---
title: "Studying the Lexicon of Dialogue Acts — Novielli 2010"
description: "The paper looks at which lexical signals mark different dialogue acts (DAs), the communicative purpose of an utterance such… 31 references."
authors: ["Nicole Novielli", "Carlo Strapparava"]
year: 2010
venue: "Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)"
source: "https://aclanthology.org/L10-1275/"
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/novielli-2010-studying-lexicon-dialogue-acts/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/novielli-2010-studying-lexicon-dialogue-acts/)

[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/page/2/) / Studying the Lexicon of Dialogue Acts

# Studying the Lexicon of Dialogue Acts

**Authors:** Nicole Novielli and [Carlo Strapparava](https://md.research.elamur.ai/free/en/authors/carlo-strapparava/) · **Year:** 2010 · **Venue:** [Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)](https://md.research.elamur.ai/free/en/venues/lrec/) ([LREC 2010](https://md.research.elamur.ai/free/en/venues/lrec/2010/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **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/L10-1275/) · [PDF](https://aclanthology.org/L10-1275.pdf) · [OpenAlex](https://openalex.org/W55482865)

**Citations:** 2 citations (OpenAlex, 2026-10-14)

## Summary
The paper looks at which lexical signals mark different dialogue acts (DAs), the communicative purpose of an utterance such as asking, stating, opining, agreeing or thanking. The authors' longer-term aim is an unsupervised DA tagger that relies only on word meaning. They use the DA-annotated part of the Switchboard telephone corpus and collapse its SWBD-DAMSL tags into nine domain-independent labels.

They first summarise their earlier experiments. A supervised SVM is compared with an unsupervised method that represents both utterances and small hand-picked seed sets for each act in an LSA space and assigns the closest act. Both are tested on English and on an Italian corpus.

The new contributions are two qualitative analyses:
- **Affective load per DA**, measured with WordNet Affect inside a BNC-derived LSA space.
- **Salient LIWC word classes per DA**, ranked by a dominance score.

Opinions and politeness acts turn out to be the most emotionally charged. Statements and opinions, the pair the classifier confuses most, differ clearly in tense, pronouns and verb types. These findings point to concrete features for better DA recognition.

## Key points
- **Data:** the annotated Switchboard portion has 1155 dialogues, about 205,000 utterances and 1.4M words. After mapping to the nine labels there are 131,265 cases, and STATEMENT dominates with 57%.
- **Earlier results (summarised here):**
  - SVM: F1 of .77 for English and .71 for Italian, against majority-label baselines of 57% and 37%.
  - Unsupervised LSA+seeds: F1 of .68 for English and .66 for Italian, against an 11% random baseline.
  - In both settings the input was lemma#POS units, and the same seeds were used for both languages.
- **Main error:** many utterances are wrongly tagged STATEMENT, especially S-OPINION. Long statements tend to contain cue words that belong to other acts.
- **Affective load:** S-OPINION has the highest affective load, followed closely by KIND-ATT, which is driven by politeness formulas.
- **Dominant LIWC classes:**
  - AGREE-ACCEPT: ASSENT (75.32).
  - REJECT: NEGATE (14.54).
  - OPENING: COMM (27.65).
  - CLOSING: HEAR (8.10).
  - STATEMENT: PAST (2.17).
  - S-OPINION: FUTURE (2.00) plus negative emotion.
  - INFO-REQ: YOU (3.73).

## Interesting ideas
- Each act is defined by a tiny, domain-free seed lexicon based purely on its communicative function, and an utterance is labelled by its closeness to these prototypes, with no training labels at all.
- A fine-grained annotation scheme is collapsed into a small domain-independent label set through an explicit mapping table, so an existing corpus becomes reusable for a new inventory.
- Interpretable word-class dominance profiles are used to explain why two labels get confused: statements lean on past tense, first person and motion/perception verbs, while opinions lean on future tense, feeling and cognition verbs.
- The finding that long statements swallow cues of other acts suggests that the act should be tied to where the cue occurs, not to the whole utterance.
- The evaluation reports a majority-label baseline for the supervised setting and a random baseline for the unsupervised one, and reuses the same seeds across two languages to test generality.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (frames): prag could hold explicit, inspectable seed lists per speech act, but match them only at tree-licensed positions (main predicate, sentence mood) so the decision stays explainable instead of bag-like.
- **I2** (learn): a similar SWBD-DAMSL→Mova speech-act mapping could turn Switchboard into silver training and evaluation data for prag at almost no cost.
- **I3** (frames): opinion-vs-statement can be decided from the tense of the main verb and whether it is a cognition or feeling predicate in the UD tree, with the reason reported as the explanation.
- **I4** (frames): assign speech acts per clause using the dependency tree, so an embedded "I think" or an agreement token does not relabel an entire narrative turn.
- **I5** (learn): speech-act evaluations should always include these trivial baselines as negative controls, and seed lexicons can be checked for over-fitting by running them on a second genre.

*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

- [Istituto per la Ricerca Scientifica e Tecnologica](https://md.research.elamur.ai/free/en/labs/istituto-per-la-ricerca-scientifica-e-tecnologica/) — Research institute, Trento, Italy · 6 works · 2,436 citations
- [University of Bari Aldo Moro](https://md.research.elamur.ai/free/en/universities/university-of-bari-aldo-moro/) — University, Bari, Italy · 3 works · 2,189 citations

📚 Shelves (4): [🖥️ 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

🧭 Topics (2): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 401 works · [💬 Speech act theory](https://md.research.elamur.ai/free/en/topics/speech-act-theory/) · 160 works

## Cite

Cite as: Nicole Novielli and Carlo Strapparava. 2010. Studying the Lexicon of Dialogue Acts. Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10).

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

```bibtex
@inproceedings{novielli2010studying,
  title = {{Studying the Lexicon of Dialogue Acts}},
  author = {Nicole Novielli and Carlo Strapparava},
  booktitle = {Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)},
  year = {2010},
  doi = {10.63317/469jm45yo9ao},
  url = {https://doi.org/10.63317/469jm45yo9ao}
}
```

- [← previous Cooperation for Arabic Language Resources and Tools –- The MEDAR Project](https://md.research.elamur.ai/free/en/papers/maegaard-2010-cooperation-arabic-language-resources-tools/)
- [next → "Mind your p's and q's": or the peregrinations of an apostrophe in 17th Century English](https://md.research.elamur.ai/free/en/papers/piton-2010-mind-p-s-q-s/)
- [↑ back to papers of 2010](https://md.research.elamur.ai/free/en/papers/2010/page/2/)

## References

31 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. J. Austin. 1962. How to do Things with Words. Oxford University Press, New York. [find](https://scholar.google.com/scholar?q=J%2E+Austin%2E+1962%2E+How+to+do+Things+with+Words%2E+Oxford+University+Press%2C+New+York%2E)
2. M. Berry. 1992. Large-scale sparse singular value computations. International Journal of Supercomputer Applications, 6(1). [↗](https://doi.org/10.1177/109434209200600103)
3. W. Bosma and E. André. 2004. Exploiting emotions to disambiguate dialogue acts. In IUI ’04: Proceedings of the 9th international conference on Intelligent user interfaces, pages 85–92, New York, NY, USA. ACM. [find](https://scholar.google.com/scholar?q=W%2E+Bosma+and+E%2E+Andre%CC%81%2E+2004%2E+Exploiting+emotions+to+disambiguate+dialogue+acts%2E+In+IUI+%E2%80%9904%3A+Proceedings+of+the+9th+international+conference+on+Intelligent+user+interfaces%2C+pages+85%E2%80%9392%2C+New+York%2C+NY%2C+)
4. G. Clarizio, I. Mazzotta, N. Novielli, and F. deRosis. 2006. Social attitude towards a conversational character. In Proceedings of the 15th IEEE International Symposium on Robot and Human Interactive Communication, pages 2–7, Hatfield, UK, September. [find](https://scholar.google.com/scholar?q=G%2E+Clarizio%2C+I%2E+Mazzotta%2C+N%2E+Novielli%2C+and+F%2E+deRosis%2E+2006%2E+Social+attitude+towards+a+conversational+character%2E+In+Proceedings+of+the+15th+IEEE+International+Symposium+on+Robot+and+Human+Interactive+)
5. P. R. Cohen and H. J. Levesque. 1995. Communicative actions for artificial agents. In in Proceedings of the First International Conference on Multi-Agent Systems, pages 65–72. AAAI Press. [find](https://scholar.google.com/scholar?q=P%2E+R%2E+Cohen+and+H%2E+J%2E+Levesque%2E+1995%2E+Communicative+actions+for+artificial+agents%2E+In+in+Proceedings+of+the+First+International+Conference+on+Multi%2DAgent+Systems%2C+pages+65%E2%80%9372%2E+AAAI+Press%2E)
6. C. Conati. 2002. Probabilistic assessment of user’s emotions in educational games. Applied Artificial Intelligence, 16:555–575. [↗](https://doi.org/10.1080/08839510290030390)
7. M. Core and J. Allen. 1997. Coding dialogs with the DAMSL annotation scheme. In Working Notes of the AAAI Fall Symposium on Communicative Action in Humans and Machines, pages 28–35, Cambridge, MA, November. [find](https://scholar.google.com/scholar?q=M%2E+Core+and+J%2E+Allen%2E+1997%2E+Coding+dialogs+with+the+DAMSL+annotation+scheme%2E+In+Working+Notes+of+the+AAAI+Fall+Symposium+on+Communicative+Action+in+Humans+and+Machines%2C+pages+28%E2%80%9335%2C+Cambridge%2C+MA%2C+Nov)
8. A. Gliozzo and C. Strapparava. 2005. Domains kernels for text categorization. In Proc. of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005), pages 56–63, University of Michigan, Ann Arbor, June. [find](https://scholar.google.com/scholar?q=A%2E+Gliozzo+and+C%2E+Strapparava%2E+2005%2E+Domains+kernels+for+text+categorization%2E+In+Proc%2E+of+the+Ninth+Conference+on+Computational+Natural+Language+Learning+%28CoNLL%2D2005%29%2C+pages+56%E2%80%9363%2C+University+of+Michi)
9. J. Godfrey, E. Holliman, and J. McDaniel. 1992. SWITCHBOARD: Telephone speech corpus for research and development. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 517–520, San Francisco, CA. IEEE. [find](https://scholar.google.com/scholar?q=J%2E+Godfrey%2C+E%2E+Holliman%2C+and+J%2E+McDaniel%2E+1992%2E+SWITCHBOARD%3A+Telephone+speech+corpus+for+research+and+development%2E+In+Proceedings+of+the+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+P)
10. D. Jurafsky, E. Shriberg, and D. Biasca. 1997. Switchboard SWBD-DAMSL shallow-discourse-function annotation coders manual, draft 13. Technical Report 97-01, University of Colorado Institute of Cognitive Science. [find](https://scholar.google.com/scholar?q=D%2E+Jurafsky%2C+E%2E+Shriberg%2C+and+D%2E+Biasca%2E+1997%2E+Switchboard+SWBD%2DDAMSL+shallow%2Ddiscourse%2Dfunction+annotation+coders+manual%2C+draft+13%2E+Technical+Report+97%2D01%2C+University+of+Colorado+Institute+of+Cogniti)
11. T. K. Landauer, P. Foltz, and D. Laham. 1998. Introduction to latent semantic analysis. Discourse Processes, 25. [find](https://scholar.google.com/scholar?q=T%2E+K%2E+Landauer%2C+P%2E+Foltz%2C+and+D%2E+Laham%2E+1998%2E+Introduction+to+latent+semantic+analysis%2E+Discourse+Processes%2C+25%2E)
12. R. Mihalcea and S. Pulman. 2009. Linguistic ethnography: Identifying dominant word classes in text. In Proceeding of Computational Linguistics and Intelligent Text Processing (CICLing-09). [find](https://scholar.google.com/scholar?q=R%2E+Mihalcea+and+S%2E+Pulman%2E+2009%2E+Linguistic+ethnography%3A+Identifying+dominant+word+classes+in+text%2E+In+Proceeding+of+Computational+Linguistics+and+Intelligent+Text+Processing+%28CICLing%2D09%29%2E)
13. N. Novielli and C. Strapparava. 2009. Towards unsupervised recognition of dialogue acts. In NAACL HLT 2009, Student Research Workshop. [find](https://scholar.google.com/scholar?q=N%2E+Novielli+and+C%2E+Strapparava%2E+2009%2E+Towards+unsupervised+recognition+of+dialogue+acts%2E+In+NAACL+HLT+2009%2C+Student+Research+Workshop%2E)
14. B. Pang and L. Lee. 2008. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, 2(1-2):1–135. [↗](https://doi.org/10.1561/9781601981516)
15. J. Pennebaker and M. Francis. 2001. Linguistic inquiry and word count: LIWC. Erlbaum Publishers. [find](https://scholar.google.com/scholar?q=J%2E+Pennebaker+and+M%2E+Francis%2E+2001%2E+Linguistic+inquiry+and+word+count%3A+LIWC%2E+Erlbaum+Publishers%2E)
16. E. Pianta, C. Girardi, and R. Zanoli. 2008. The TextPro tool suite. In Proceedings of LREC-08, Marrakech, Morocco, May. [find](https://scholar.google.com/scholar?q=E%2E+Pianta%2C+C%2E+Girardi%2C+and+R%2E+Zanoli%2E+2008%2E+The+TextPro+tool+suite%2E+In+Proceedings+of+LREC%2D08%2C+Marrakech%2C+Morocco%2C+May%2E)
17. R. W. Picard and J. Klein. 2001. Computers that recognise and respond to user emotion: Theoretical and practical implications. Technical report, MIT Media Lab. [↗](https://doi.org/10.1016/s0953-5438(01)00055-8)
18. M. Poesio and A. Mikheev. 1998. The predictive power of game structure in dialogue act recognition: Experimental results using maximum entropy estimation. In Proceedings of ICSLP-98, Sydney, December. [find](https://scholar.google.com/scholar?q=M%2E+Poesio+and+A%2E+Mikheev%2E+1998%2E+The+predictive+power+of+game+structure+in+dialogue+act+recognition%3A+Experimental+results+using+maximum+entropy+estimation%2E+In+Proceedings+of+ICSLP%2D98%2C+Sydney%2C+December%2E)
19. R. Power. 1979. The organisation of purposeful dialogues. Linguistics, 17:107–152. [↗](https://doi.org/10.1515/ling.1979.17.1-2.107)
20. N. Reithinger, M. Kipp, R. Engel, and M. Klesen. 1996. Predicting dialogue acts for a speech-to-speech translation system. In Proceedings of the International Conference on Spoken Language Processing, pages 654–657. [↗](https://doi.org/10.22028/d291-25293)
21. H. Sacks, E. Schegloff, and G. Jefferson. 1974. A simplest systematics for the organization of turn-taking for conversation. Language, 50(4):696–735. [↗](https://doi.org/10.2307/412243)
22. K. Samuel, S. Carberry, and K. Vijay-Shanker. 1998. [Dialogue act tagging with transformation-based learning](https://md.research.elamur.ai/free/en/papers/samuel-1998-dialogue-act-tagging-transformation-based/). In Proceedings of the 17th international conference on Computational linguistics, pages 1150–1156, Morristown, NJ, USA. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.cmp-lg/9806006)
23. E. Schegloff. 1968. Sequencing in conversational openings. American Anthropologist, 70:1075–1095. [find](https://scholar.google.com/scholar?q=E%2E+Schegloff%2E+1968%2E+Sequencing+in+conversational+openings%2E+American+Anthropologist%2C+70%3A1075%E2%80%931095%2E)
24. J. Searle. 1969. [Speech Acts](https://md.research.elamur.ai/free/en/papers/searle-1969-speech-acts/): An Essay in the Philosophy of Language. Cambridge University Press, Cambridge, London. [↗](https://doi.org/10.1017/cbo9781139173438)
25. A. Stolcke, N. Coccaro, R. Bates, P. Taylor, C. Van Ess-Dykema, K. Ries, E. Shriberg, D. Jurafsky, R. Martin, and M. Meteer. 2000. [Dialogue act modeling for automatic tagging and recognition of conversational speech](https://md.research.elamur.ai/free/en/papers/stolcke-2000-dialogue-act-modeling-automatic-tagging/). Computational Linguistics, 26(3):339–373. [↗](https://doi.org/10.1162/089120100561737)
26. C. Strapparava and R. Mihalcea. 2007. [SemEval-2007 task 14: Affective Text](https://md.research.elamur.ai/free/en/papers/strapparava-2007-semeval-2007-task-14-affective/). In Proceedings of the 4 th International Workshop on Semantic Evaluations (SemEval 2007), pages 70–74, Prague, June.
27. C. Strapparava and R. Mihalcea. 2008. Learning to identify emotions in text. In SAC ’08: Proceedings of the 2008 ACM symposium on Applied computing, pages 1556–1560, New York, NY, USA. ACM. [find](https://scholar.google.com/scholar?q=C%2E+Strapparava+and+R%2E+Mihalcea%2E+2008%2E+Learning+to+identify+emotions+in+text%2E+In+SAC+%E2%80%9908%3A+Proceedings+of+the+2008+ACM+symposium+on+Applied+computing%2C+pages+1556%E2%80%931560%2C+New+York%2C+NY%2C+USA%2E+ACM%2E)
28. C. Strapparava and A. Valitutti. 2004. [WordNet-Affect: an affective extension of WordNet](https://md.research.elamur.ai/free/en/papers/strapparava-2004-wordnet-affect-affective-extension-wordnet/). In Proceedings of LREC, volume 4, pages 1083–1086.
29. D. Traum. 2000. 20 questions for dialogue act taxonomies. Journal of Semantics, 17(1):7–30. [find](https://scholar.google.com/scholar?q=D%2E+Traum%2E+2000%2E+20+questions+for+dialogue+act+taxonomies%2E+Journal+of+Semantics%2C+17%281%29%3A7%E2%80%9330%2E)
30. V. Vapnik. 1995. The Nature of Statistical Learning Theory. Springer-Verlag. [↗](https://doi.org/10.1007/978-1-4757-2440-0)
31. V. Warnke, R. Kompe, H. Niemann, and E. Nöth. 1997. Integrated dialog act segmentation and classification using prosodic features and language models. In Proceedings of 5th European Conference on Speech Communication and Technology, volume 1, pages 207–210, Rhodes, Greece. [find](https://scholar.google.com/scholar?q=V%2E+Warnke%2C+R%2E+Kompe%2C+H%2E+Niemann%2C+and+E%2E+No%CC%88th%2E+1997%2E+Integrated+dialog+act+segmentation+and+classification+using+prosodic+features+and+language+models%2E+In+Proceedings+of+5th+European+Conference+on+Spe)

*Updated 24 October 2026*