[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/disc-2009-pitler-automatic-sense-prediction-implicit-discourse/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [English](https://md.mova.elamur.ai/free/en/docs/papers/en/) / Automatic sense prediction for implicit discourse relations in text

# Automatic sense prediction for implicit discourse relations in text

**Authors:** [Emily Pitler](https://md.mova.elamur.ai/free/en/docs/papers/authors/emily-pitler/), [Annie Louis](https://md.mova.elamur.ai/free/en/docs/papers/authors/annie-louis/), [Ani Nenkova](https://md.mova.elamur.ai/free/en/docs/papers/authors/ani-nenkova/) · **Year:** 2009 · **Venue:** Proceedings of ACL-IJCNLP 2009 **Link:** [aclanthology.org/P09-1077](https://aclanthology.org/P09-1077/) · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) (ACL Anthology, before 2016) — summary only

[**141** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/disc-2009-pitler-automatic-sense-prediction-implicit-discourse/) of the 140673 papers whose bibliographies we read[Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP](https://aclanthology.org/volumes/P09-1/)[licence](https://creativecommons.org/licenses/by-nc-sa/3.0/)

- [Publisher's page](https://aclanthology.org/P09-1077/)
- [PDF](https://aclanthology.org/P09-1077.pdf)

**Authors (3)**

1. Emily Pitler
2. Annie Louis
3. Ani Nenkova

Citations and author metrics from OpenAlex (); authors with the same name are not always told apart.

## What it is about

The paper predicts the sense (Comparison, Contingency, Expansion, Temporal) of implicit discourse relations, meaning adjacent sentences with no connective, in PDTB newswire. It tests whether word-pair features from earlier work help. Word pairs from artificial implicit data (explicit connectives removed) learn the connectives that were removed, and their top pairs are function-word pairs such as "but-but", so they do not capture semantic opposition. The authors add polarity tags, Levin verb classes, first and last words, modality, number features and context (a neighbouring explicit relation or a paragraph boundary). The best model reaches F about 47 for Contingency (16 points over the word-pair baseline) and about 76 for Expansion. Evaluation uses the natural class distribution, with sections 2-20 for training and 21-22 for testing.

## Ideas

- I1. Leakage audit for Mova's own training data. When the explicit connective is removed from a tale or school sentence to make a synthetic relation, check whether a pair model still sees the connective. Run the pair check first: if the top features are connective pairs, the synthetic data is leaking. Measure with two-fold `cv` and two identical runs.
- I2. Polarity pairs from the `en` lexicon as a Contingency signal. The paper finds opposite-polarity pairs help Contingency, not Comparison. Test this on our tale text, one relation at a time, and report per-relation F rather than total accuracy.
- I3. Neighbour context for implicit links in `prag`. If the previous link is explicit, use its connective and sense as a prior for the next implicit one. Measure on world paragraphs and report the gain only after two identical runs.
- I4. Report per-sense F and a majority baseline for every relation set, not accuracy alone. Expansion dominates the distribution, so accuracy by itself hides a weak classifier.

## For Mova

The chapter is [36. Discourse relations and coherence](https://md.mova.elamur.ai/free/en/docs/languages/en/36-discourse-relations/), section 7 (implicit relations). The code is the link labels in `prag` and the word-pair and polarity features would live in a new module next to them. The paper's datasets (PDTB, TextRels, the Wilson polarity lexicon and the General Inquirer) need a licence check before use; the paper's own experiments are research-only, so use them as a reference, not as training data in a release.

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

## Cite

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

```
@inproceedings{pitler2009automatic,
  title = {{Automatic sense prediction for implicit discourse relations in text}},
  author = {Pitler, Emily and Louis, Annie and Nenkova, Ani},
  booktitle = {Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP},
  year = {2009},
  url = {https://aclanthology.org/P09-1077/}
}
```

- [← previous The Penn Discourse TreeBank 2.0.](https://md.mova.elamur.ai/free/en/docs/papers/disc-2008-prasad-penn-discourse-treebank-2-0/)
- [next → Bias in polar questions: Evidence from English and German production experiments](https://md.mova.elamur.ai/free/en/docs/papers/domaneschi-2017-bias-polar-questions-evidence-english/)
- [↑ back to English](https://md.mova.elamur.ai/free/en/docs/papers/en/)

## References

23 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. N. Asher and A. Lascarides. 2003. Logics of conversation. Cambridge University Press. [find](https://scholar.google.com/scholar?q=N%2E+Asher+and+A%2E+Lascarides%2E+2003%2E+Logics+of+conversation%2E+Cambridge+University+Press%2E)
2. S. Blair-Goldensohn, K.R. McKeown, and O.C. Rambow. 2007. Building and Refining Rhetorical-Semantic Relation Models. In Proceedings of NAACL HLT, pages 428–435. [find](https://scholar.google.com/scholar?q=S%2E+Blair%2DGoldensohn%2C+K%2ER%2E+McKeown%2C+and+O%2EC%2E+Rambow%2E+2007%2E+Building+and+Refining+Rhetorical%2DSemantic+Relation+Models%2E+In+Proceedings+of+NAACL+HLT%2C+pages+428%E2%80%93435%2E)
3. L. Carlson, D. Marcu, and M.E. Okurowski. 2001. Building a discourse-tagged corpus in the framework of rhetorical structure theory. In Proceedings of the Second SIGdial Workshop on Discourse and Dialogue, pages 1–10. [find](https://scholar.google.com/scholar?q=L%2E+Carlson%2C+D%2E+Marcu%2C+and+M%2EE%2E+Okurowski%2E+2001%2E+Building+a+discourse%2Dtagged+corpus+in+the+framework+of+rhetorical+structure+theory%2E+In+Proceedings+of+the+Second+SIGdial+Workshop+on+Discourse+and+Dialo) [our card](https://md.mova.elamur.ai/free/en/docs/papers/carlson-2001-building-discourse-tagged-corpus-framework/)
4. B.J. Dorr. 2001. LCS Verb Database. Technical Report Online Software Database, University of Maryland, College Park, MD. [find](https://scholar.google.com/scholar?q=B%2EJ%2E+Dorr%2E+2001%2E+LCS+Verb+Database%2E+Technical+Report+Online+Software+Database%2C+University+of+Maryland%2C+College+Park%2C+MD%2E)
5. Y. Freund and R.E. Schapire. 1996. Experiments with a New Boosting Algorithm. In Machine Learning: Proceedings of the Thirteenth International Conference, pages 148–156. [find](https://scholar.google.com/scholar?q=Y%2E+Freund+and+R%2EE%2E+Schapire%2E+1996%2E+Experiments+with+a+New+Boosting+Algorithm%2E+In+Machine+Learning%3A+Proceedings+of+the+Thirteenth+International+Conference%2C+pages+148%E2%80%93156%2E)
6. R. Girju. 2003. Automatic detection of causal relations for Question Answering. In Proceedings of the ACL 2003 workshop on Multilingual summarization and question answering-Volume 12, pages 76–83. [find](https://scholar.google.com/scholar?q=R%2E+Girju%2E+2003%2E+Automatic+detection+of+causal+relations+for+Question+Answering%2E+In+Proceedings+of+the+ACL+2003+workshop+on+Multilingual+summarization+and+question+answering%2DVolume+12%2C+pages+76%E2%80%9383%2E)
7. D. Graff. 2003. English gigaword corpus. Corpus number LDC2003T05, Linguistic Data Consortium, Philadelphia. [find](https://scholar.google.com/scholar?q=D%2E+Graff%2E+2003%2E+English+gigaword+corpus%2E+Corpus+number+LDC2003T05%2C+Linguistic+Data+Consortium%2C+Philadelphia%2E)
8. J. Hobbs. 1979. Coherence and coreference. Cognitive Science, 3:67–90. [find](https://scholar.google.com/scholar?q=J%2E+Hobbs%2E+1979%2E+Coherence+and+coreference%2E+Cognitive+Science%2C+3%3A67%E2%80%9390%2E)
9. A. Knott and T. Sanders. 1998. The classification of coherence relations and their linguistic markers: An exploration of two languages. Journal of Pragmatics, 30(2):135–175. [find](https://scholar.google.com/scholar?q=A%2E+Knott+and+T%2E+Sanders%2E+1998%2E+The+classification+of+coherence+relations+and+their+linguistic+markers%3A+An+exploration+of+two+languages%2E+Journal+of+Pragmatics%2C+30%282%29%3A135%E2%80%93175%2E)
10. J. Lafferty, A. McCallum, and F. Pereira. 2001. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In International Conference on Machine Learning 2001, pages 282–289. [find](https://scholar.google.com/scholar?q=J%2E+Lafferty%2C+A%2E+McCallum%2C+and+F%2E+Pereira%2E+2001%2E+Conditional+Random+Fields%3A+Probabilistic+Models+for+Segmenting+and+Labeling+Sequence+Data%2E+In+International+Conference+on+Machine+Learning+2001%2C+pages+2)
11. M. Lapata and A. Lascarides. 2004. sentence-internal temporal relations. NAACL 2004: Main Proceedings. Inferring In HLT-B. [find](https://scholar.google.com/scholar?q=M%2E+Lapata+and+A%2E+Lascarides%2E+2004%2E+sentence%2Dinternal+temporal+relations%2E+NAACL+2004%3A+Main+Proceedings%2E+Inferring+In+HLT%2DB%2E)
12. Levin. 1993. English Verb Classes and Alternations: A Preliminary Investigation. Chicago, IL. [find](https://scholar.google.com/scholar?q=Levin%2E+1993%2E+English+Verb+Classes+and+Alternations%3A+A+Preliminary+Investigation%2E+Chicago%2C+IL%2E)
13. W.C. Mann and S.A. Thompson. 1988. Rhetorical structure theory: Towards a functional theory of text organization. Text, 8. [find](https://scholar.google.com/scholar?q=W%2EC%2E+Mann+and+S%2EA%2E+Thompson%2E+1988%2E+Rhetorical+structure+theory%3A+Towards+a+functional+theory+of+text+organization%2E+Text%2C+8%2E)
14. D. Marcu and A. Echihabi. 2001. An unsupervised approach to recognizing discourse relations. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pages 368–375. [find](https://scholar.google.com/scholar?q=D%2E+Marcu+and+A%2E+Echihabi%2E+2001%2E+An+unsupervised+approach+to+recognizing+discourse+relations%2E+In+Proceedings+of+the+40th+Annual+Meeting+on+Association+for+Computational+Linguistics%2C+pages+368%E2%80%93375%2E)
15. D. Marcu. 2000. The Theory and Practice of Discourse and Summarization. The MIT Press. [find](https://scholar.google.com/scholar?q=D%2E+Marcu%2E+2000%2E+The+Theory+and+Practice+of+Discourse+and+Summarization%2E+The+MIT+Press%2E)
16. K. McKeown. 1985. Text Generation: Using Discourse strategies and Focus Constraints to Generate Natural Language Text. Cambridge University Press, Cambridge, England. [find](https://scholar.google.com/scholar?q=K%2E+McKeown%2E+1985%2E+Text+Generation%3A+Using+Discourse+strategies+and+Focus+Constraints+to+Generate+Natural+Language+Text%2E+Cambridge+University+Press%2C+Cambridge%2C+England%2E)
17. E. Pitler, M. Raghupathy, H. Mehta, A. Nenkova, A. Lee, and A. Joshi. 2008. Easily identifiable discourse relations. In Proceedings of the 22nd International Conference on Computational Linguistics (COLING08), short paper. [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+Proceedings+of+the+22nd+International+Conference+on+Computational+Linguistics+%28C)
18. R. Soricut and D. Marcu. 2003. Sentence level discourse parsing using syntactic and lexical information. In HLT-NAACL. [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+In+HLT%2DNAACL%2E) [our card](https://md.mova.elamur.ai/free/en/docs/papers/soricut-2003-sentence-level-discourse-parsing-syntactic/)
19. C. Sporleder and A. Lascarides. 2008. Using automatically labelled examples to classify rhetorical relations: An assessment. Natural Language Engineering, 14:369–416. [find](https://scholar.google.com/scholar?q=C%2E+Sporleder+and+A%2E+Lascarides%2E+2008%2E+Using+automatically+labelled+examples+to+classify+rhetorical+relations%3A+An+assessment%2E+Natural+Language+Engineering%2C+14%3A369%E2%80%93416%2E)
20. P.J. Stone, J. Kirsh, and Cambridge Computer Associates. 1966. The General Inquirer: A Computer Approach to Content Analysis. MIT Press. [find](https://scholar.google.com/scholar?q=P%2EJ%2E+Stone%2C+J%2E+Kirsh%2C+and+Cambridge+Computer+Associates%2E+1966%2E+The+General+Inquirer%3A+A+Computer+Approach+to+Content+Analysis%2E+MIT+Press%2E)
21. B. Wellner, J. Pustejovsky, C. Havasi, A. Rumshisky, and R. Sauri. 2006. Classification of discourse coherence relations: An exploratory study using multiple knowledge sources. In Proceedings of the 7th SIGdial Workshop on Discourse and Dialogue. [find](https://scholar.google.com/scholar?q=B%2E+Wellner%2C+J%2E+Pustejovsky%2C+C%2E+Havasi%2C+A%2E+Rumshisky%2C+and+R%2E+Sauri%2E+2006%2E+Classification+of+discourse+coherence+relations%3A+An+exploratory+study+using+multiple+knowledge+sources%2E+In+Proceedings+of+the+7)
22. T. Wilson, J. Wiebe, and P. Hoffmann. 2005. Recognizing contextual polarity in phrase-level sentiment analysis. In Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, pages 347–354. [find](https://scholar.google.com/scholar?q=T%2E+Wilson%2C+J%2E+Wiebe%2C+and+P%2E+Hoffmann%2E+2005%2E+Recognizing+contextual+polarity+in+phrase%2Dlevel+sentiment+analysis%2E+In+Proceedings+of+the+conference+on+Human+Language+Technology+and+Empirical+Methods+in+N)
23. F. Wolf and E. Gibson. 2005. Representing discourse coherence: A corpus-based study. Computational Linguistics, 31(2):249–288. [find](https://scholar.google.com/scholar?q=F%2E+Wolf+and+E%2E+Gibson%2E+2005%2E+Representing+discourse+coherence%3A+A+corpus%2Dbased+study%2E+Computational+Linguistics%2C+31%282%29%3A249%E2%80%93288%2E)