---
title: "Combining Intra- and Multi-sentential Rhetorical Parsing for"
description: "Joty et al. propose a two-stage parser (TSP) to address all three issues. 25 references, cited by 82 papers here."
authors: ["Shafiq Joty", "Giuseppe Carenini", "Raymond Ng", "Yashar Mehdad"]
year: 2013
venue: "Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/P13-1048/"
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/joty-2013-combining-intra-multi-sentential-rhetorical/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/joty-2013-combining-intra-multi-sentential-rhetorical/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2013](https://md.research.elamur.ai/free/en/papers/2013/) / Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis

# Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis

**Authors:** [Shafiq Joty](https://md.research.elamur.ai/free/en/authors/shafiq-joty/), [Giuseppe Carenini](https://md.research.elamur.ai/free/en/authors/giuseppe-carenini/), [Raymond Ng](https://md.research.elamur.ai/free/en/authors/raymond-ng/) and [Yashar Mehdad](https://md.research.elamur.ai/free/en/authors/yashar-mehdad/) · **Year:** 2013 · **Venue:** [Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2013](https://md.research.elamur.ai/free/en/venues/acl/2013/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **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/P13-1048/) · [PDF](https://aclanthology.org/P13-1048.pdf) · [OpenAlex](https://openalex.org/W2251211118)

**Citations:** 135 citations (OpenAlex, 2026-10-14) · [82](https://md.research.elamur.ai/free/en/papers/joty-2013-combining-intra-multi-sentential-rhetorical/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Document-level discourse parsing in the RST framework lags well behind human agreement. Existing parsers such as HILDA predict tree structure and relation labels in separate pipeline steps, build trees greedily, and treat a whole document as one uniform problem. Joty et al. propose a two-stage parser (TSP) to address all three issues. One Conditional Random Field handles parsing inside sentences and a second handles parsing across sentences. Each CRF jointly scores the span and the relation label (with nuclearity) of every candidate constituent. Both stages share one optimal, non-greedy bottom-up parsing algorithm that searches over these probabilities.

The authors test two ways to connect the stages:
- **1S-1S:** parse each sentence separately.
- **Sliding window:** parse pairs of adjacent sentences, which catches structures that cross sentence boundaries.

Evaluation covers two genres, RST-DT news and an Instructional how-to corpus. The parser beats HILDA and an ILP-based system by large, statistically significant margins on span, nuclearity and relation F-scores. This narrows the gap to human performance.

## Key points
- On RST-DT with gold segmentation and 18 coarse relations, TSP reaches about 82.5–82.7 span, 68.4 nuclearity and 55.7 relation F-score. HILDA scores 74.68 / 58.99 / 44.32, and human agreement is 88.70 / 77.72 / 65.75.
- On the Instructional corpus, TSP scores about 79.7–80.9 span, 63.0–63.1 nuclearity and 43.5–43.6 relation. The ILP system of Subba and Di-Eugenio reports 70.35 / 49.47 / 35.44.
- The sliding-window variant (TSP SW) finds significantly more correct spans than TSP 1-1 but does not improve relation labeling.
- In a 20-document RST-DT development sample, the two settings show different relation distributions:
  - Attribution and Same-Unit outnumber Joint inside sentences.
  - Joint is more frequent than both across sentences.
- The intra-sentential model is a chain-structured dynamic CRF. Exhaustive search over a whole document is infeasible because the number of valid trees grows as a Catalan number.

## Interesting ideas
- **Split the problem along a natural text boundary.** Separate models for sentence-level and document-level decisions can learn different label distributions and use features that only make sense at one level, such as syntactic dominance sets inside sentences or lexical chains across them. The same split could suit any hierarchical structured prediction task.
- **Score structure and label jointly, then decode exactly.** Predicting a span and its relation together, then running an optimal search over those probabilities, avoids the error propagation of greedy merge-then-label pipelines.
- **Use overlapping windows to handle leaky boundaries.** Parsing two adjacent sentences at a time and reconciling the overlapping results recovers structures that cross sentence boundaries. The authors note this is especially promising for corpora with many such crossings.
- **Fairly replicate a baseline that cannot be rerun.** When the competitor's data split was unavailable, the authors averaged results over 5 random splits of matching size. This is a practical way to compare against figures reported only in another paper.
- **Use confusion-matrix error analysis to explain mistakes.** The analysis separates two causes of labeling errors: a dominant majority class (Elaboration) and semantically close relations (for example, Cause vs. Explanation). Each cause points to a different fix: ensembles or bagging for class imbalance, and richer semantic features for similar relations.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of British Columbia](https://md.research.elamur.ai/free/en/universities/university-of-british-columbia/) — University, Vancouver, Canada · 46 works · 33,673 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works · [🤔 Philosophy](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/philosophy/) · 211 works

🧭 Topics (1): [🧵 Discourse analysis](https://md.research.elamur.ai/free/en/topics/discourse-analysis/) · 394 works

💡 Concepts (1): [🧵 Discourse analysis](https://md.research.elamur.ai/free/en/concepts/discourse-analysis/) · 30 works

## Cite

Cite as: Shafiq Joty, Giuseppe Carenini, Raymond Ng and Yashar Mehdad. 2013. Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis. Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{joty2013combining,
  title = {{Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis}},
  author = {Shafiq Joty, Giuseppe Carenini, Raymond Ng and Yashar Mehdad},
  booktitle = {Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2013},
  url = {https://aclanthology.org/P13-1048/}
}
```

- [← previous Improving Text Simplification Language Modeling Using Unsimplified Text Data](https://md.research.elamur.ai/free/en/papers/kauchak-2013-improving-text-simplification-language-modeling/)
- [next → Strategic conversation](https://md.research.elamur.ai/free/en/papers/asher-2013-strategic-conversation/)
- [↑ back to papers of 2013](https://md.research.elamur.ai/free/en/papers/2013/)

## 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. O. Biran and O. Rambow. 2011. Identifying Justifications in Written Dialogs by Classifying Text as Argumentative. International Journal of Semantic Computing, 5(4):363–381. [find](https://scholar.google.com/scholar?q=O%2E+Biran+and+O%2E+Rambow%2E+2011%2E+Identifying+Justifications+in+Written+Dialogs+by+Classifying+Text+as+Argumentative%2E+International+Journal+of+Semantic+Computing%2C+5%284%29%3A363%E2%80%93381%2E)
2. L. Carlson, D. Marcu, and M. Okurowski. 2002. RST Discourse Treebank (RST-DT) LDC2002T07. Linguistic Data Consortium, Philadelphia. [find](https://scholar.google.com/scholar?q=L%2E+Carlson%2C+D%2E+Marcu%2C+and+M%2E+Okurowski%2E+2002%2E+RST+Discourse+Treebank+%28RST%2DDT%29+LDC2002T07%2E+Linguistic+Data+Consortium%2C+Philadelphia%2E)
3. V. Feng and G. Hirst. 2012. [Text-level Discourse Parsing with Rich Linguistic Features](https://md.research.elamur.ai/free/en/papers/feng-2012-text-level-discourse-parsing-rich/). In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, ACL ’12, pages 60–68, Jeju Island, Korea. Association for Computational Linguistics.
4. S. Fisher and B. Roark. 2007. The Utility of Parse-derived Features for Automatic Discourse Segmentation. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, ACL ’07, pages 488–495, Prague, Czech Republic. Association for Computational Linguistics. [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+the+45th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+AC)
5. M. Galley and K. McKeown. 2003. Improving Word Sense Disambiguation in Lexical Chaining. In Proceedings of the 18th International Joint Conference on Artificial Intelligence, IJCAI ’07, pages 1486– 1488, Acapulco, Mexico. [find](https://scholar.google.com/scholar?q=M%2E+Galley+and+K%2E+McKeown%2E+2003%2E+Improving+Word+Sense+Disambiguation+in+Lexical+Chaining%2E+In+Proceedings+of+the+18th+International+Joint+Conference+on+Artificial+Intelligence%2C+IJCAI+%E2%80%9907%2C+pages+1486%E2%80%93+14)
6. H. Hernault, H. Prendinger, D. duVerle, and M. Ishizuka. 2010. [HILDA: A Discourse Parser Using Support Vector Machine Classification](https://md.research.elamur.ai/free/en/papers/hernault-2010-hilda-discourse-parser-support-vector/). Dialogue and Discourse, 1(3):1–33.
7. S. Joty, G. Carenini, and R. T. Ng. 2012. A Novel Discriminative Framework for Sentence-Level Discourse Analysis. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL ’12, pages 904– 915, Jeju Island,… [find](https://scholar.google.com/scholar?q=S%2E+Joty%2C+G%2E+Carenini%2C+and+R%2E+T%2E+Ng%2E+2012%2E+A+Novel+Discriminative+Framework+for+Sentence%2DLevel+Discourse+Analysis%2E+In+Proceedings+of+the+2012+Joint+Conference+on+Empirical+Methods+in+Natural+Language+P)
8. H. LeThanh, G. Abeysinghe, and C. Huyck. 2004. Generating Discourse Structures for Written Texts. In Proceedings of the 20th international conference on Computational Linguistics, COLING ’04, Geneva, Switzerland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=H%2E+LeThanh%2C+G%2E+Abeysinghe%2C+and+C%2E+Huyck%2E+2004%2E+Generating+Discourse+Structures+for+Written+Texts%2E+In+Proceedings+of+the+20th+international+conference+on+Computational+Linguistics%2C+COLING+%E2%80%9904%2C+Geneva%2C+)
9. A. Louis, A. Joshi, and A. Nenkova. 2010. Discourse Indicators for Content Selection in Summarization. In Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL ’10, pages 147–156, Tokyo, Japan. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=A%2E+Louis%2C+A%2E+Joshi%2C+and+A%2E+Nenkova%2E+2010%2E+Discourse+Indicators+for+Content+Selection+in+Summarization%2E+In+Proceedings+of+the+11th+Annual+Meeting+of+the+Special+Interest+Group+on+Discourse+and+Dialogue)
10. W. Mann and S. Thompson. 1988. [Rhetorical Structure Theory: Toward a Functional Theory of Text Organization](https://md.research.elamur.ai/free/en/papers/mann-1988-rhetorical-structure-theory-functional/). Text, 8(3):243–281.
11. D. Marcu and A. Echihabi. 2002. [An Unsupervised Approach to Recognizing Discourse Relations](https://md.research.elamur.ai/free/en/papers/marcu-2002-unsupervised-approach-recognizing-discourse-relations/). In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL ’02, pages 368–375. Association for Computational Linguistics.
12. D. Marcu. 2000a. [The Rhetorical Parsing of Unrestricted Texts: A Surface-based Approach](https://md.research.elamur.ai/free/en/papers/marcu-2000-rhetorical-parsing-unrestricted-texts-surface/). Computational Linguistics, 26:395–448.
13. D. Marcu. 2000b. The Theory and Practice of Discourse Parsing and Summarization. MIT Press, Cambridge, MA, USA. [find](https://scholar.google.com/scholar?q=D%2E+Marcu%2E+2000b%2E+The+Theory+and+Practice+of+Discourse+Parsing+and+Summarization%2E+MIT+Press%2C+Cambridge%2C+MA%2C+USA%2E)
14. J. Morris and G. Hirst. 1991. Lexical Cohesion Computed by Thesaural Relations as an Indicator of Structure of Text. Computational Linguistics, 17(1):21–48. [find](https://scholar.google.com/scholar?q=J%2E+Morris+and+G%2E+Hirst%2E+1991%2E+Lexical+Cohesion+Computed+by+Thesaural+Relations+as+an+Indicator+of+Structure+of+Text%2E+Computational+Linguistics%2C+17%281%29%3A21%E2%80%9348%2E)
15. R. Prasad, A. Joshi, N. Dinesh, A. Lee, E. Miltsakaki, and B. Webber. 2005. The Penn Discourse Tree-Bank as a Resource for Natural Language Generation. In Proceedings of the Corpus Linguistics Workshop on Using Corpora for Natural Language Generation, pages 25–32, Birmingham, U.K. [find](https://scholar.google.com/scholar?q=R%2E+Prasad%2C+A%2E+Joshi%2C+N%2E+Dinesh%2C+A%2E+Lee%2C+E%2E+Miltsakaki%2C+and+B%2E+Webber%2E+2005%2E+The+Penn+Discourse+Tree%2DBank+as+a+Resource+for+Natural+Language+Generation%2E+In+Proceedings+of+the+Corpus+Linguistics+Worksho)
16. S. Somasundaran, 2010. Discourse-Level Relations for Opinion Analysis. PhD thesis, University of Pittsburgh. [find](https://scholar.google.com/scholar?q=S%2E+Somasundaran%2C+2010%2E+Discourse%2DLevel+Relations+for+Opinion+Analysis%2E+PhD+thesis%2C+University+of+Pittsburgh%2E)
17. R. Soricut and D. Marcu. 2003. [Sentence Level Discourse Parsing Using Syntactic and Lexical Information](https://md.research.elamur.ai/free/en/papers/soricut-2003-sentence-level-discourse-parsing-syntactic/). In Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, NAACL-HLT ’03, pages 149– 156, Edmonton, Canada.…
18. C. Sporleder and M. Lapata. 2005. Discourse Chunking and its Application to Sentence Compression. In Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, pages 257–264, Vancouver, British Columbia, Canada. Association for Computational Ling… [find](https://scholar.google.com/scholar?q=C%2E+Sporleder+and+M%2E+Lapata%2E+2005%2E+Discourse+Chunking+and+its+Application+to+Sentence+Compression%2E+In+Proceedings+of+the+conference+on+Human+Language+Technology+and+Empirical+Methods+in+Natural+Languag)
19. C. Sporleder and A. Lascarides. 2004. Combining Hierarchical Clustering and Machine Learning to Predict High-Level Discourse Structure. In Proceedings of the 20th international conference on Computational Linguistics, COLING ’04, Geneva, Switzerland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=C%2E+Sporleder+and+A%2E+Lascarides%2E+2004%2E+Combining+Hierarchical+Clustering+and+Machine+Learning+to+Predict+High%2DLevel+Discourse+Structure%2E+In+Proceedings+of+the+20th+international+conference+on+Computati)
20. M. Stede. 2004. The Potsdam Commentary Corpus. In Proceedings of the ACL-04 Workshop on Discourse Annotation, Barcelona. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=M%2E+Stede%2E+2004%2E+The+Potsdam+Commentary+Corpus%2E+In+Proceedings+of+the+ACL%2D04+Workshop+on+Discourse+Annotation%2C+Barcelona%2E+Association+for+Computational+Linguistics%2E)
21. R. Subba and B. Di-Eugenio. 2009. [An Effective Discourse Parser that Uses Rich Linguistic Information](https://md.research.elamur.ai/free/en/papers/subba-2009-effective-discourse-parser-that-uses/). In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, HLT-NAACL ’09, pages 566–574, Boulder, Colo…
22. C. Sutton and A. McCallum. 2012. An Introduction to Conditional Random Fields. Foundations and Trends in Machine Learning, 4(4):267–373. [find](https://scholar.google.com/scholar?q=C%2E+Sutton+and+A%2E+McCallum%2E+2012%2E+An+Introduction+to+Conditional+Random+Fields%2E+Foundations+and+Trends+in+Machine+Learning%2C+4%284%29%3A267%E2%80%93373%2E)
23. C. Sutton, A. McCallum, and K. Rohanimanesh. 2007. Dynamic Conditional Random Fields: Factorized Probabilistic Models for Labeling and Segmenting Sequence Data. Journal of Machine Learning Research (JMLR), 8:693–723. [find](https://scholar.google.com/scholar?q=C%2E+Sutton%2C+A%2E+McCallum%2C+and+K%2E+Rohanimanesh%2E+2007%2E+Dynamic+Conditional+Random+Fields%3A+Factorized+Probabilistic+Models+for+Labeling+and+Segmenting+Sequence+Data%2E+Journal+of+Machine+Learning+Research+%28J)
24. S. Verberne, L. Boves, N. Oostdijk, and P. Coppen. 2007. Evaluating Discourse-based Answer Extraction for Why-question Answering. In Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, pages 735–736, Amsterdam, The Netherlands. ACM. [find](https://scholar.google.com/scholar?q=S%2E+Verberne%2C+L%2E+Boves%2C+N%2E+Oostdijk%2C+and+P%2E+Coppen%2E+2007%2E+Evaluating+Discourse%2Dbased+Answer+Extraction+for+Why%2Dquestion+Answering%2E+In+Proceedings+of+the+30th+annual+international+ACM+SIGIR+conference+o)
25. N. Vliet and G. Redeker. 2011. Complex Sentences as Leaky Units in Discourse Parsing. In Proceedings of Constraints in Discourse, Agay-Saint Raphael, September. [find](https://scholar.google.com/scholar?q=N%2E+Vliet+and+G%2E+Redeker%2E+2011%2E+Complex+Sentences+as+Leaky+Units+in+Discourse+Parsing%2E+In+Proceedings+of+Constraints+in+Discourse%2C+Agay%2DSaint+Raphael%2C+September%2E)

*Updated 24 October 2026*