Elamur Research⌕
☰
home / papers / 2020 / Modelling Structures for Situated Discourse

Modelling Structures for Situated Discourse

Paper · 2020 · Nicholas Asher, Julie Hunter and Kate Thompson

Summary

The paper asks how discourse structure should be modelled when conversation happens inside a changing nonlinguistic environment. The authors use the STAC corpus of multiparty chats from an online version of The Settlers of Catan, annotated in the SDRT framework. Annotation was done in two passes. The first covered only the chat messages. The second added game events taken from the logs, such as dice rolls, trades and robber moves, as full discourse units. The authors argue that game events should not merely attach to utterances through rhetorical relations. Events also relate to one another, and these event-to-event links produce structure that shapes how chat moves are read, giving rise to new kinds of discourse structure and new views of threads and goals. Comparing the two passes shows that adding the situated context reorganises the discourse considerably. Structures built from chat alone rarely keep their role, core or peripheral, once embedded in the situated graphs. This suggests that what drives the conversation's main goals is often not signalled linguistically.

Key points

  • The STAC Settlers corpus is described as the first corpus with full discourse structures for multiparty dialogue situated in a virtual environment.
  • Chat transcripts from 46 games were annotated with the Glozz tool. Logs were split into "dialogues" built around bargaining sessions.
  • Chat-only annotations came first. Situated annotations, with game events as arguments of relations such as Result, were added afterwards. New game messages got sequence IDs so the original turn numbering stayed intact.
  • Of 296 core-only chat structures, only 23% kept core type in the situated graphs.
  • For asymmetric structures, only 4% showed perfect type preservation. Across all chat structures, 7% preserved periphery type and 11.5% preserved core type.

Interesting ideas

  • I1. Annotating the same data first without context and then with context turns the context's contribution into a measurable difference, much like an ablation study.
  • I2. Nonlinguistic events can sit in the same graph as speech acts and serve as arguments of the same relations, for example an event causing a reply.
  • I3. Relations between the events themselves, not just event-to-utterance links, form structure that affects how later moves are interpreted.
  • I4. Graph analyses can be compared by structure preservation, checking whether a substructure keeps its core or peripheral role after embedding into a richer graph, rather than by counting matching relation instances.
  • I5. When enriching an existing annotated stream, new items receive sub-identifiers so earlier numbering and alignments stay valid.

For Mova

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

  • I1 (learn): Run the reader with and without the world-of-text state as a built-in negative control, and report how much each answer or link depends on it.
  • I2 (world): Let state changes in the text world be nodes that utterances can relate to, so a character's reply in a fable can link directly to the event it reacts to.
  • I3 (world): Build explicit causal and sequential links among world events, then let frame and speech-act interpretation consult this event structure instead of only the preceding sentence.
  • I4 (learn): When comparing parser witnesses or pipeline versions, measure whether subgraphs keep their role, which catches reorganisations that edge-level agreement scores miss.
  • I5 (learn): Version silver data by adding inserted tokens, events or repairs under derived IDs, so older annotations and evaluations remain comparable across iterations.

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

🔬Centre National de la Recherche ScientifiqueParis · France104 works · 60,877 citations🔬Institut de Recherche en Informatique de ToulouseToulouse · France23 works · 1,667 citations🏢LinagoraToulouse · France4 works · 78 citations

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 works

🧭 Topics 1Research subjects and languages the work is about.Discourse analysis · 394 works

Cite

Cite as Nicholas Asher, Julie Hunter and Kate Thompson. 2020. Modelling Structures for Situated Discourse. Dialogue & Discourse.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.5087/dad.2020.104

@inproceedings{asher2020modelling,
  title = {{Modelling Structures for Situated Discourse}},
  author = {Nicholas Asher, Julie Hunter and Kate Thompson},
  booktitle = {Dialogue \& Discourse},
  year = {2020},
  doi = {10.5087/dad.2020.104},
  url = {https://doi.org/10.5087/dad.2020.104}
}

References

41 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Stergos Afantenos, Nicholas Asher, Farah Benamara, Myriam Bras, Cécile Fabre, Lydia-Mai Ho-Dac, Anne Le Draoulec, Philippe Muller, Marie-Paule Péry-Woodley, Laurent Prévot, Josette Rebeyrolle, Ludovic Tanguy, Marianne Vergez-Couret, and Laure Vieu. An empirical resource for discovering cognitive principles of discourse organisation: the ANNODIS corpus. In The Eight International Conference on Language Resources and Evaluation, pages 2727– 2734, Istanbul, Turkey, May 2012. European Language Resources Association (ELRA). URL http://www.lrec-conf.org/proceedings/lrec2012/index.html. ↗
  2. Stergos Afantenos, Eric Kow, Nicholas Asher, and Jérémy Perret. Discourse parsing for multi-party chat dialogues. In The 2015 Conference on Empirical Methods in Natural Language Processing, pages 928–937, Lisbon, Portugal, September 2015. Association for Computational Linguistics. URL http://aclweb.org/anthology/D15-1109. ↗
  3. Nicholas Asher. Reference to Abstract Objects in Discourse. Kluwer Academic Publishers, 1993. ↗
  4. Nicholas Asher and Alex Lascarides. Logics of Conversation. Cambridge University Press, 2003. find
  5. Nicholas Asher and Soumya Paul. Strategic conversation under imperfect information: epistemic Message Exchange games. Logic, Language and Information, 27(4):343–385, 2018. find
  6. Nicholas Asher, Julie Hunter, Mathieu Morey, Farah Benamara, and Stergos Afantenos. Discourse structure and dialogue acts in multiparty dialogue: the STAC corpus. In The Tenth International Conference on Language Resources and Evaluation, pages 2721–2727, Portorož, Slovenia, May 2016. European Language Resources Association (ELRA). URL http://www.juliejhunter.com/uploads/3/9/6/1/39617901/lrec2016 final.pdf. ↗
  7. Jason Baldridge, Nicholas Asher, and Julie Hunter. Annotation for and robust parsing of discourse structure on unrestricted texts. Zeitschrift fur Sprachwissenschaft, 26:213–239, 2007. ↗
  8. Tom Bartlett. Analyzing Power in Language: A Practical Guide. Routledge, London, 2014. find
  9. Lynn Carlson and Daniel Marcu. Discourse tagging reference manual. ISI Technical Report ISI-TR-545, 54:56, 2001. find
  10. Lynn Carlson, Mary Ellen Okurowski, and Daniel Marcu. RST Discourse Treebank LDC2002T07. Linguistic Data Consortium, University of Pennsylvania, 2002. find
  11. C.C. Chang and H. Jerome Keisler. Model Theory. North Holland Publishing, 1973. find
  12. David Crystal. Internet Linguistics. Routledge, London, 2011. find
  13. Elisa Ferracane, Greg Durrett, Junyi Jessy Li, and Katrin Erk. Evaluating discourse in structured text representations. In The 57th Annual Meeting of the Association for Computational Linguistics, pages 646–653, Florence, Italy, July 2019. Association for Computational Linguistics. URL https://www.aclweb.org/anthology/P19-1062. ↗
  14. Katherine Forbes, Eleni Miltsakaki, Rashmi Prasad, Anoop Sarkar, Aravind K. Joshi, and Bonnie L. Webber. D-LTAG system: Discourse parsing with a lexicalized tree-adjoining grammar. Journal of Logic, Language and Information, 12(3):261–279, 2003. ↗
  15. Jonathan Ginzburg. The Interactive Stance: Meaning for Conversation. Oxford University Press, Oxford, 2012. find
  16. Julie Hunter, Nicholas Asher, Eric Kow, Jérémy Perret, and Stergos Afantenos. Defining the right frontier in multi-party dialogue. In The Semantics and Pragmatics of Dialogue (goDIAL), pages 95–103, Gothenburg, Sweden, August 2015a. URL https://flov.gu.se/digitalAssets/1537/1537599 semdial2015 godial proceedings.pdf. ↗
  17. Julie Hunter, Nicholas Asher, and Alex Lascarides. Integrating non-linguistic events into discourse structure. In The 11th International Conference on Computational Semantics (IWCS), pages 184–194, London, England, April 2015b. URL http://www.aclweb.org/anthology/W15-0123. ↗
  18. Julie Hunter, Nicholas Asher, and Alex Lascarides. A formal semantics for situated conversation. Semantics & Pragmatics, 11(10), 2018. URL https://doi.org/10.3765/sp.11.10. early access. ↗
  19. David Kaplan. Demonstratives. In J. Almog, J. Perry, and H. Wettstein, editors, Themes from Kaplan. Oxford, 1989. find
  20. Yasuhiro Katagiri, Mayumi Bono, and Noriko Suzuki. Conversational inverse information for context-based retrieval of personal experiences. In JSAI’05: Proceedings of the 2005 international conference on New Frontiers in Artificial Intelligence, pages 365–376. find
  21. Alfred Kranstedt, Peter Kühnlein, and Ipke Wachsmuth. Deixis in multimodal human computer interaction: An interdisciplinary approach. In A. Camurri and G. Volpe, editors, Gesture-based Communication in Human-Computer Interaction, pages 112–123. Springer, 2004. find
  22. Geert-Jan M. Kruijff, Pierre Lison, Trevor Benjamin, Henrik Jacobsson, Hendrik Zender, Ivana Kruijff-Korbayová, and Nick Hawes. Situated dialogue processing for human-robot interaction. In H. I. Christensen, G. M. Kruijff, and J. L. Wyatt, editors, Cognitive Systems, pages 311–364. Springer Berlin Heidelberg, Berlin, Heidelberg, 2010. URL http://dx.doi.org/10.1007/978-3-642-11694-0 8. ↗
  23. Alex Lascarides and Nicholas Asher. Agreement, disputes and commitment in dialogue. Journal of Semantics, 26(2):109–158, 2009. find
  24. Alex Lascarides and Matthew Stone. A formal semantic analysis of gesture. Journal of Semantics, 26(4):393–449, 2009. find
  25. William C. Mann and Sandra A. Thompson. Rhetorical structure theory: A framework for the analysis of texts. International Pragmatics Association Papers in Pragmatics, 1:79–105, 1987. find
  26. Jérémy Perret, Stergos Afantenos, Nicholas Asher, and Mathieu Morey. Integer linear programming for discourse parsing. In the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 99– 109, San Diego, California, June 2016. Association for Computational Linguistics. URL http://www.aclweb.org/anthology/N16-1013. ↗
  27. John Perry. Perception, action, and the structure of believing. In R. Grandy and R. Warner, editors, Philosophical Grounds of Rationality, pages 333–361. Oxford, 1986. find
  28. Livia Polanyi. A theory of discourse structure and discourse coherence. In W. H. Eilfort, P. D. Kroeber, and K. L. Peterson, editors, Papers from the General Session at the 21st Regional Meeting of the Chicago Linguistics Society. Chicago Linguistics Society, 1985. find
  29. Livia Polanyi, Chris Culy, Martin van den Berg, Gian Lorenzo Thione, and David Ahn. A rule based approach to discourse parsing. In the 5th SIGdial Workshop on Discourse and Dialogue, pages 108–117, Cambridge, Massachusetts, USA, April 30 - May 1 2004. Association for Computational Linguistics. URL http://www.aclweb.org/anthology/W04-2322. ↗
  30. Paul Portner. The semantics of imperatives within a theory of clause types. In Semantics and Linguistic Theory 14, pages 235–252, Evanston, Illinois, U.S.A., May 2004. URL https://journals.linguisticsociety.org/proceedings/index.php/SALT/article/view/2907. ↗
  31. Christopher Potts. The Logic of Conventional Implicatures. Number 7. Oxford University Press on Demand, 2005. ↗
  32. Rashmi Prasad, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, Livio Robaldo, Aravind Joshi, and Bonnie Webber. The penn discourse treebank 2.0. In The Sixth International Conference on Language Resources and Evaluation, pages 2961 – 2968, Marrakech, Morocco, May 2008. ELRA. URL http://www.lrec-conf.org/proceedings/lrec2008/pdf/754 paper.pdf. ↗
  33. Gert Rickheit and Ipke Wachsmuth. Situated Communication. Walter de Gruyter, 2006. find
  34. Craige Roberts. Information structure in discourse: Towards an integrated formal theory of pragmatics. Semantics and Pragmatics, 5(6):1–69, 2012. ↗
  35. Mandy Simons, Judith Tonhauser, David Beaver, and Craige Roberts. What projects and why. In Semantics and Linguistic Theory 20, pages 309–327, Vancouver, British Columbia, Canada, April 29 - May 1 2010. URL https://journals.linguisticsociety.org/proceedings/index.php/SALT/article/view/2584. ↗
  36. Thora Tenbrink, Kathleen Eberhard, Hui Shi, Sandra Kuebler, and Matthias Scheutz. Annotation of negotiation processes in joint-action dialogues. Dialogue and Discourse, 4(2):185–214, 2013. ↗
  37. Antoine Venant and Nicholas Asher. Dynamics of public commitments in dialogue. In The 11th International Conference on Computational Semantics, pages 272–282, London, England, 2015. Association for Computational Linguistics. URL http://www.aclweb.org/anthology/W/W15/W15-0131. ↗
  38. Antoine Venant, Nicholas Asher, Philippe Muller, Pascal Denis, and Stergos D. Afantenos. Expressivity and comparison of models of discourse structure. In Proceedings of Sigdial 2013, pages 2–11, Metz, France, August 2013. URL https://www.aclweb.org/anthology/W13-40.pdf. ↗
  39. Antoine Venant, Nicholas Asher, and Cedric Degremont. Credibility and its attacks. In The 18th Workshop on the Semantics and Pragmatics of Dialogue, pages 154–162, Edinburgh, Scotland, September 2014. URL http://www.macs.hw.ac.uk/InteractionLab/Semdial/semdial14.pdf. ↗
  40. Antoine Widlöcher and Yann Mathet. La plate–forme GLOZZ : environnement d’annotation et d’exploration de corpus. In la 16e Conférence Traitement Automatique des Langues Naturelles, Senlis, France, June 2009. ATALA, LIPN. URL http://talnarchives.atala.org/TALN/TALN-2009/taln-2009-court-023.pdf. ↗
  41. Florian Wolf and Edward Gibson. Representing discourse coherence: A corpus based study. Computational Linguistics, 31(2):249–287, 2005. 6. Appendix 6.1 Formal definitions for asymmetric structures (Hunter et al., 2018)

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/asher-2020-modelling-structures-situated-discourse/