---
title: "A Semi-Supervised Approach to Improve — Hernault 2010"
description: "Discourse relation classifiers are usually trained with full supervision."
authors: ["Hugo Hernault", "Danushka Bollegala", "Mitsuru Ishizuka"]
year: 2010
venue: "Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/D10-1039/"
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/en/papers/hernault-2010-semi-supervised-approach-improve-classification/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/hernault-2010-semi-supervised-approach-improve-classification/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2010](https://md.research.elamur.ai/free/en/papers/2010/) / A Semi-Supervised Approach to Improve Classification of Infrequent Discourse Relations Using Feature Vector Extension

# A Semi-Supervised Approach to Improve Classification of Infrequent Discourse Relations Using Feature Vector Extension

**Authors:** [Hugo Hernault](https://md.research.elamur.ai/free/en/authors/hugo-hernault/), [Danushka Bollegala](https://md.research.elamur.ai/free/en/authors/danushka-bollegala/), [Mitsuru Ishizuka](https://md.research.elamur.ai/free/en/authors/mitsuru-ishizuka/) · **Year:** 2010 · **Venue:** Proceedings of the 2010 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/D10-1039/) · [PDF](https://aclanthology.org/D10-1039.pdf) · [OpenAlex](https://openalex.org/W2124169982)

**Citations:** 37 citations (openalex-snapshot · 2026-10-14) · [15](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Discourse relation classifiers are usually trained with full supervision. They handle common relations well but perform poorly on rare ones, and annotated data is expensive to produce. Hernault, Bollegala and Ishizuka address this with a semi-supervised technique that draws on cheap unlabeled text. They measure how often features occur together in unlabeled instances, scoring each pair with the χ² statistic. The result is a normalized feature co-occurrence matrix. The matrix is then used to extend feature vectors during both training and testing. As a result, test features never seen in training can still contribute through features related to them. The approach works with any multi-class learner.

Experiments on the RST Discourse Treebank (RSTDT) and Penn Discourse Treebank (PDTB) show large relative gains in accuracy and macro-average F-score when labeled data is scarce. The gains shrink as the labeled set grows. Absolute scores remain too low for standalone parsing. Still, the method is a practical first step toward detecting infrequent relations in domains with little annotation.

## Key points
- Task scale: RSTDT relations become a 41-class problem once nuclearity is included, while PDTB uses 15 level-two relations. Class frequencies range from thousands of instances down to only 2–17.
- Co-occurrence pairs are kept only when their χ² value exceeds the critical value 3.84 (0.05 confidence level, one degree of freedom). Scores are rescaled to [0, 1].
- With roughly 1000 labeled instances, accuracy and macro-average F-score improve by up to 50% over a baseline classifier.
- With 100 labeled and 100,000 unlabeled instances, macro-average F-score rises by 119% on RSTDT and 459% on PDTB. With 10,000 labeled instances, the maximum gains fall to 2.5% and 15% respectively.
- Improvements grow with the number of test features unseen during training and with the amount of unlabeled data used.

*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/en/shelves/linguistics/)

Topics: [Discourse analysis](https://md.research.elamur.ai/free/en/topics/discourse-analysis/)

## Cited by

Cited by

15 papers of our library cite it (of the 140673 whose bibliographies we read); 7 of them have a page here, 8 not yet.

- [Text-level Discourse Parsing with Rich Linguistic Features](https://md.research.elamur.ai/free/en/papers/feng-2012-text-level-discourse-parsing-rich/)
- [Chinese Discourse Relation Recognition](https://md.research.elamur.ai/free/en/papers/huang-2011-chinese-discourse-relation-recognition/)
- [Leveraging Synthetic Discourse Data via Multi-task Learning for Implicit Discourse Relation Recognition](https://md.research.elamur.ai/free/en/papers/lan-2013-leveraging-synthetic-discourse-data-multi/)
- [Recursive Deep Models for Discourse Parsing](https://md.research.elamur.ai/free/en/papers/li-2014-recursive-deep-models-discourse-parsing/)
- [Reducing Sparsity Improves the Recognition of Implicit Discourse Relations](https://md.research.elamur.ai/free/en/papers/li-2014-reducing-sparsity-improves-recognition-implicit/)
- [On the Need of Cross Validation for Discourse Relation Classification](https://md.research.elamur.ai/free/en/papers/shi-2017-need-cross-validation-discourse-relation/)
- [Exploiting Discourse Relations for Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/wang-2012-exploiting-discourse-relations-sentiment-analysis/)

## Cite

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

```bibtex
@inproceedings{hernault2010semi,
  title = {{A Semi-Supervised Approach to Improve Classification of Infrequent Discourse Relations Using Feature Vector Extension}},
  author = {Hernault, Hugo and Bollegala, Danushka and Ishizuka, Mitsuru},
  booktitle = {Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing},
  year = {2010},
  url = {https://aclanthology.org/D10-1039/}
}
```

- [← previous A Probabilistic Morphological Analyzer for Syriac](https://md.research.elamur.ai/free/en/papers/aclbulk-2010-mcclanahan-probabilistic-morphological-analyzer-syriac/)
- [next → A Simple Domain-Independent Probabilistic Approach to Generation](https://md.research.elamur.ai/free/en/papers/angeli-2010-simple-domain-independent-probabilistic-approach/)
- [↑ back to papers of 2010](https://md.research.elamur.ai/free/en/papers/2010/)

## References

31 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. R. Basili, M. Cammisa, and A. Moschitti. 2006. A semantic kernel to classify texts with very few training examples. Informatica (Slovenia), 30(2):163–172. [find](https://scholar.google.com/scholar?q=R%2E+Basili%2C+M%2E+Cammisa%2C+and+A%2E+Moschitti%2E+2006%2E+A+semantic+kernel+to+classify+texts+with+very+few+training+examples%2E+Informatica+%28Slovenia%29%2C+30%282%29%3A163%E2%80%93172%2E)
2. S. Bloehdorn, R. Basili, M. Cammisa, and A. Moschitti. 2006. Semantic kernels for text classification based on topological measures of feature similarity. In Proc. of ICDM’06, pages 808–812. [find](https://scholar.google.com/scholar?q=S%2E+Bloehdorn%2C+R%2E+Basili%2C+M%2E+Cammisa%2C+and+A%2E+Moschitti%2E+2006%2E+Semantic+kernels+for+text+classification+based+on+topological+measures+of+feature+similarity%2E+In+Proc%2E+of+ICDM%E2%80%9906%2C+pages+808%E2%80%93812%2E)
3. L. Carlson, D. Marcu, and M. E. Okurowski. 2001. Building a discourse-tagged corpus in the framework of Rhetorical Structure Theory. Proc. of Second SIGdial Workshop on Discourse and Dialogue-Volume 16, pages 1–10. [find](https://scholar.google.com/scholar?q=L%2E+Carlson%2C+D%2E+Marcu%2C+and+M%2E+E%2E+Okurowski%2E+2001%2E+Building+a+discourse%2Dtagged+corpus+in+the+framework+of+Rhetorical+Structure+Theory%2E+Proc%2E+of+Second+SIGdial+Workshop+on+Discourse+and+Dialogue%2DVolume+1) [our card](https://md.research.elamur.ai/free/en/papers/carlson-2001-building-discourse-tagged-corpus-framework/)
4. N. Cristianini, J. Shawe-Taylor, and H. Lodhi. 2002. Latent semantic kernels. Journal of Intelligent Information Systems, 18:127–152. [find](https://scholar.google.com/scholar?q=N%2E+Cristianini%2C+J%2E+Shawe%2DTaylor%2C+and+H%2E+Lodhi%2E+2002%2E+Latent+semantic+kernels%2E+Journal+of+Intelligent+Information+Systems%2C+18%3A127%E2%80%93152%2E)
5. S. C. Deerwester, S. T. Dumais, T. K. Landauer, G. W. Furnas, and R. A. Harshman. 1990. Indexing by latent semantic analysis. Journal of the American Society of Information Science, 41(6):391–407. [find](https://scholar.google.com/scholar?q=S%2E+C%2E+Deerwester%2C+S%2E+T%2E+Dumais%2C+T%2E+K%2E+Landauer%2C+G%2E+W%2E+Furnas%2C+and+R%2E+A%2E+Harshman%2E+1990%2E+Indexing+by+latent+semantic+analysis%2E+Journal+of+the+American+Society+of+Information+Science%2C+41%286%29%3A391%E2%80%93407%2E)
6. D. A. duVerle and H. Prendinger. 2009. A novel discourse parser based on Support Vector Machine classification. In Proc. of ACL’09, pages 665–673. [find](https://scholar.google.com/scholar?q=D%2E+A%2E+duVerle+and+H%2E+Prendinger%2E+2009%2E+A+novel+discourse+parser+based+on+Support+Vector+Machine+classification%2E+In+Proc%2E+of+ACL%E2%80%9909%2C+pages+665%E2%80%93673%2E) [our card](https://md.research.elamur.ai/free/en/papers/duverle-2009-novel-discourse-parser-based-support/)
7. H. Fang. 2008. A re-examination of query expansion using lexical resources. In Proc. of ACL’08, pages 139– 147. [find](https://scholar.google.com/scholar?q=H%2E+Fang%2E+2008%2E+A+re%2Dexamination+of+query+expansion+using+lexical+resources%2E+In+Proc%2E+of+ACL%E2%80%9908%2C+pages+139%E2%80%93+147%2E)
8. C. Fellbaum, editor. 1998. WordNet: An electronic lexical database. MIT Press. [find](https://scholar.google.com/scholar?q=C%2E+Fellbaum%2C+editor%2E+1998%2E+WordNet%3A+An+electronic+lexical+database%2E+MIT+Press%2E)
9. H. Hernault, D. Bollegala, and M. Ishizuka. 2010. A sequential model for discourse segmentation. In Proc. of CICLing’10, pages 315–326. [find](https://scholar.google.com/scholar?q=H%2E+Hernault%2C+D%2E+Bollegala%2C+and+M%2E+Ishizuka%2E+2010%2E+A+sequential+model+for+discourse+segmentation%2E+In+Proc%2E+of+CICLing%E2%80%9910%2C+pages+315%E2%80%93326%2E)
10. D. Klein and C. D. Manning. 2003. Fast exact inference with a factored model for natural language parsing. In Advances in Neural Information Processing Systems, volume 15. MIT Press. [find](https://scholar.google.com/scholar?q=D%2E+Klein+and+C%2E+D%2E+Manning%2E+2003%2E+Fast+exact+inference+with+a+factored+model+for+natural+language+parsing%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+15%2E+MIT+Press%2E)
11. Z. Lin, M-Y. Kan, and H. T. Ng. 2009. Recognizing implicit discourse relations in the Penn Discourse Treebank. In Proc. of EMNLP’09, pages 343–351. [find](https://scholar.google.com/scholar?q=Z%2E+Lin%2C+M%2DY%2E+Kan%2C+and+H%2E+T%2E+Ng%2E+2009%2E+Recognizing+implicit+discourse+relations+in+the+Penn+Discourse+Treebank%2E+In+Proc%2E+of+EMNLP%E2%80%9909%2C+pages+343%E2%80%93351%2E) [our card](https://md.research.elamur.ai/free/en/papers/lin-2009-recognizing-implicit-discourse-relations-penn/)
12. E. Loper and S. Bird. 2002. NLTK: The natural language toolkit. In Proc. of ACL’02 Workshop on Effective tools and methodologies for teaching natural language processing and computational linguistics, pages 63–70. [find](https://scholar.google.com/scholar?q=E%2E+Loper+and+S%2E+Bird%2E+2002%2E+NLTK%3A+The+natural+language+toolkit%2E+In+Proc%2E+of+ACL%E2%80%9902+Workshop+on+Effective+tools+and+methodologies+for+teaching+natural+language+processing+and+computational+linguistics%2C)
13. D. M. Magerman. 1995. Statistical decision-tree models for parsing. Proc. of ACL’95, pages 276–283. [find](https://scholar.google.com/scholar?q=D%2E+M%2E+Magerman%2E+1995%2E+Statistical+decision%2Dtree+models+for+parsing%2E+Proc%2E+of+ACL%E2%80%9995%2C+pages+276%E2%80%93283%2E) [our card](https://md.research.elamur.ai/free/en/papers/magerman-1995-statistical-decision-tree-models-parsing/)
14. W. C. Mann and S. A. Thompson. 1988. Rhetorical Structure Theory: Toward a functional theory of text organization. Text, 8(3):243–281. [find](https://scholar.google.com/scholar?q=W%2E+C%2E+Mann+and+S%2E+A%2E+Thompson%2E+1988%2E+Rhetorical+Structure+Theory%3A+Toward+a+functional+theory+of+text+organization%2E+Text%2C+8%283%29%3A243%E2%80%93281%2E) [our card](https://md.research.elamur.ai/free/en/papers/enud-1988-mann-rhetorical-structure-theory-functional/)
15. C. D. Manning and H. Schütze. 1999. Foundations of Statistical Natural Language processing. MIT Press. [find](https://scholar.google.com/scholar?q=C%2E+D%2E+Manning+and+H%2E+Schu%CC%88tze%2E+1999%2E+Foundations+of+Statistical+Natural+Language+processing%2E+MIT+Press%2E)
16. D. Marcu and A. Echihabi. 2002. An unsupervised approach to recognizing discourse relations. In Proc. of ACL’02, pages 368–375. [find](https://scholar.google.com/scholar?q=D%2E+Marcu+and+A%2E+Echihabi%2E+2002%2E+An+unsupervised+approach+to+recognizing+discourse+relations%2E+In+Proc%2E+of+ACL%E2%80%9902%2C+pages+368%E2%80%93375%2E) [our card](https://md.research.elamur.ai/free/en/papers/marcu-2002-unsupervised-approach-recognizing-discourse-relations/)
17. D. Marcu. 2000. The Theory and Practice of Discourse Parsing and Summarization. MIT Press. [find](https://scholar.google.com/scholar?q=D%2E+Marcu%2E+2000%2E+The+Theory+and+Practice+of+Discourse+Parsing+and+Summarization%2E+MIT+Press%2E)
18. M. P. Marcus, M. A. Marcinkiewicz, and B. Santorini. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19(2):313–330. [find](https://scholar.google.com/scholar?q=M%2E+P%2E+Marcus%2C+M%2E+A%2E+Marcinkiewicz%2C+and+B%2E+Santorini%2E+1993%2E+Building+a+large+annotated+corpus+of+English%3A+The+Penn+Treebank%2E+Computational+Linguistics%2C+19%282%29%3A313%E2%80%93330%2E) [our card](https://md.research.elamur.ai/free/en/papers/bank-1993-marcus-building-large-annotated-corpus-english/)
19. N. Okazaki. 2009. Classias: A collection of machine-learning algorithms for classification. [http://www.chokkan.org/software/classias/](http://www.chokkan.org/software/classias/). [↗](http://www.chokkan.org/software/classias/)
20. B. Pang and L. Lee. 2008. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, 2(1-2):1–135. [find](https://scholar.google.com/scholar?q=B%2E+Pang+and+L%2E+Lee%2E+2008%2E+Opinion+mining+and+sentiment+analysis%2E+Foundations+and+Trends+in+Information+Retrieval%2C+2%281%2D2%29%3A1%E2%80%93135%2E)
21. E. Pitler, M. Raghupathy, H. Mehta, A. Nenkova, A. Lee, and A. Joshi. 2008. Easily identifiable discourse relations. In Proc. of COLING’08 (Posters), pages 87–90. [find](https://scholar.google.com/scholar?q=E%2E+Pitler%2C+M%2E+Raghupathy%2C+H%2E+Mehta%2C+A%2E+Nenkova%2C+A%2E+Lee%2C+and+A%2E+Joshi%2E+2008%2E+Easily+identifiable+discourse+relations%2E+In+Proc%2E+of+COLING%E2%80%9908+%28Posters%29%2C+pages+87%E2%80%9390%2E) [our card](https://md.research.elamur.ai/free/en/papers/pitler-2008-easily-identifiable-discourse-relations/)
22. E. Pitler, A. Louis, and A. Nenkova. 2009. Automatic sense prediction for implicit discourse relations in text. In Proc. of ACL’09, pages 683–691. [find](https://scholar.google.com/scholar?q=E%2E+Pitler%2C+A%2E+Louis%2C+and+A%2E+Nenkova%2E+2009%2E+Automatic+sense+prediction+for+implicit+discourse+relations+in+text%2E+In+Proc%2E+of+ACL%E2%80%9909%2C+pages+683%E2%80%93691%2E) [our card](https://md.research.elamur.ai/free/en/papers/disc-2009-pitler-automatic-sense-prediction-implicit-discourse/)
23. P. Piwek, H. Hernault, H. Prendinger, and M. Ishizuka. 2007. Generating dialogues between virtual agents automatically from text. In Proc. of IVA’07, pages 161– 174. [find](https://scholar.google.com/scholar?q=P%2E+Piwek%2C+H%2E+Hernault%2C+H%2E+Prendinger%2C+and+M%2E+Ishizuka%2E+2007%2E+Generating+dialogues+between+virtual+agents+automatically+from+text%2E+In+Proc%2E+of+IVA%E2%80%9907%2C+pages+161%E2%80%93+174%2E)
24. R. L. Plackett. 1983. Karl Pearson and the chi-squared test. International Statistical Review / Revue Internationale de Statistique, 51(1):59–72. [find](https://scholar.google.com/scholar?q=R%2E+L%2E+Plackett%2E+1983%2E+Karl+Pearson+and+the+chi%2Dsquared+test%2E+International+Statistical+Review+%2F+Revue+Internationale+de+Statistique%2C+51%281%29%3A59%E2%80%9372%2E)
25. R. Prasad, N. Dinesh, A. Lee, E. Miltsakaki, L. Robaldo, A. Joshi, and B. Webber. 2008a. The Penn Discourse TreeBank 2.0. In Proc. of LREC’08. [find](https://scholar.google.com/scholar?q=R%2E+Prasad%2C+N%2E+Dinesh%2C+A%2E+Lee%2C+E%2E+Miltsakaki%2C+L%2E+Robaldo%2C+A%2E+Joshi%2C+and+B%2E+Webber%2E+2008a%2E+The+Penn+Discourse+TreeBank+2%2E0%2E+In+Proc%2E+of+LREC%E2%80%9908%2E) [our card](https://md.research.elamur.ai/free/en/papers/disc-2008-prasad-penn-discourse-treebank-2-0/)
26. R. Prasad, E. Miltsakaki, N. Dinesh, A. Lee, A. Joshi, L. Robaldo, and B. Webber. 2008b. The Penn Discourse Treebank 2.0 annotation manual. Technical report, University of Pennsylvania Institute for Research in Cognitive Science. [find](https://scholar.google.com/scholar?q=R%2E+Prasad%2C+E%2E+Miltsakaki%2C+N%2E+Dinesh%2C+A%2E+Lee%2C+A%2E+Joshi%2C+L%2E+Robaldo%2C+and+B%2E+Webber%2E+2008b%2E+The+Penn+Discourse+Treebank+2%2E0+annotation+manual%2E+Technical+report%2C+University+of+Pennsylvania+Institute+for+R)
27. G. Salton and C. Buckley. 1983. Introduction to Modern Information Retrieval. McGraw-Hill Book Company. [find](https://scholar.google.com/scholar?q=G%2E+Salton+and+C%2E+Buckley%2E+1983%2E+Introduction+to+Modern+Information+Retrieval%2E+McGraw%2DHill+Book+Company%2E)
28. G. Siolas and F. d’Alché-Buc. 2000. Support Vector Machines based on a semantic kernel for text categorization. In Proc. of IJCNN’00, volume 5, page 5205. [find](https://scholar.google.com/scholar?q=G%2E+Siolas+and+F%2E+d%E2%80%99Alche%CC%81%2DBuc%2E+2000%2E+Support+Vector+Machines+based+on+a+semantic+kernel+for+text+categorization%2E+In+Proc%2E+of+IJCNN%E2%80%9900%2C+volume+5%2C+page+5205%2E)
29. S. Somasundaran, G. Namata, J. Wiebe, and L. Getoor. 2009. Supervised and unsupervised methods in employing discourse relations for improving opinion polarity classification. In Proc. of EMNLP’09, pages 170–179. [find](https://scholar.google.com/scholar?q=S%2E+Somasundaran%2C+G%2E+Namata%2C+J%2E+Wiebe%2C+and+L%2E+Getoor%2E+2009%2E+Supervised+and+unsupervised+methods+in+employing+discourse+relations+for+improving+opinion+polarity+classification%2E+In+Proc%2E+of+EMNLP%E2%80%9909%2C+pag) [our card](https://md.research.elamur.ai/free/en/papers/somasundaran-2009-supervised-unsupervised-methods-employing-discourse/)
30. R. Soricut and D. Marcu. 2003. Sentence level discourse parsing using syntactic and lexical information. Proc. of NA-ACL’03, 1:149–156. [find](https://scholar.google.com/scholar?q=R%2E+Soricut+and+D%2E+Marcu%2E+2003%2E+Sentence+level+discourse+parsing+using+syntactic+and+lexical+information%2E+Proc%2E+of+NA%2DACL%E2%80%9903%2C+1%3A149%E2%80%93156%2E) [our card](https://md.research.elamur.ai/free/en/papers/soricut-2003-sentence-level-discourse-parsing-syntactic/)
31. V. N. Vapnik. 1995. The Nature of Statistical Learning Theory. Springer-Verlag New York, Inc. [find](https://scholar.google.com/scholar?q=V%2E+N%2E+Vapnik%2E+1995%2E+The+Nature+of+Statistical+Learning+Theory%2E+Springer%2DVerlag+New+York%2C+Inc%2E)