---
title: "Comparison of methods for explicit discourse — Scholman 2021"
description: "Shallow discourse parsing begins by locating explicit connectives."
authors: ["Merel Scholman", "Tianai Dong", "Frances Yung", "Vera Demberg"]
year: 2021
venue: "Proceedings of the 2nd Workshop on Computational Approaches to Discourse"
source: "https://aclanthology.org/2021.codi-main.9/"
doi: "10.18653/v1/2021.codi-main.9"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/scholman-2021-comparison-methods-explicit-discourse-connective/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/scholman-2021-comparison-methods-explicit-discourse-connective/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2021](https://md.research.elamur.ai/free/papers/2021/) / Comparison of methods for explicit discourse connective identification across various domains

# Comparison of methods for explicit discourse connective identification across various domains

**Authors:** [Merel Scholman](https://md.research.elamur.ai/free/authors/merel-scholman/), [Tianai Dong](https://md.research.elamur.ai/free/authors/tianai-dong/), [Frances Yung](https://md.research.elamur.ai/free/authors/frances-yung/), [Vera Demberg](https://md.research.elamur.ai/free/authors/vera-demberg/) · **Year:** 2021 · **Venue:** Proceedings of the 2nd Workshop on Computational Approaches to Discourse · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2021.codi-main.9/) · [PDF](https://aclanthology.org/2021.codi-main.9.pdf) · [DOI 10.18653/v1/2021.codi-main.9](https://doi.org/10.18653/v1/2021.codi-main.9) · [OpenAlex](https://openalex.org/W3214534028)

**Citations:** 7 citations (openalex-snapshot · 2026-10-14) · [11](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Shallow discourse parsing begins by locating explicit connectives. This step is harder than it looks: words such as "yet", "so" or "but" do not always join two discourse arguments, and how they are used shifts between genres. Connective detectors have mostly been tested on newspaper text, and rarely against one another. Scholman et al. compare four systems: the feature-based PDTB e2e parser, the CONLL2015 winner (Wang and Lan), DisSent, and the BERT-based neural Discopy. They add a naive lookup baseline built on the PDTB2 connective list. All five are run on four discourse-annotated English corpora: news (PDTB), biomedical articles (BioDRB), TED talks (TED-MDB) and spontaneous conversation (DiscoSPICE).

Discopy wins on every corpus except DiscoSPICE, where PDTB e2e leads, though no system copes well with spontaneous speech. Accuracy drops clearly once systems leave the PDTB. The error analysis links failures to speech-specific structures, flawed gold labels, segmentation mismatches and incomplete connective lexicons. The authors call for out-of-domain evaluation, domain adaptation and more transparent reporting.

## Key points
- **Systems compared:** PDTB e2e (Lin et al., 2014); the system by Wang and Lan (2015) that ranked first in CONLL2015; Nie et al.'s (2019) DisSent; Discopy (Knaebel and Stede, 2020); and a heuristic baseline that tags every item from the 100-entry PDTB2 connective list.
- **Corpora and DisSent's coverage:**
  - Test domains: PDTB (news), BioDRB (science), TED-MDB (prepared speech) and Disco-SPICE, which contains 1163 explicit connective tokens from Irish broadcast and telephone talk annotated in PDTB3 style.
  - DisSent was trained on BookCorpus and covers only 18 connective types, compared with roughly 100 for the other parsers.
- **Main results:**
  - Discopy is best on PDTB, BioDRB and TED-MDB, while PDTB e2e is best on DiscoSPICE.
  - All parsers lose accuracy outside the PDTB, and the loss is worst on spontaneous speech, which features disfluencies, cut-off arguments and "so" used as a discourse marker.
- **Error sources:**
  - Some false positives look like connectives that the gold annotation missed.
  - Frameworks disagree on what counts as an argument (e.g., "until" + NP in BioDRB, "what if" in Discopy's output).
  - Connectives absent from PDTB2's list (e.g., "hereafter") are never found. The authors suggest extending the lexicon with the PDTB 3.0 list or the lexicon of Das et al. (2018).
- **Reproducibility and cost:** The originally published scores could not be fully reproduced, even by two independent implementers. Discopy also needs far more compute than the feature-based parsers.

*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/)

## Cited by

Cited by

11 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 8 not yet.

- [The DISRPT 2023 Shared Task on Elementary Discourse Unit Segmentation, Connective Detection, and Relation Classification](https://md.research.elamur.ai/free/papers/braud-2023-disrpt-2023-shared-task-elementary/)
- [DiscoGeM: A Crowdsourced Corpus of Genre-Mixed Implicit Discourse Relations](https://md.research.elamur.ai/free/papers/scholman-2022-discogem-crowdsourced-corpus-genre-mixed/)
- [eRST: A Signaled Graph Theory of Discourse Relations and Organization](https://md.research.elamur.ai/free/papers/zeldes-2025-erst-signaled-graph-theory-discourse/)

## Cite

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

```bibtex
@inproceedings{scholman2021comparison,
  title = {{Comparison of methods for explicit discourse connective identification across various domains}},
  author = {Scholman, Merel and Dong, Tianai and Yung, Frances and Demberg, Vera},
  booktitle = {Proceedings of the 2nd Workshop on Computational Approaches to Discourse},
  year = {2021},
  doi = {10.18653/v1/2021.codi-main.9},
  url = {https://doi.org/10.18653/v1/2021.codi-main.9}
}
```

- [← previous Combined discourse representations: Coherence relations and questions under Discussion](https://md.research.elamur.ai/free/papers/riester-2021-combined-discourse-representations-coherence-relations/)
- [next → ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer](https://md.research.elamur.ai/free/papers/yan-2021-consert-contrastive-framework-self-supervised/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/papers/2021/)

## References

28 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Emily M. Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell. 2021. On the dangers of stochastic parrots: Can language models be too big? . Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. [find](https://scholar.google.com/scholar?q=Emily+M%2E+Bender%2C+Timnit+Gebru%2C+Angelina+McMillan%2DMajor%2C+and+Shmargaret+Shmitchell%2E+2021%2E+On+the+dangers+of+stochastic+parrots%3A+Can+language+models+be+too+big%3F+%2E+Proceedings+of+the+2021+ACM+Conference+)
2. Emily M. Bender and Alexander Koller. 2020. Climbing towards NLU: On meaning, form, and understanding in the age of data. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5185–5198, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Emily+M%2E+Bender+and+Alexander+Koller%2E+2020%2E+Climbing+towards+NLU%3A+On+meaning%2C+form%2C+and+understanding+in+the+age+of+data%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+for+Computational) [our card](https://md.research.elamur.ai/free/papers/bender-2020-climbing-nlu-meaning-form-understanding/)
3. Ludivine Crible and Maria-Josep Cuenca. 2017. Discourse markers in speech: characteristics and challenges for corpus annotation. Dialogue and Discourse, 8(2):149–166. [find](https://scholar.google.com/scholar?q=Ludivine+Crible+and+Maria%2DJosep+Cuenca%2E+2017%2E+Discourse+markers+in+speech%3A+characteristics+and+challenges+for+corpus+annotation%2E+Dialogue+and+Discourse%2C+8%282%29%3A149%E2%80%93166%2E)
4. Debopam Das, Tatjana Scheffler, Peter Bourgonje, and Manfred Stede. 2018. Constructing a lexicon of English discourse connectives. In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, pages 360–365. [find](https://scholar.google.com/scholar?q=Debopam+Das%2C+Tatjana+Scheffler%2C+Peter+Bourgonje%2C+and+Manfred+Stede%2E+2018%2E+Constructing+a+lexicon+of+English+discourse+connectives%2E+In+Proceedings+of+the+19th+Annual+SIGdial+Meeting+on+Discourse+and+Di) [our card](https://md.research.elamur.ai/free/papers/das-2018-constructing-lexicon-english-discourse-connectives/)
5. Sindhuja Gopalan and Sobha Lalitha Devi. 2016. BioDCA Identifier: A System for Automatic Identification of Discourse Connective and Arguments from Biomedical Text. In Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM2016), pages 89– 98. [find](https://scholar.google.com/scholar?q=Sindhuja+Gopalan+and+Sobha+Lalitha+Devi%2E+2016%2E+BioDCA+Identifier%3A+A+System+for+Automatic+Identification+of+Discourse+Connective+and+Arguments+from+Biomedical+Text%2E+In+Proceedings+of+the+Fifth+Workshop)
6. Kelvin Han, Phyllicia Leavitt, and Srilakshmi Balard. 2020. Comparing PTB and UD information for PDTB discourseconnective identification. In Actes de la 6e conférence conjointe Journées d’Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Renc… [find](https://scholar.google.com/scholar?q=Kelvin+Han%2C+Phyllicia+Leavitt%2C+and+Srilakshmi+Balard%2E+2020%2E+Comparing+PTB+and+UD+information+for+PDTB+discourseconnective+identification%2E+In+Actes+de+la+6e+conf%C3%A9rence+conjointe+Journ%C3%A9es+d%E2%80%99%C3%89tudes+sur+l) [our card](https://md.research.elamur.ai/free/papers/han-2020-comparing-ptb-ud-information-pdtb/)
7. Jet Hoek, Jacqueline Evers-Vermeul, and Ted JM Sanders. 2018. Segmenting discourse: Incorporating interpretation into segmentation? Corpus Linguistics and Linguistic Theory, 14(2):357–386. [find](https://scholar.google.com/scholar?q=Jet+Hoek%2C+Jacqueline+Evers%2DVermeul%2C+and+Ted+JM+Sanders%2E+2018%2E+Segmenting+discourse%3A+Incorporating+interpretation+into+segmentation%3F+Corpus+Linguistics+and+Linguistic+Theory%2C+14%282%29%3A357%E2%80%93386%2E)
8. Yangfeng Ji, Gholamreza Haffari, and Jacob Eisenstein. 2016. A latent variable recurrent neural network for discourse-driven language models. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 332–… [find](https://scholar.google.com/scholar?q=Yangfeng+Ji%2C+Gholamreza+Haffari%2C+and+Jacob+Eisenstein%2E+2016%2E+A+latent+variable+recurrent+neural+network+for+discourse%2Ddriven+language+models%2E+In+Proceedings+of+the+2016+Conference+of+the+North+America)
9. Jeffrey L Kallen and John Monfries Kirk. 2008. ICE-Ireland: A User’s Guide: Documentation to Accompany the Ireland Component of the International Corpus of English (ICE-Ireland). Cló Ollscoil na Banríona. [find](https://scholar.google.com/scholar?q=Jeffrey+L+Kallen+and+John+Monfries+Kirk%2E+2008%2E+ICE%2DIreland%3A+A+User%E2%80%99s+Guide%3A+Documentation+to+Accompany+the+Ireland+Component+of+the+International+Corpus+of+English+%28ICE%2DIreland%29%2E+Cl%C3%B3+Ollscoil+na+Banr%C3%AD)
10. Najoung Kim, Song Feng, Chulaka Gunasekara, and Luis Lastras. 2020. Implicit discourse relation classification: We need to talk about evaluation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5404– 5414. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Najoung+Kim%2C+Song+Feng%2C+Chulaka+Gunasekara%2C+and+Luis+Lastras%2E+2020%2E+Implicit+discourse+relation+classification%3A+We+need+to+talk+about+evaluation%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Assoc) [our card](https://md.research.elamur.ai/free/papers/kim-2020-implicit-discourse-relation-classification-we/)
11. René Knaebel and Manfred Stede. 2020. Contextualized embeddings for connective disambiguation in shallow discourse parsing. In Proceedings of the First Workshop on Computational Approaches to Discourse, pages 65–75, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ren%C3%A9+Knaebel+and+Manfred+Stede%2E+2020%2E+Contextualized+embeddings+for+connective+disambiguation+in+shallow+discourse+parsing%2E+In+Proceedings+of+the+First+Workshop+on+Computational+Approaches+to+Discours) [our card](https://md.research.elamur.ai/free/papers/knaebel-2020-contextualized-embeddings-connective-disambiguation-shallow/)
12. Murathan Kurfalı and Robert Östling. 2021. Let’s be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction. arXiv preprint arXiv:2106.03192. [find](https://scholar.google.com/scholar?q=Murathan+Kurfal%C4%B1+and+Robert+%C3%96stling%2E+2021%2E+Let%E2%80%99s+be+explicit+about+that%3A+Distant+supervision+for+implicit+discourse+relation+classification+via+connective+prediction%2E+arXiv+preprint+arXiv%3A2106%2E03192%2E) [our card](https://md.research.elamur.ai/free/papers/kurfal-2021-let-s-be-explicit-about/)
13. Majid Laali and Leila Kosseim. 2014. Inducing discourse connectives from parallel texts. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pages 610–619. [find](https://scholar.google.com/scholar?q=Majid+Laali+and+Leila+Kosseim%2E+2014%2E+Inducing+discourse+connectives+from+parallel+texts%2E+In+Proceedings+of+COLING+2014%2C+the+25th+International+Conference+on+Computational+Linguistics%3A+Technical+Papers) [our card](https://md.research.elamur.ai/free/papers/laali-2014-inducing-discourse-connectives-parallel-texts/)
14. Man Lan, Jianxiang Wang, Yuanbin Wu, Zheng-Yu Niu, and Haifeng Wang. 2017. Multi-task attention-based neural networks for implicit discourse relationship representation and identification. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1299– 1308, Co… [find](https://scholar.google.com/scholar?q=Man+Lan%2C+Jianxiang+Wang%2C+Yuanbin+Wu%2C+Zheng%2DYu+Niu%2C+and+Haifeng+Wang%2E+2017%2E+Multi%2Dtask+attention%2Dbased+neural+networks+for+implicit+discourse+relationship+representation+and+identification%2E+In+Proceedi) [our card](https://md.research.elamur.ai/free/papers/lan-2017-multi-task-attention-based-neural/)
15. Ziheng Lin, Hwee Tou Ng, and Min-Yen Kan. 2014. A PDTB-styled end-to-end discourse parser. Natural Language Engineering, 20(2):151–184. [find](https://scholar.google.com/scholar?q=Ziheng+Lin%2C+Hwee+Tou+Ng%2C+and+Min%2DYen+Kan%2E+2014%2E+A+PDTB%2Dstyled+end%2Dto%2Dend+discourse+parser%2E+Natural+Language+Engineering%2C+20%282%29%3A151%E2%80%93184%2E)
16. Marian Marchal, Merel CJ Scholman, and Vera Demberg. 2021. Semi-automatic discourse annotation in a low-resource language: Developing a connective lexicon for Nigerian Pidgin. In Proceedings of the Second Workshop on Computational Approaches to Discourse. [find](https://scholar.google.com/scholar?q=Marian+Marchal%2C+Merel+CJ+Scholman%2C+and+Vera+Demberg%2E+2021%2E+Semi%2Dautomatic+discourse+annotation+in+a+low%2Dresource+language%3A+Developing+a+connective+lexicon+for+Nigerian+Pidgin%2E+In+Proceedings+of+the+Se)
17. Rashmi Prasad, Susan McRoy, Nadya Frid, Aravind Joshi, and Hong Yu. 2011. The biomedical discourse relation bank. BMC bioinformatics, 12(1):1– 18. [find](https://scholar.google.com/scholar?q=Rashmi+Prasad%2C+Susan+McRoy%2C+Nadya+Frid%2C+Aravind+Joshi%2C+and+Hong+Yu%2E+2011%2E+The+biomedical+discourse+relation+bank%2E+BMC+bioinformatics%2C+12%281%29%3A1%E2%80%93+18%2E)
18. Balaji Polepalli Ramesh and Hong Yu. 2010. Identifying discourse connectives in biomedical text. In AMIA Annual Symposium Proceedings, volume 2010, page 657. American Medical Informatics Association. [find](https://scholar.google.com/scholar?q=Balaji+Polepalli+Ramesh+and+Hong+Yu%2E+2010%2E+Identifying+discourse+connectives+in+biomedical+text%2E+In+AMIA+Annual+Symposium+Proceedings%2C+volume+2010%2C+page+657%2E+American+Medical+Informatics+Association%2E)
19. Ines Rehbein, Merel Scholman, and Vera Demberg. 2016. Annotating discourse relations in spoken language: A comparison of the PDTB and CCR frameworks. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 1039–1046, Portorož, Slovenia. European Lan… [find](https://scholar.google.com/scholar?q=Ines+Rehbein%2C+Merel+Scholman%2C+and+Vera+Demberg%2E+2016%2E+Annotating+discourse+relations+in+spoken+language%3A+A+comparison+of+the+PDTB+and+CCR+frameworks%2E+In+Proceedings+of+the+Tenth+International+Conferen) [our card](https://md.research.elamur.ai/free/papers/rehbein-2016-annotating-discourse-relations-spoken-language/)
20. Diego Xavier Roman, Allison Briceño, Hannah Rohde, and Stephanie Hironaka. 2016. Linguistic cohesion in middle-school texts: A comparison of logical connectives usage in science and social studies textbooks. The Electronic Journal for Research in Science & Mathematics Education, 20(6). [find](https://scholar.google.com/scholar?q=Diego+Xavier+Roman%2C+Allison+Brice%C3%B1o%2C+Hannah+Rohde%2C+and+Stephanie+Hironaka%2E+2016%2E+Linguistic+cohesion+in+middle%2Dschool+texts%3A+A+comparison+of+logical+connectives+usage+in+science+and+social+studies+tex)
21. Wei Shi and Vera Demberg. 2019. Learning to explic-itate connectives with Seq2Seq network for implicit discourse relation classification. In Proceedings of the 13th International Conference on Computational Semantics - Long Papers, pages 188–199, Gothenburg, Sweden. Association for Computational Lin… [find](https://scholar.google.com/scholar?q=Wei+Shi+and+Vera+Demberg%2E+2019%2E+Learning+to+explic%2Ditate+connectives+with+Seq2Seq+network+for+implicit+discourse+relation+classification%2E+In+Proceedings+of+the+13th+International+Conference+on+Computa)
22. Jianxiang Wang and Man Lan. 2015. A refined end-to-end discourse parser. In Proceedings of the Nineteenth Conference on Computational Natural Language Learning - Shared Task, pages 17–24, Beijing, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jianxiang+Wang+and+Man+Lan%2E+2015%2E+A+refined+end%2Dto%2Dend+discourse+parser%2E+In+Proceedings+of+the+Nineteenth+Conference+on+Computational+Natural+Language+Learning+%2D+Shared+Task%2C+pages+17%E2%80%9324%2C+Beijing%2C+Chi) [our card](https://md.research.elamur.ai/free/papers/wang-2015-refined-end-end-discourse-parser/)
23. Bonnie Webber, Rashmi Prasad, Alan Lee, and Aravind Joshi. 2019. The Penn Discourse Treebank 3.0 annotation manual. Philadelphia, University of Pennsylvania. [find](https://scholar.google.com/scholar?q=Bonnie+Webber%2C+Rashmi+Prasad%2C+Alan+Lee%2C+and+Aravind+Joshi%2E+2019%2E+The+Penn+Discourse+Treebank+3%2E0+annotation+manual%2E+Philadelphia%2C+University+of+Pennsylvania%2E)
24. Allen Nie, Erin Bennett, and Noah Goodman. 2019. DisSent: Learning sentence representations from explicit discourse relations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4497–4510, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Allen+Nie%2C+Erin+Bennett%2C+and+Noah+Goodman%2E+2019%2E+DisSent%3A+Learning+sentence+representations+from+explicit+discourse+relations%2E+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+for+Computat) [our card](https://md.research.elamur.ai/free/papers/nie-2019-dissent-learning-sentence-representations-explicit/)
25. Deniz Zeyrek, Amália Mendes, Yulia Grishina, Murathan Kurfalı, Samuel Gibbon, and Maciej Ogrodniczuk. 2019. Ted multilingual discourse bank (ted-mdb): a parallel corpus annotated in the pdtb style. Language Resources and Evaluation, pages 1–27. [find](https://scholar.google.com/scholar?q=Deniz+Zeyrek%2C+Am%C3%A1lia+Mendes%2C+Yulia+Grishina%2C+Murathan+Kurfal%C4%B1%2C+Samuel+Gibbon%2C+and+Maciej+Ogrodniczuk%2E+2019%2E+Ted+multilingual+discourse+bank+%28ted%2Dmdb%29%3A+a+parallel+corpus+annotated+in+the+pdtb+style%2E+La)
26. Emily Pitler and Ani Nenkova. 2009. Using syntax to disambiguate explicit discourse connectives in text. In Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pages 13–16, Suntec, Singapore. Association for Computational Linguistics. [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+In+Proceedings+of+the+ACL%2DIJCNLP+2009+Conference+Short+Papers%2C+pages+13%E2%80%9316%2C+Suntec%2C+Singapore%2E+) [our card](https://md.research.elamur.ai/free/papers/pitler-2009-syntax-disambiguate-explicit-discourse-connectives/)
27. Yukun Zhu, Ryan Kiros, Rich Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, and Sanja Fidler. 2015. Aligning books and movies: Towards story-like visual explanations by watching movies and reading books. In Proceedings of the IEEE international conference on computer vision, pages 19–… [find](https://scholar.google.com/scholar?q=Yukun+Zhu%2C+Ryan+Kiros%2C+Rich+Zemel%2C+Ruslan+Salakhutdinov%2C+Raquel+Urtasun%2C+Antonio+Torralba%2C+and+Sanja+Fidler%2E+2015%2E+Aligning+books+and+movies%3A+Towards+story%2Dlike+visual+explanations+by+watching+movies+) [our card](https://md.research.elamur.ai/free/papers/zhu-2015-aligning-books-movies-towards-story/)
28. Rashmi Prasad, Nikhil Dinesh, Alan Lee, Eleni Milt-sakaki, Livio Robaldo, Aravind Joshi, and Bonnie Webber. 2008. The Penn Discourse TreeBank 2.0. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08), Marrakech, Morocco. European Language Resources Asso… [find](https://scholar.google.com/scholar?q=Rashmi+Prasad%2C+Nikhil+Dinesh%2C+Alan+Lee%2C+Eleni+Milt%2Dsakaki%2C+Livio+Robaldo%2C+Aravind+Joshi%2C+and+Bonnie+Webber%2E+2008%2E+The+Penn+Discourse+TreeBank+2%2E0%2E+In+Proceedings+of+the+Sixth+International+Conference+) [our card](https://md.research.elamur.ai/free/papers/disc-2008-prasad-penn-discourse-treebank-2-0/)