[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/pitler-2009-syntax-disambiguate-explicit-discourse-connectives/)

[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/) / Using Syntax to Disambiguate Explicit Discourse Connectives in Text

# Using Syntax to Disambiguate Explicit Discourse Connectives in Text

**Authors:** [Emily Pitler](https://md.mova.elamur.ai/free/en/docs/papers/authors/emily-pitler/), [Ani Nenkova](https://md.mova.elamur.ai/free/en/docs/papers/authors/ani-nenkova/) · **Year:** 2009 · **Venue:** Proceedings of the ACL-IJCNLP 2009 Conference Short Papers **Link:** [aclanthology.org/P09-2004](https://aclanthology.org/P09-2004/) · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) (ACL Anthology, before 2016) — summary only; PDTB data evaluation only

[**137** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/pitler-2009-syntax-disambiguate-explicit-discourse-connectives/) of the 140673 papers whose bibliographies we read[Proceedings of the ACL-IJCNLP 2009 Conference Short Papers](https://aclanthology.org/volumes/P09-2/)[licence](https://creativecommons.org/licenses/by-nc-sa/3.0/)

- [Publisher's page](https://aclanthology.org/P09-2004/)
- [PDF](https://aclanthology.org/P09-2004.pdf)

**Authors (2)**

1. Emily Pitler
2. Ani Nenkova

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

## What it is about

Discourse connectives such as "once", "since" and "and" are often ambiguous in two ways: between a discourse use and a non-discourse use, and between discourse senses. The paper shows that syntax helps in both tasks. It uses gold Penn Treebank parses of the PDTB articles. The syntactic features are the category of the connective's node, of its parent, of its left and right siblings, and two flags on the right sibling (contains a VP, contains a trace). For discourse vs non-discourse usage, a maximum-entropy classifier with 10-fold cross-validation over sections 2 to 22 reaches F 75.33 with the connective string alone, 88.19 with syntax only, 92.28 with both, 93.63 with connective-syntax interactions, and 94.19 with syntax-syntax interactions. For the four top-level senses, a Naive Bayes classifier reaches 93.67% accuracy with the connective alone and 94.15% with syntax. The earlier surface-based result of Marcu (2000) was F 84.9, on a different corpus.

## Ideas

- I1. A gate for connectives in `en` parse output: an explicit decision list ("right sibling is a clause, so discourse use") with a reason stored per decision. Measure it on held-out data only, because the PDTB data are evaluation only.
- I2. Keep a connective table in [36. Discourse relations and coherence](https://md.mova.elamur.ai/free/en/docs/languages/en/36-discourse-relations/) as a BTreeMap from each connective to the syntactic contexts that it accepts. The paper says 11 connectives are discourse more than 90% of the time; start there.
- I3. The paper uses constituency categories. Translate the features to UD: the deprel of the connective's head and of its right dependent. Report how much of the gain survives on the parser output of `en/src/parse.rs`, since the paper's numbers used gold trees.
- I4. Negative control: replace the syntactic features with the labels of shuffled parents. The gain over the connective string must disappear.

## For Mova

The code is `en/src/parse.rs` and `en/src/tok.rs`. The chapters are [36. Discourse relations and coherence](https://md.mova.elamur.ai/free/en/docs/languages/en/36-discourse-relations/), [38. Dialogue, discourse markers and reported speech](https://md.mova.elamur.ai/free/en/docs/languages/en/38-dialogue-and-discourse-markers/) and [19. The lexicon: vocabulary, multiword expressions and register](https://md.mova.elamur.ai/free/en/docs/languages/en/19-lexicon-mwe-register/). The measure is accuracy and F on the discourse vs non-discourse decision, run twice on the same split, with gold and parser trees reported separately.

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{pitler2009using,
  title = {{Using Syntax to Disambiguate Explicit Discourse Connectives in Text}},
  author = {Pitler, Emily and Nenkova, Ani},
  booktitle = {Proceedings of the ACL-IJCNLP 2009 Conference Short Papers},
  year = {2009},
  url = {https://aclanthology.org/P09-2004/}
}
```

- [← previous Familiar vs. unique in a diachronic perspective. Case study of the rise of the definite article in North Germanic](https://md.mova.elamur.ai/free/en/docs/papers/piotrowska-2021-familiar-vs-unique-diachronic-perspective/)
- [next → Automatic transcription of 17th century English text in Contemporary English with NooJ: Method and Evaluation](https://md.mova.elamur.ai/free/en/docs/papers/piton-2011-automatic-transcription-17th-century-english/)
- [↑ back to English](https://md.mova.elamur.ai/free/en/docs/papers/en/)

## 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. R. Elwell and J. Baldridge. 2008. Discourse connective argument identification with connective specific rankers. In Proceedings of the International Conference on Semantic Computing, Santa Clara, CA. [find](https://scholar.google.com/scholar?q=R%2E+Elwell+and+J%2E+Baldridge%2E+2008%2E+Discourse+connective+argument+identification+with+connective+specific+rankers%2E+In+Proceedings+of+the+International+Conference+on+Semantic+Computing%2C+Santa+Clara%2C+CA%2E)
2. S. Fisher and B. Roark. 2007. The utility of parse-derived features for automatic discourse segmentation. In Proceedings of ACL, pages 488–495. [find](https://scholar.google.com/scholar?q=S%2E+Fisher+and+B%2E+Roark%2E+2007%2E+The+utility+of+parse%2Dderived+features+for+automatic+discourse+segmentation%2E+In+Proceedings+of+ACL%2C+pages+488%E2%80%93495%2E)
3. A. Gravano, S. Benus, H. Chavez, J. Hirschberg, and L. Wilcox. 2007. On the role of context and prosody in the interpretation of ’okay’. In Proceedings of ACL, pages 800–807. [find](https://scholar.google.com/scholar?q=A%2E+Gravano%2C+S%2E+Benus%2C+H%2E+Chavez%2C+J%2E+Hirschberg%2C+and+L%2E+Wilcox%2E+2007%2E+On+the+role+of+context+and+prosody+in+the+interpretation+of+%E2%80%99okay%E2%80%99%2E+In+Proceedings+of+ACL%2C+pages+800%E2%80%93807%2E)
4. J. Hirschberg and D. Litman. 1993. Empirical studies on the disambiguation of cue phrases. Computational linguistics, 19(3):501–530. [find](https://scholar.google.com/scholar?q=J%2E+Hirschberg+and+D%2E+Litman%2E+1993%2E+Empirical+studies+on+the+disambiguation+of+cue+phrases%2E+Computational+linguistics%2C+19%283%29%3A501%E2%80%93530%2E)
5. D. Marcu. 2000. The rhetorical parsing of unrestricted texts: A surface-based approach. Computational Linguistics, 26(3):395–448. [find](https://scholar.google.com/scholar?q=D%2E+Marcu%2E+2000%2E+The+rhetorical+parsing+of+unrestricted+texts%3A+A+surface%2Dbased+approach%2E+Computational+Linguistics%2C+26%283%29%3A395%E2%80%93448%2E)
6. M.P. Marcus, B. Santorini, and M.A. Marcinkiewicz. 1994. Building a large annotated corpus of english: The penn treebank. Computational Linguistics, 19(2):313–330. [find](https://scholar.google.com/scholar?q=M%2EP%2E+Marcus%2C+B%2E+Santorini%2C+and+M%2EA%2E+Marcinkiewicz%2E+1994%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.mova.elamur.ai/free/en/docs/papers/bank-1993-marcus-building-large-annotated-corpus-english/)
7. E. Miltsakaki, N. Dinesh, R. Prasad, A. Joshi, and B. Webber. 2005. Experiments on sense annotation and sense disambiguation of discourse connectives. In Proceedings of the Fourth Workshop on Treebanks and Linguistic Theories (TLT 2005). [find](https://scholar.google.com/scholar?q=E%2E+Miltsakaki%2C+N%2E+Dinesh%2C+R%2E+Prasad%2C+A%2E+Joshi%2C+and+B%2E+Webber%2E+2005%2E+Experiments+on+sense+annotation+and+sense+disambiguation+of+discourse+connectives%2E+In+Proceedings+of+the+Fourth+Workshop+on+Treebank)
8. E. Pitler, M. Raghupathy, H. Mehta, A. Nenkova, A. Lee, and A. Joshi. 2008. Easily identifiable discourse relations. In COLING, 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+COLING%2C+short+paper%2E)
9. R. Prasad, N. Dinesh, A. Lee, E. Miltsakaki, L. Robaldo, A. Joshi, and B. Webber. 2008. The penn discourse treebank 2.0. In Proceedings 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+2008%2E+The+penn+discourse+treebank+2%2E0%2E+In+Proceedings+of+LREC%E2%80%9908%2E) [our card](https://md.mova.elamur.ai/free/en/docs/papers/disc-2008-prasad-penn-discourse-treebank-2-0/)
10. 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/)
11. 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)
12. B. Wellner and J. Pustejovsky. 2007. Automatically identifying the arguments of discourse connectives. In Proceedings of EMNLP-CoNLL, pages 92–101. [find](https://scholar.google.com/scholar?q=B%2E+Wellner+and+J%2E+Pustejovsky%2E+2007%2E+Automatically+identifying+the+arguments+of+discourse+connectives%2E+In+Proceedings+of+EMNLP%2DCoNLL%2C+pages+92%E2%80%93101%2E)
13. 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)