1 / 16

A preliminary classification of dialogue genres

A preliminary classification of dialogue genres. Staffan Larsson Internkonferens 2003. overview. previous typologies Dahlbäck 1997 Allen 2001 3 dimensions of classification moves and infostate dialogue features activity features Allwood’s activity based pragmatics. Goal

dwayne
Download Presentation

A preliminary classification of dialogue genres

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. A preliminary classification of dialogue genres Staffan Larsson Internkonferens 2003

  2. overview • previous typologies • Dahlbäck 1997 • Allen 2001 • 3 dimensions of classification • moves and infostate • dialogue features • activity features • Allwood’s activity based pragmatics

  3. Goal • A classification of dialogue genres • Relevant for development of dialogue systems • Dimensions of classification correlating with dialogue system properties • We will try to correlate our classification with GoDiS information state etc.

  4. Dahlbäck (1997) • modality: spoken/written • kinds of agents: human/computer • interaction: dialogue/monologue • context: spatial, temporal • number & type of tasks • simultaneous? • dialogue-task distance • similarity of dialogue structure – task structure • kinds of shared knowledge exploited • perceptual, linguistic, cultural

  5. Allen et. al. (2001)

  6. discussion • Dahlbäck: several dimensions, but not so relevant for our purpouses • Allen: single dimension of classification • some types of dialogue not included • tutorial • explanatory • instructional • We want a classification • based on several independent dimensions • covering not only information seeking and collaborative planning dialogue

  7. Basic distinction: inquiry vs. action-oriented dialogue • IOD: raising and addressing issues • AOD introduces (non-communicative) actions to performed (requests) • pure AOD vs. AOD+IOD

  8. General dialogue phenomena • grounding & accommodation probably present in all H-H dialogue; not included in classification • negotiation perhaps less frequent

  9. activity-related factors • result type: (what goes in SH.COM and SH.ACTIONS) • simple: proposition, action • complex: plan, proof, explanation • requires incremental construction • proactivity of external process • passive: database, simple device • (pro)active: device, e.g. Robot • this dimension correlates with the way the system is connexted to the device • distribution of decision rights • disjoint: each question can be answered only by one DP (e.g. destination city, price); this DP ”decides” the answer • shared: some question(s) should be answered jointly; negotiation may be needed • so this dimension correlates with negotiation

  10. Possible additional activity-related factors • static/dynamic ext. Process • Correlates with ability to apply updates to resource [is this interesting?] • distribution of information • Symmetric: DPs have same kind of information • Asymmetric: DPs have different kinds of information • Correlates with what? Rules for who should answer which questions? • …?

  11. Allwood’s activity-based pragmatics • Levels of activity/context • Physical: artifacts etc. • Biological • Psychological: beliefs, desires, intentions, … • Social: incl. rights & obligations, communicative and task-related • How do these fit with the proposed activity-related factors? • Distribution of decision rights: social • Proactivity of external process: Physical (Biological? Psychological?) • Result type: Psychological? • Information state components: Psychological and social

  12. comments • The presence of grounding and accommodation may be independent of activity • … but not their form • Make a decision graph which based on activity leads to dialogue genre/properties of system • System properties should be given nonformal but exact formulations that can be used by nonexperts • Correlation to system properties given in table form; correlate with libraries?

  13. More thoughts • Table shows • A classification of activities according to features of a dialogue system needed to particitpate in dialogues in these activities • Very specific activity types; e.g. Dialogue with Panasonic VCR 4500? Which level is right? • Rule libraries come with infostate extensions/requirements, and with additional moves • Requirements not only on structure, but also on how it’s to be used, e.g. What does the order of a queue mean?

  14. more • How feedback is realised • Have different ICM grammars for different kinds of activity • Which factors determine genre-specific ICM? • Written/spoken • Noisiness • Available modalities • How important to be right? AOD->higher requirements on recognition, more checks? • Negotiation (in ”alternatives” sense) not really directly correlated with shared decision rights

  15. More… • Possible additional dimensions • Opposing goals? • Argumentation? • Number of simultaneous tasks (one or several) • Several instances of same task-type simultaneously? • How handle classroom questions?

More Related