Elamur Research⌕
☰
home / papers / 2011 / On Incrementality in Dialogue: Evidence from Compound Contributions

On Incrementality in Dialogue: Evidence from Compound Contributions

Paper · 2011 · Christine Howes, Matthew Purver, Patrick G. T. Healey et al.

Summary

The paper examines compound contributions (CCs): utterances that extend or finish an earlier contribution, whether by the original speaker or someone else. The authors treat CCs as a test case for whether dialogue is processed incrementally. They annotated part of the British National Corpus (BNC) and found that CCs are common. About one in five contributions qualifies, and close to 3% are cross-person completions. Splits can fall inside syntactic constituents, which points to word-by-word incremental parsing and generation. Same-person and cross-person cases differ systematically, which points to pragmatic effects. A second study inserted fake CCs into multi-party text chat. It showed that cross-person completions change who participants expect to speak next and make them perceive the two contributors as a coalition, or "party". It also showed that participants are not interchangeable. The work matters for dialogue systems in two ways. Systems need incremental mechanisms that can build one structure across several speakers' turns. They also need to model higher-level units, such as parties, that affect turn-taking and shared context.

Key points

  • Contributions are defined as stretches of talk bounded by a speaker change, a notable pause, or a sentence end. They follow BNC transcription lines. A CC is one syntactic or propositional unit spread over several such contributions.
  • In the BNC sample, almost 20% of contributions belong to CCs, and nearly 3% are the cross-person kind usually studied.
  • Cross-person CCs more often follow an unfilled pause than a filled one. They also follow an antecedent that could already stand as complete more often than same-person CCs do.
  • Antecedents that were already end-complete:
    • 72% of all corpus CCs versus 37% of arbitrary experimental splits;
    • 74% versus 38% for other-person CCs.
  • In the chat experiment, contradicting the expectations created by a CC led to longer response times. Cross-person CCs changed expectations about turn-taking and party membership. Continuations rarely start as complete units on their own.

Interesting ideas

  • I1. Natural split points are compared against arbitrary, artificially created splits, so the baseline shows what chance would produce.
  • I2. Continuations seldom begin as self-standing units, so their incomplete start is a surface signal that they attach to something earlier.
  • I3. Most continuations extend an antecedent that was already complete, much like adding an adjunct or apposition rather than filling a missing argument.
  • I4. When one person finishes another's sentence, observers infer that the two form a party, so syntax carries social alignment.
  • I5. Antecedent and continuation can be far apart, with intervening material, so matching them is a non-local search.

For Mova

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

  • I1 (learn): Evaluations could add random-split or random-attachment controls, so that any claimed regularity is measured against a chance distribution.
  • I2 (tree): A dialogue parser could flag start-incomplete fragments and try to attach them to the open dependency tree of a prior turn, even across speakers.
  • I3 (back): Generation could produce a complete core clause first and then offer optional extensions, which supports incremental, interruptible output.
  • I4 (world): When reading dialogue in tales, the world model could record alliances when characters complete each other's utterances.
  • I5 (frames): Frame building could keep unfinished frames open across several turns and fill their roles when a later fragment arrives, rather than closing frames at each turn boundary.

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

🎓Stanford UniversityStanford · United States310 works · 284,480 citations🎓Queen Mary University of LondonLondon · United Kingdom39 works · 3,307 citations🎓King's College LondonLondon · United Kingdom19 works · 1,454 citations

📚 Shelves 4 Computer Science · 9,086 works Artificial Intelligence · 8,889 works Arts and Humanities · 9,296 works Language and Linguistics · 9,206 works

🧭 Topics 1 Dialogue systems · 401 works

Cite

Cite as Christine Howes, Matthew Purver, Patrick G. T. Healey, Gregory J. Mills and Eleni Gregoromichelaki. 2011. On Incrementality in Dialogue: Evidence from Compound Contributions. Dialogue & Discourse.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.5087/dad.2011.111

@inproceedings{howes2011incrementality,
  title = {{On Incrementality in Dialogue: Evidence from Compound Contributions}},
  author = {Christine Howes, Matthew Purver, Patrick G. T. Healey, Gregory J. Mills and Eleni Gregoromichelaki},
  booktitle = {Dialogue \& Discourse},
  year = {2011},
  doi = {10.5087/dad.2011.111},
  url = {https://doi.org/10.5087/dad.2011.111}
}

References

48 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. G.A. Ballinger. Using generalized estimating equations for longitudinal data analysis. Organizational Research Methods, 7(2):127–150, 2004. ↗
  2. Harry Bunt. Multifunctionality and multidimensional dialogue semantics. In Proceedings of Dia-Holmia, 13th SEMDIAL Workshop, 2009. find
  3. Lou Burnard. Reference Guide for the British National Corpus (World Edition). Oxford University Computing Services http://www.natcorp.ox.ac.uk/docs/userManual/, 2000. URL http://www.natcorp.ox.ac.uk/docs/userManual/. ↗
  4. Okko Buß, Timo Baumann, and David Schlangen. Collaborating on utterances with a spoken dialogue system using an ISU-based approach to incremental dialogue management. In Proceedings of the SIGDIAL 2010 Conference, pages 233–236, Tokyo, Japan, September 2010. Association for Computational Linguistics. URL http://www.sigdial.org/workshops/workshop11/proc/pdf/SIGDIAL42.pdf. ↗
  5. Ronnie Cann, Ruth Kempson, and Lutz Marten. The Dynamics of Language. Elsevier, Oxford, 2005. find
  6. Jean Carletta. Assessing agreement on classification tasks: The kappa statistic. Computational Linguistics, 22(2):249–255, 1996. ↗ our card
  7. Herbert H. Clark. Using Language. Cambridge University Press, 1996. find
  8. Herbert H. Clark and Jean E. Fox Tree. Using uh and um in spontaneous speaking. Cognition, 84 (1):73–111, 2002. ↗
  9. Jan Peter de Ruiter and Mattia van Dienst. Completing other people’s utterances: evidence for forward modeling in conversation. ms., in preparation. David DeVault, Kenji Sagae, and David Traum. Can I finish? learning when to respond to incremental interpretation results in interactive dialogue. In Proceedings of the SIGDIAL 2009 Conference, pages 11–20, London, UK, September 2009. Association for Computational Linguistics. URL http://www.aclweb.org/anthology/W/W09/W09-3902. ↗
  10. Arash Eshghi. Uncommon ground: The distribution of dialogue contexts. PhD thesis, School of Electronic Engineering and Computer Science, Queen Mary University of London, 2009. find
  11. Raquel Fernández and Jonathan Ginzburg. Non-sentential utterances: A corpus-based study. Traitement Automatique des Langues, 43(2), 2002. find
  12. Victor Ferreira. Is it better to give than to donate? Syntactic flexibility in language production. Journal of Memory and Language, 35:724–755, 1996. find
  13. Barbara A. Fox. Principles shaping grammatical practices: an exploration. Discourse Studies, 9(3): 299, 2007. ↗
  14. Andrew Gargett, Eleni Gregoromichelaki, Ruth Kempson, Matthew Purver, and Yo Sato. Grammar resources for modelling dialogue dynamically. Cognitive Neurodynamics, 3(4):347–363, 2009. ISSN 1871-4080. URL http://dx.doi.org/10.1007/s11571-009-9088-y. ↗
  15. Jonathan Ginzburg and Robin Cooper. Clarification, ellipsis, and the nature of contextual updates in dialogue. Linguistics and Philosophy, 27(3):297–365, 2004. ↗
  16. Eleni Gregoromichelaki, Yo Sato, Ruth Kempson, Andrew Gargett, and Christine Howes. Dialogue modelling and the remit of core grammar. In Proceedings of IWCS, 2009. find
  17. Eleni Gregoromichelaki, Ruth Kempson, Matthew Purver, Greg J. Mills, Ronnie Cann, Wilfried Meyer-Viol, and Pat Healey. Incrementality and intention-recognition in utterance processing. Dialogue and Discourse, to appear, 2011. to appear. ↗ our card
  18. Markus Guhe. Incremental Conceptualization for Language Production. NJ: Lawrence Erlbaum Associates, 2007. find
  19. Makoto Hayashi. Where Grammar and Interaction Meet: A Study of Co-Participant Completion in Japanese Conversation. Human Studies, 22(2):475–499, 1999. ↗
  20. Patrick Healey, Matthew Purver, James King, Jonathan Ginzburg, and Greg Mills. Experimenting with clarification in dialogue. In Proceedings of the 25th Annual Meeting of the Cognitive Science Society, Boston, Massachusetts, August 2003. find
  21. Marja-Liisa Helasvuo. Shared syntax: the grammar of co-constructions. Journal of Pragmatics, 36 (8):1315–1336, 2004. ↗
  22. Ruth Kempson, Wilfried Meyer-Viol, and Dov Gabbay. Dynamic Syntax: The Flow of Language Understanding. Blackwell, 2001. find
  23. Gene H. Lerner. On the syntax of sentences-in-progress. Language in Society, pages 441–458, 1991. ↗
  24. Gene H. Lerner. On the “semi-permeable” character of grammatical units in conversation: Conditional entry into the turn space of another speaker. In Elinor Ochs, Emanuel A. Schegloff, and Sandra A. Thompson, editors, Interaction and grammar, pages 238–276. Cambridge University Press, 1996. find
  25. Gene H. Lerner. Collaborative turn sequences. In Conversation analysis: Studies from the first generation, pages 225–256. John Benjamins, 2004. ↗
  26. Gene H. Lerner and Tomoyo Takagi. On the place of linguistic resources in the organization of talk-in-interaction: A co-investigation of English and Japanese grammatical practices. Journal of Pragmatics, 31(1):49–75, 1999. ↗
  27. Kung-Yee Liang and Scott L. Zeger. Longitudinal data analysis using generalized linear models. Biometrika, 73(1):13, 1986. ISSN 0006-3444. ↗
  28. Tsuyoshi Ono and Sandra A. Thompson. What can conversation tell us about syntax. In P.W. Davis, editor, Alternative Linguistics: Descriptive and Theoretical Modes. Benjamin, 1993. find
  29. Martin Pickering and Simon Garrod. Toward a mechanistic psychology of dialogue. Behavioral and Brain Sciences, 27:169–226, 2004. ↗
  30. Massimo Poesio and Hannes Rieser. Completions, coordination, and alignment in dialogue. Dialogue and Discourse, 1:1–89, 2010. ISSN 2152-9620. URL http://elanguage.net/journals/index.php/dad/article/view/91/512. ↗ our card
  31. Matthew Purver, Jonathan Ginzburg, and Patrick Healey. On the means for clarification in dialogue. In R. Smith and J. van Kuppevelt, editors, Current and New Directions in Discourse & Dialogue, pages 235–255. Kluwer Academic Publishers, 2003. ↗
  32. Matthew Purver, Ronnie Cann, and Ruth Kempson. Grammars as parsers: Meeting the dialogue challenge. Research on Language and Computation, 4(2-3):289–326, 2006. ↗
  33. Kepa Rodrı́guez and David Schlangen. Form, intonation and function of clarification requests in German task-oriented spoken dialogues. In Proceedings of the 8th Workshop on the Semantics and Pragmatics of Dialogue (SEMDIAL), Barcelona, Spain, July 2004. find
  34. Carolyn P. Rosé, Diane Litman, Dumisizwe Bhembe, Kate Forbes, Scott Silliman, Ramesh Srivastava, and Kurt VanLehn. A comparison of tutor and student behavior in speech versus text based tutoring. In Proceedings of the HLT-NAACL 03 workshop on Building educational applications using natural language processing-Volume 2, page 37. Association for Computational Linguistics, 2003. find
  35. Christoph Rühlemann. Conversation in context: a corpus-driven approach. Continuum, 2007. find
  36. Harvey Sacks. Lectures on Conversation. Blackwell, 1992. find
  37. Harvey Sacks, Emanuel A. Schegloff, and Gail Jefferson. A simplest systematics for the organization of turn-taking for conversation. Language, 50(4):696–735, 1974. ↗
  38. Emanuel A. Schegloff. Parties and talking together: Two ways in which numbers are significant for talk-in-interaction. Situated order: Studies in the social organization of talk and embodied activities, pages 31–42, 1995. find
  39. Emanuel A. Schegloff. Turn organization: One intersection of grammar and interaction. In Elinor Ochs, Emanuel A. Schegloff, and Sandra A. Thompson, editors, Interaction and grammar, pages 52–133. Cambridge University Press, 1996. ↗
  40. Emanuel A. Schegloff, Gail Jefferson, and Harvey Sacks. The preference for self-correction in the organization of repair in conversation. Language, 53(2):361–382, 1977. ↗
  41. David Schlangen. From reaction to prediction: Experiments with computational models of turn-taking. In Proceedings of the 9th International Conference on Spoken Language Processing (INTERSPEECH - ICSLP), Pittsburgh, PA, September 2006. find
  42. Michael F. Schober and Susan E. Brennan. Processes of interactive spoken discourse: The role of the partner. Handbook of discourse processes, pages 123–64, 2003. ↗
  43. Gabriel Skantze and David Schlangen. Incremental dialogue processing in a micro-domain. In Proceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009), pages 745–753, Athens, Greece, March 2009. Association for Computational Linguistics. URL http://www.aclweb.org/anthology/E09-1085. ↗
  44. Kristina Skuplik. Satzkooperationen. definition und empirische untersuchung. SFB 360 1999/03, Bielefeld University, 1999. find
  45. Mark Steedman. The Syntactic Process. MIT Press, Cambridge, MA, 2000. ↗
  46. Beatrice Szczepek. Formal Aspects of Collaborative Productions in English Conversation. Interaction and Linguistic Structures (InLiSt), http://www.uni-potsdam.de/u/inlist/issues/17/, 2000a. ↗
  47. Beatrice Szczepek. Functional Aspects of Collaborative Productions in English Conversation. Interaction and Linguistic Structures (InLiSt), http://www.uni-potsdam.de/u/inlist/issues/21/, 2000b. ↗
  48. Hongyin Tao and Michael J. McCarthy. Understanding non-restrictive which-clauses in spoken English, which is not an easy thing. Language Sciences, 23(6):651–677, 2001. ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/howes-2011-incrementality-dialogue-evidence-compound-contributions/