md.research.elamur.ai/free/papers/meyer-2013-machine-translation-many-manually-labeled/)
- [Document-Level Neural Machine Translation with Hierarchical Attention Networks](https://md.research.elamur.ai/free/papers/miculicich-2018-document-level-neural-machine-translation/)
- [Exploring Joint Neural Model for Sentence Level Discourse Parsing and Sentiment Analysis](https://md.research.elamur.ai/free/papers/nejat-2017-exploring-joint-neural-model-sentence/)
- [Reflections on the Penn Discourse TreeBank, Comparable Corpora, and Complementary Annotation](https://md.research.elamur.ai/free/papers/prasad-2014-reflections-penn-discourse-treebank-comparable/)
- [A Stacking Gated Neural Architecture for Implicit Discourse Relation Classification](https://md.research.elamur.ai/free/papers/qin-2016-stacking-gated-neural-architecture-implicit/)

## Cite

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

```bibtex
@inproceedings{meyer2012using,
  title = {{Using Sense-labeled Discourse Connectives for Statistical Machine Translation}},
  author = {Meyer, Thomas and Popescu-Belis, Andrei},
  booktitle = {Proceedings of the Joint Workshop on Exploiting Synergies between Information Retrieval and Machine Translation (ESIRMT) and Hybrid Approaches to Machine Translation (HyTra)},
  year = {2012},
  url = {https://aclanthology.org/W12-0117/}
}
```

- [← previous Unsupervised Morphology Rivals Supervised Morphology for Arabic MT](https://md.research.elamur.ai/free/papers/aclbulk-2012-stallard-unsupervised-morphology-rivals-supervised-morphology/)
- [next → Using Syntactic Dependencies to Solve Coreferences](https://md.research.elamur.ai/free/papers/stamborg-2012-syntactic-dependencies-solve-coreferences/)
- [↑ back to papers of 2012](https://md.research.elamur.ai/free/papers/2012/page/2/)

## References

25 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Satanjeev Banerjee and Ted Pedersen. 2002. An Adapted Lesk Algorithm for Word Sense Disambiguation Using WordNet. In Alexander Gelbukh, editor, Computational Linguistics and Intelligent Text Processing, LNCS 2276, pages 117–171. Springer, Berlin/Heidelberg. [find](https://scholar.google.com/scholar?q=Satanjeev+Banerjee+and+Ted+Pedersen%2E+2002%2E+An+Adapted+Lesk+Algorithm+for+Word+Sense+Disambiguation+Using+WordNet%2E+In+Alexander+Gelbukh%2C+editor%2C+Computational+Linguistics+and+Intelligent+Text+Processin)
2. Marine Carpuat and Dekai Wu. 2007. Improving Statistical Machine Translation using Word Sense Disambiguation. Proc. of EMNLP-CoNLL, pages 61– 72, Prague. [find](https://scholar.google.com/scholar?q=Marine+Carpuat+and+Dekai+Wu%2E+2007%2E+Improving+Statistical+Machine+Translation+using+Word+Sense+Disambiguation%2E+Proc%2E+of+EMNLP%2DCoNLL%2C+pages+61%E2%80%93+72%2C+Prague%2E)
3. Bruno Cartoni, Sandrine Zufferey, Thomas Meyer, and Andrei Popescu-Belis. 2011. How Comparable are Parallel Corpora? Measuring the Distribution of General Vocabulary and Connectives. Proc. of the 4th Workshop on Building and Using Comparable Corpora (BUCC), pages 78–86, Portland, OR. [find](https://scholar.google.com/scholar?q=Bruno+Cartoni%2C+Sandrine+Zufferey%2C+Thomas+Meyer%2C+and+Andrei+Popescu%2DBelis%2E+2011%2E+How+Comparable+are+Parallel+Corpora%3F+Measuring+the+Distribution+of+General+Vocabulary+and+Connectives%2E+Proc%2E+of+the+4th+)
4. Pi-Chuan Chang, Dan Jurafsky, and Christopher D. Manning. 2009. Disambiguating ‘DE’ for Chinese-English Machine Translation. Proc. of the Fourth Workshop on Statistical Machine Translation at EACL-2009, Athens. [find](https://scholar.google.com/scholar?q=Pi%2DChuan+Chang%2C+Dan+Jurafsky%2C+and+Christopher+D%2E+Manning%2E+2009%2E+Disambiguating+%E2%80%98DE%E2%80%99+for+Chinese%2DEnglish+Machine+Translation%2E+Proc%2E+of+the+Fourth+Workshop+on+Statistical+Machine+Translation+at+EACL%2D200)
5. Eugene Charniak and Mark Johnson. 2005. Coarse-to-fine n-best Parsing and MaxEnt Discriminative Reranking. Proc. of the 43rd Annual Meeting of the ACL, pages 173–180, Ann Arbor, MI. [find](https://scholar.google.com/scholar?q=Eugene+Charniak+and+Mark+Johnson%2E+2005%2E+Coarse%2Dto%2Dfine+n%2Dbest+Parsing+and+MaxEnt+Discriminative+Reranking%2E+Proc%2E+of+the+43rd+Annual+Meeting+of+the+ACL%2C+pages+173%E2%80%93180%2C+Ann+Arbor%2C+MI%2E) [our card](https://md.research.elamur.ai/free/papers/narrative-2005-charniak-coarse-fine-n-best-parsing/)
6. Laurence Danlos and Charlotte Roze. 2011. Traduction (Automatique) des Connecteurs de Discours. Actes 18e Conférence sur le Traitement Automatique des Langues Naturelles (TALN), Montpellier. [find](https://scholar.google.com/scholar?q=Laurence+Danlos+and+Charlotte+Roze%2E+2011%2E+Traduction+%28Automatique%29+des+Connecteurs+de+Discours%2E+Actes+18e+Confe%CC%81rence+sur+le+Traitement+Automatique+des+Langues+Naturelles+%28TALN%29%2C+Montpellier%2E)
7. Robert Elwell and Jason Baldridge. 2008. Discourse Connective Argument Identification with Connective Specific Rankers. Proc. of the 2nd IEEE International Conference on Semantic Computing (ICSC), pages 198–205, Santa Clara, CA. [find](https://scholar.google.com/scholar?q=Robert+Elwell+and+Jason+Baldridge%2E+2008%2E+Discourse+Connective+Argument+Identification+with+Connective+Specific+Rankers%2E+Proc%2E+of+the+2nd+IEEE+International+Conference+on+Semantic+Computing+%28ICSC%29%2C+pag)
8. Hugo Hernault, Helmut Prendinger, David A. duVerle, and Mitsuru Ishizuka. 2010. HILDA: A Discourse Parser using Support Vector Machine classification. Dialogue and Discourse, 3(1):1–33. [find](https://scholar.google.com/scholar?q=Hugo+Hernault%2C+Helmut+Prendinger%2C+David+A%2E+duVerle%2C+and+Mitsuru+Ishizuka%2E+2010%2E+HILDA%3A+A+Discourse+Parser+using+Support+Vector+Machine+classification%2E+Dialogue+and+Discourse%2C+3%281%29%3A1%E2%80%9333%2E) [our card](https://md.research.elamur.ai/free/papers/hernault-2010-hilda-discourse-parser-support-vector/)
9. Philipp Koehn, et al. 2007. Moses: Open Source Toolkit for Statistical Machine Translation. Proc. of 45th Annual Meeting of the ACL, Demonstration Session, pages 177–180, Prague. [find](https://scholar.google.com/scholar?q=Philipp+Koehn%2C+et+al%2E+2007%2E+Moses%3A+Open+Source+Toolkit+for+Statistical+Machine+Translation%2E+Proc%2E+of+45th+Annual+Meeting+of+the+ACL%2C+Demonstration+Session%2C+pages+177%E2%80%93180%2C+Prague%2E)
10. Philipp Koehn. 2005. Europarl: A Parallel Corpus for Statistical Machine Translation. Proc. of MT Summit X, pages 79–86, Phuket. [find](https://scholar.google.com/scholar?q=Philipp+Koehn%2E+2005%2E+Europarl%3A+A+Parallel+Corpus+for+Statistical+Machine+Translation%2E+Proc%2E+of+MT+Summit+X%2C+pages+79%E2%80%9386%2C+Phuket%2E)
11. Ziheng Lin, Hwee Tou Ng, and Min-Yen Kan. 2010. A PDTB-styled End-to-end Discourse Parser. Technical Report TRB8/10, School of Computing, National University of Singapore. [find](https://scholar.google.com/scholar?q=Ziheng+Lin%2C+Hwee+Tou+Ng%2C+and+Min%2DYen+Kan%2E+2010%2E+A+PDTB%2Dstyled+End%2Dto%2Dend+Discourse+Parser%2E+Technical+Report+TRB8%2F10%2C+School+of+Computing%2C+National+University+of+Singapore%2E)
12. Jianjun Ma, Degen Huang, Haixia Liu, and Wenfeng Sheng. 2011. POS Tagging of English Particles for Machine Translation. Proc. of MT Summit XIII, pages 57–63, Xiamen. [find](https://scholar.google.com/scholar?q=Jianjun+Ma%2C+Degen+Huang%2C+Haixia+Liu%2C+and+Wenfeng+Sheng%2E+2011%2E+POS+Tagging+of+English+Particles+for+Machine+Translation%2E+Proc%2E+of+MT+Summit+XIII%2C+pages+57%E2%80%9363%2C+Xiamen%2E)
13. Christopher Manning and Dan Klein. 2003. Optimization, MaxEnt Models, and Conditional Estimation without Magic. Tutorial at HLT-NAACL and 41st ACL conferences, Edmonton, AB and Sapporo. [find](https://scholar.google.com/scholar?q=Christopher+Manning+and+Dan+Klein%2E+2003%2E+Optimization%2C+MaxEnt+Models%2C+and+Conditional+Estimation+without+Magic%2E+Tutorial+at+HLT%2DNAACL+and+41st+ACL+conferences%2C+Edmonton%2C+AB+and+Sapporo%2E)
14. Daniel Marcu. 2000. The Theory and Practice of Discourse Parsing and Summarization. A Bradford Book. The MIT Press, Cambridge, MA. [find](https://scholar.google.com/scholar?q=Daniel+Marcu%2E+2000%2E+The+Theory+and+Practice+of+Discourse+Parsing+and+Summarization%2E+A+Bradford+Book%2E+The+MIT+Press%2C+Cambridge%2C+MA%2E)
15. George A. Miller. 1995. WordNet: A Lexical Database for English. Communications of the ACM, 38(11):39–41. [find](https://scholar.google.com/scholar?q=George+A%2E+Miller%2E+1995%2E+WordNet%3A+A+Lexical+Database+for+English%2E+Communications+of+the+ACM%2C+38%2811%29%3A39%E2%80%9341%2E) [our card](https://md.research.elamur.ai/free/papers/lex-1994-miller-wordnet/)
16. Eleni Miltsakaki, Nikhil Dinesh, Rashmi Prasad, Aravind Joshi, and Bonnie Webber. 2005. Experiments on Sense Annotations and Sense Disambiguation of Discourse Connectives. Proc. of the 4th Workshop on Treebanks and Linguistic Theories (TLT), Barcelona. [find](https://scholar.google.com/scholar?q=Eleni+Miltsakaki%2C+Nikhil+Dinesh%2C+Rashmi+Prasad%2C+Aravind+Joshi%2C+and+Bonnie+Webber%2E+2005%2E+Experiments+on+Sense+Annotations+and+Sense+Disambiguation+of+Discourse+Connectives%2E+Proc%2E+of+the+4th+Workshop+on)
17. Franz Josef Och and Hermann Ney. 2003. A Systematic Comparison of Various Statistical Alignment Models. Computational Linguistics, 29(1):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%281%29%3A19%E2%80%9351%2E)
18. Franz Josef Och. 2003. Minimum Error Rate Training in Statistical Machine Translation. Proc. of the 41st Annual Meeting of the ACL, pages 160–167, Sapporo. [find](https://scholar.google.com/scholar?q=Franz+Josef+Och%2E+2003%2E+Minimum+Error+Rate+Training+in+Statistical+Machine+Translation%2E+Proc%2E+of+the+41st+Annual+Meeting+of+the+ACL%2C+pages+160%E2%80%93167%2C+Sapporo%2E)
19. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: A method for Automatic Evaluation of Machine Translation. Proc. of 40th Annual Meeting of the ACL, pages 311–318, Philadelphia, PA. [find](https://scholar.google.com/scholar?q=Kishore+Papineni%2C+Salim+Roukos%2C+Todd+Ward%2C+and+Wei%2DJing+Zhu%2E+2002%2E+BLEU%3A+A+method+for+Automatic+Evaluation+of+Machine+Translation%2E+Proc%2E+of+40th+Annual+Meeting+of+the+ACL%2C+pages+311%E2%80%93318%2C+Philadelphia%2C) [our card](https://md.research.elamur.ai/free/papers/papineni-2002-bleu-method-automatic-evaluation-machine/)
20. Emily Pitler and Ani Nenkova. 2009. Using Syntax to Disambiguate Explicit Discourse Connectives in Text. Proc. of the 47th Annual Meeting of the ACL and the 4th International Joint Conference of the AFNLP (ACL-IJCNLP), Short Papers, pages 13–16, Singapore. [find](https://scholar.google.com/scholar?q=Emily+Pitler+and+Ani+Nenkova%2E+2009%2E+Using+Syntax+to+Disambiguate+Explicit+Discourse+Connectives+in+Text%2E+Proc%2E+of+the+47th+Annual+Meeting+of+the+ACL+and+the+4th+International+Joint+Conference+of+the+A) [our card](https://md.research.elamur.ai/free/papers/pitler-2009-syntax-disambiguate-explicit-discourse-connectives/)
21. Rashmi Prasad, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, Livio Robaldo, Aravind Joshi, and Bonnie Webber. 2008. The Penn Discourse Treebank 2.0. Proc. of the 6th International Conference on Language Resources and Evaluation (LREC), pages 2961–2968, Marrakech. [find](https://scholar.google.com/scholar?q=Rashmi+Prasad%2C+Nikhil+Dinesh%2C+Alan+Lee%2C+Eleni+Miltsakaki%2C+Livio+Robaldo%2C+Aravind+Joshi%2C+and+Bonnie+Webber%2E+2008%2E+The+Penn+Discourse+Treebank+2%2E0%2E+Proc%2E+of+the+6th+International+Conference+on+Language+) [our card](https://md.research.elamur.ai/free/papers/disc-2008-prasad-penn-discourse-treebank-2-0/)
22. Marc Verhagen and James Pustejovsky. 2008. Temporal Processing with the TARSQI Toolkit. Proc. of the 22nd International Conference on Computational Linguistics (COLING), Demonstrations, pages 189–192, Manchester, UK. [find](https://scholar.google.com/scholar?q=Marc+Verhagen+and+James+Pustejovsky%2E+2008%2E+Temporal+Processing+with+the+TARSQI+Toolkit%2E+Proc%2E+of+the+22nd+International+Conference+on+Computational+Linguistics+%28COLING%29%2C+Demonstrations%2C+pages+189%E2%80%93192%2C)
23. Ben Wellner, James Pustejovsky, Catherine Havasi, Roser Sauri, and Anna Rumshisky. 2006. Classification of Discourse Coherence Relations: An Exploratory Study using Multiple Knowledge Sources. Proc. of the 7th SIGdial Meeting on Discourse and Dialog, pages 117–125, Sydney. [find](https://scholar.google.com/scholar?q=Ben+Wellner%2C+James+Pustejovsky%2C+Catherine+Havasi%2C+Roser+Sauri%2C+and+Anna+Rumshisky%2E+2006%2E+Classification+of+Discourse+Coherence+Relations%3A+An+Exploratory+Study+using+Multiple+Knowledge+Sources%2E+Proc%2E+o) [our card](https://md.research.elamur.ai/free/papers/wellner-2006-classification-discourse-coherence-relations-exploratory/)
24. Ben Wellner. 2009. Sequence Models and Ranking Methods for Discourse Parsing. PhD thesis, Brandeis University, Waltham, MA. [find](https://scholar.google.com/scholar?q=Ben+Wellner%2E+2009%2E+Sequence+Models+and+Ranking+Methods+for+Discourse+Parsing%2E+PhD+thesis%2C+Brandeis+University%2C+Waltham%2C+MA%2E)
25. Ying Zhang and Stefan Vogel. 2010. Significance Tests of Automatic Machine Translation Evaluation Metrics. Machine Translation, 24(1):51–65. [find](https://scholar.google.com/scholar?q=Ying+Zhang+and+Stefan+Vogel%2E+2010%2E+Significance+Tests+of+Automatic+Machine+Translation+Evaluation+Metrics%2E+Machine+Translation%2C+24%281%29%3A51%E2%80%9365%2E)