Comparing approaches
description
Transcript of Comparing approaches
![Page 1: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/1.jpg)
Comparing approaches
Part XVIII:
Approaches to dialogue
Peter Kühnlein
![Page 2: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/2.jpg)
Comparing approaches
![Page 3: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/3.jpg)
Parameters for theories
Levin & Moore (1977)Mann (1988)Mann (2002)
Garrod & Pickering (2003)
Grosz & Sidner (1986)
Bratman (1999)
Clark (1996)
A number of theories have been discussed
Comparing approaches
![Page 4: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/4.jpg)
Dialogue games - intuition
Established patterns represented as sets of knowledge structures arecalled dialogue-games dialogue-games (DGs).They capture shared conventional knowledge about communication andthe use of communication to achieve goals
Comparing approaches
![Page 5: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/5.jpg)
Parameters for theories
Levin & Moore (1977) PatternMann (1988)Mann (2002)
Garrod & Pickering (2003)
Grosz & Sidner (1986)
Bratman (1999)
Clark (1996)
A number of theories have been discussed
Comparing approaches
![Page 6: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/6.jpg)
Dialogue and Alignment • Alignment and routinization
A „routine“ is an expression that is „fixed“ to some extent• it has a higher frequency than the frequency of its component words would lead to expect• it has a particular analysis at each level of linguistic representation• highly frequent in dialogue
„Routinization“ establishes routines on the fly:if an interlocutor uses an expression in a particular way, it may become a routine for the purpose of the conversation
Comparing approaches
![Page 7: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/7.jpg)
Parameters for theories
Levin & Moore (1977) PatternMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine
Grosz & Sidner (1986)
Bratman (1999)
Clark (1996)
A number of theories have been discussed
Comparing approaches
![Page 8: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/8.jpg)
(OCP) (f ) (c): (a) ICP initiated DS intending 1. OCP to think DS possesses f 2. OCP to think f correlated in way c with ψ-ing that p 3. OCP to think, on the basis of the fulfillment of 1. and [2.] that ICP intends OCP to think that ICP ψs that p 4. OCP, on the basis of the fulfillment of 3. to think that
ICP ψs that pand (for some cases)5. OCP, on the basis of the fulfillment of 4., himself to ψ that p
By initiating DS ICP meant that *ψp is true iff
ψ in the above formulae names an appropriate propositionalattitude, e.g., belief . * is a „mood marker“.
Comparing approaches
![Page 9: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/9.jpg)
Parameters for theories
Levin & Moore (1977) PatternMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine
Grosz & Sidner (1986) Propertiesof utterances
Bratman (1999)
Clark (1996)
A number of theories have been discussed
Comparing approaches
![Page 10: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/10.jpg)
Conventional language • coordination problem
C 13
Signals are deliberate actions. Some are performed as parts of conventionallanguages like English, Dakota, Japanese, or American Sign Language…
C 70,71
A convention, according to Lewis (1969), is a community's solution to arecurrent coordination problem. … What makes something a convention?According to Lewis, it has these five properties:A convention is:1. a regularity r in behaviour2. partly arbitrary3. that is common ground in a given community C4. as a coordination device5. for a recurrent coordination problem s.
Comparing approaches
![Page 11: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/11.jpg)
Parameters for theories
Levin & Moore (1977) PatternMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine
Grosz & Sidner (1986) Propertiesof utterances
Bratman (1999)
Clark (1996) Convention
A number of theories have been discussed
Comparing approaches
![Page 12: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/12.jpg)
Core Intuitions • Aims & State-of-the-Art
Dialogue is the most basic and natural form of language use
Hence, psycholinguistics should provide an account of the basic languageprocessing mechanisms in dialogue
Thesis: Dialogue is coordinated behaviour in that the representations thatunderly discourse become aligned.
Comparing approaches
![Page 13: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/13.jpg)
Parameters for theories
Levin & Moore (1977) PatternMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine Representation
Grosz & Sidner (1986) Propertiesof utterances
Bratman (1999)
Clark (1996) Convention
A number of theories have been discussed
Comparing approaches
![Page 14: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/14.jpg)
The formal notion of a dialogue game • basic assumptions
- natural dialogue has a recognizable „episodic“ structure and coherence which conform to a set of conventions- virtually all communication is characterizable as goal pursuit activity (broader theoretical perspective)- a dialogue reflects intentions and goal pursuit activity on the part of each participant- goals are consequential over the period of pursuit- goals are regarded as having scopes: intervals over which they prevail- speaker exibits goal pursuit and provides suitable information - hearer has tacit knowledge of possible goal sets - hearer´s knowledge includes relationships between goals (subordination)
Comparing approaches
![Page 15: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/15.jpg)
Parameters for theories
Levin & Moore (1977) Pattern BeliefMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine Representation
Grosz & Sidner (1986) Propertiesof utterances
Bratman (1999)
Clark (1996) Convention
A number of theories have been discussed
Comparing approaches
![Page 16: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/16.jpg)
Conventional language • common ground • shared basis
C 93
The technical notion of common ground was introduced by Robert Stalnaker(1978; cf. Karttunen and Peters, 1975) … Two people's common ground is,in effect, the sum of their mutual, common, or joint knowledge, beliefs, andsuppositions.
C 94
Common ground (shared basis)p is common ground for members of community C if and only if:1. every member of C has information that basis b holds;2. b indicates to every member of C that every member of C has
information that b holds;3. b indicates to members of C that p.
Comparing approaches
![Page 17: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/17.jpg)
Parameters for theories
Levin & Moore (1977) Pattern BeliefMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine Representation
Grosz & Sidner (1986) Propertiesof utterances
Bratman (1999)
Clark (1996) Convention Bel.
A number of theories have been discussed
Comparing approaches
![Page 18: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/18.jpg)
Discourse structure • a structure of intentions
G&S 178
Typically, an ICP will have a number of different kinds of intentions thatlead to initiating the discourse. … The kinds of intentions that can serve as discourse purposes or discourse segment purposes are distinguished fromother intentions by the fact that they are intended to be recognized….Discourse purposes and discourse segment purposes share this propertywith certain utterance-level intentions that Grice (1969) uses in definingutterance meaning.
Comparing approaches
![Page 19: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/19.jpg)
Parameters for theories
Levin & Moore (1977) Pattern BeliefMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine Representation
Grosz & Sidner (1986) Properties Intentionof utterances
Bratman (1999)
Clark (1996) Convention Bel.
A number of theories have been discussed
Comparing approaches
![Page 20: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/20.jpg)
A major goal of [DMT] is to provide a descriptive account for the coherence of a wide diversity of natural dialogues. A dialogue is said to be coherent ifa person who has good access to the dialogue is left with the impressionthat every part of the dialogue contributed to the remainder, or equivalentlythat there are no parts whose presence is not easily explained.
M02, 3-4:
Dialogue coherence arises from the intentions (also called goals) of thedialogue participants.
Comparing approaches
![Page 21: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/21.jpg)
Parameters for theories
Levin & Moore (1977) Pattern Belief IntentionMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine Representation
Grosz & Sidner (1986) Properties Intentionof utterances
Bratman (1999)
Clark (1996) Convention Bel.
A number of theories have been discussed
Comparing approaches
![Page 22: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/22.jpg)
Core Intuitions • Aims & State-of-the-Art
Dialogue is the most basic and natural form of language use
Hence, psycholinguistics should provide an account of the basic languageprocessing mechanisms in dialogue
Thesis: Dialogue is coordinated behaviour in that the representations thatunderly discourse become aligned
The linguistic representations employed by the interlocutors become aligned at many levels of representation
Alignment• is the result of a largely automatic process• greatly simplifies production and comprehension
Comparing approaches
![Page 23: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/23.jpg)
Parameters for theories
Levin & Moore (1977) Pattern Belief IntentionMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine Representation Process
Grosz & Sidner (1986) Properties Intentionof utterances
Bratman (1999)
Clark (1996) Convention Bel.
A number of theories have been discussed
Comparing approaches
![Page 24: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/24.jpg)
The notion of Intention • Commitment
When you intend to perform a certain action φ, you are committed to perform φ. This commitment is at work even in cases where you intend to φ at a considerably later time, say after one year.
The fact to note is to intend something means that your choices have to becompatible with that intention. You can’t consistently intend to φ and performactions that will prevent you from φing. So your intentions will be interdependent in a larger framework.
Call the larger frameworks plans.
Comparing approaches
![Page 25: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/25.jpg)
Parameters for theories
Levin & Moore (1977) Pattern Belief IntentionMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine Representation Process
Grosz & Sidner (1986) Properties Intentionof utterances
Bratman (1999) Intention aspart of plan
Clark (1996) Convention Bel.
A number of theories have been discussed
Comparing approaches
![Page 26: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/26.jpg)
Joint activities • joint actions • joint construal
C 192
Uptake […] presupposes understanding. Although [participant A mightreach] a construal of [participant B's] utterance, is it the one [B]intended – is it the one [B] will accept? I will call this the joint construalproblem. … There is a tight link between the way two people settle on a jointconstrual of a signal (level 3) and the way they propose and take up jointprojects (level 4).
Comparing approaches
![Page 27: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/27.jpg)
Parameters for theories
Levin & Moore (1977) Pattern Belief IntentionMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine Representation Process
Grosz & Sidner (1986) Properties Intentionof utterances
Bratman (1999) Intention aspart of plan
Clark (1996) Convention Bel. Construal
A number of theories have been discussed
Comparing approaches
![Page 28: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/28.jpg)
Conventional language
C 13
Signals are deliberate actions. Some are performed as parts of conventionallanguages like English, Dakota, Japanese, or American Sign Language…
C 75
Languages like English are conventional signaling systems par excellence.Most English speakers, for example, have contingency plans that includethis pairing of conditionals, which I will call a signaling doublet: Speaker: If you intend to denote the cipher naught, you can utter the word zero. Addressee: If a speaker utters the word zero, he or she can be denoting the cipher naught.This doublet happens to be conventional. … It is a coordination device for arecurrent coordination problem – speakers wanting to denote naughtand their addressees wanting to recognize this.
Comparing approaches
![Page 29: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/29.jpg)
Parameters for theories
Levin & Moore (1977) Pattern Belief IntentionMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine Representation Process
Grosz & Sidner (1986) Properties Intentionof utterances
Bratman (1999) Intention aspart of plan
Clark (1996) Convention Bel. Construal Coordination
A number of theories have been discussed
Comparing approaches
![Page 30: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/30.jpg)
A major goal of [DMT] is to provide a descriptive account for the coherence of a wide diversity of natural dialogues. A dialogue is said to be coherent ifa person who has good access to the dialogue is left with the impressionthat every part of the dialogue contributed to the remainder, or equivalentlythat there are no parts whose presence is not easily explained.
M02, 3-4:
Dialogue coherence arises from the intentions (also called goals) of thedialogue participants. It arises especially from the way that the conventionsof dialogue cause the participants to adopt and dismiss groups of intentions.Grouping of intentions is the foundation for coordination of the activities ofdialogue participants.
Comparing approaches
![Page 31: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/31.jpg)
Parameters for theories
Levin & Moore (1977) Pattern Belief Intention PlayingMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine Representation Process
Grosz & Sidner (1986) Properties Intentionof utterances
Bratman (1999) Intention aspart of plan
Clark (1996) Convention Bel. Construal Coordination
A number of theories have been discussed
Comparing approaches
![Page 32: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/32.jpg)
Core Intuitions • Aims & State-of-the-Art
Dialogue is the most basic and natural form of language use
Hence, psycholinguistics should provide an account of the basic languageprocessing mechanisms in dialogue
Thesis: Dialogue is coordinated behaviour in that the representations thatunderly discourse become aligned
Alignment differs from the classical (Lewis, Clark) kind of coordination inthat it is a psychological mechanism, not a strategy in behaviour
Comparing approaches
![Page 33: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/33.jpg)
Parameters for theories
Levin & Moore (1977) Pattern Belief Intention PlayingMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine Representation Process Alignment
Grosz & Sidner (1986) Properties Intentionof utterances
Bratman (1999) Intention aspart of plan
Clark (1996) Convention Bel. Construal Coordination
A number of theories have been discussed
Comparing approaches
![Page 34: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/34.jpg)
G&S 199
Discourse structure • a structure of intentions
The intentions that serve as DP/DSPs are natural extensions of the intentionsthat Grice (1969) considers essential to developing a theory of utterer'smeaning. There is a crucial difference, however, between our use of discourse-level intentions in this paper (and the theory, as developed so far) and Grice'suse of utterance-level intentions. We are not yet addressing the issue of discourse meaning, but are concerned with the role of DP/DSPs in determining discourse structure and in specifying how these intentions can be recognized by an OCP.
Comparing approaches
![Page 35: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/35.jpg)
Parameters for theories
Levin & Moore (1977) Pattern Belief Intention PlayingMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine Representation Process Alignment
Grosz & Sidner (1986) Properties Intention Recognitionof utterances
Bratman (1999) Intention aspart of plan
Clark (1996) Convention Bel. Construal Coordination
A number of theories have been discussed
Comparing approaches
![Page 36: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/36.jpg)
Plans are hierarchically organized. And sometimes plans comprise jointactions by a number of people.
Examples are: Two people dancing together. (This is a good example with all the features.) These two should be said to jointly perform some action.Given that their joint action is constituted by individual actions, it is neverthelessan issue to explain the notion of intending a joint action.
V4: We intend to φ iff 1. I intend that we φ and you intend that we φ,2. each of us intends to φ because of 1 and meshing subplans of 1, and3. 1 is common knowledge among us.
This suggestion doesn’t settle the question whether groups can jointly intendsomething: There are two readings of “we intend” – one distributive, andone collective reading.
The notion of Intention • Jointly intending to act
Comparing approaches
![Page 37: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/37.jpg)
Parameters for theories
Levin & Moore (1977) Pattern Belief Intention PlayingMann (1988)Mann (2002)
Garrod & Pickering (2003) Routine Representation Process Alignment
Grosz & Sidner (1986) Properties Intention Recognitionof utterances
Bratman (1999) Intention as Sharedpart of plan Intentions
Clark (1996) Convention Bel. Construal Coordination
A number of theories have been discussed
Comparing approaches
![Page 38: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/38.jpg)
Coverage wrt the benchmark dialogue
Comparing approaches
![Page 39: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/39.jpg)
(A)Inst: So, jetzt nimmst du
Well, now you takeCnst: eine Schraube
a screw.Inst: eine <-> orangene mit einem
Schlitz.an <-> orange one with a slit
Cnst: Ja. Yes
Coverage wrt the benchmark dialogue
Comparing approaches
![Page 40: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/40.jpg)
(A)Inst: So, jetzt nimmst du
Well, now you takeCnst: eine Schraube
a screw.Inst: eine <-> orangene mit einem
Schlitz.an <-> orange one with a slit
Cnst: Ja. Yes
Available Bolts
Coverage wrt the benchmark dialogue
Comparing approaches
![Page 41: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/41.jpg)
(B)
Inst: Und steckst sie dadurch, also
And you put it through there,
let’s see
Cnst: Von oben.
From the top.
Inst: Von oben, daß also die drei festgeschraubt werden dann.
From the top, so that the three bars get fixed.
Cnst: Ja.
Yes.
Intended Junction
Intended Result
Coverage wrt the benchmark dialogue
Comparing approaches
![Page 42: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/42.jpg)
(A)Inst: Well, now you takeCnst: a screw.Inst: an <-> orange one with a slitCnst: Yes.
(B)Inst: And you put it through there, let’s seeCnst: From the top.Inst: From the top, so that the three bars get fixed.Cnst: Yes.
Coverage wrt the benchmark dialogue
Comparing approaches
![Page 43: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/43.jpg)
Coverage wrt the benchmark dialogue
Levin & Moore (1977)Mann (1988)Mann (2002)
Garrod & Pickering (2003)
Grosz & Sidner (1986)
Bratman (1999)
Clark (1996)
And here are the scores
Comparing approaches
![Page 44: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/44.jpg)
Coverage wrt the benchmark dialogue
Levin & Moore (1977) Idealizations required;Mann (1988)Mann (2002)
Garrod & Pickering (2003)
Grosz & Sidner (1986)
Bratman (1999)
Clark (1996)
And here are the scores
Comparing approaches
![Page 45: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/45.jpg)
Coverage wrt the benchmark dialogue
Levin & Moore (1977) Idealizations required;Mann (1988) relation between segments unclear;Mann (2002)
Garrod & Pickering (2003)
Grosz & Sidner (1986)
Bratman (1999)
Clark (1996)
And here are the scores
Comparing approaches
![Page 46: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/46.jpg)
Coverage wrt the benchmark dialogue
Levin & Moore (1977) Idealizations required;Mann (1988) relation between segments unclear; result not plausibleMann (2002)
Garrod & Pickering (2003)
Grosz & Sidner (1986)
Bratman (1999)
Clark (1996)
And here are the scores
Comparing approaches
![Page 47: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/47.jpg)
Coverage wrt the benchmark dialogue
Levin & Moore (1977) Idealizations required; (directive/action pair not covered;)Mann (1988) relation between segments unclear; result not plausibleMann (2002) (covers directive/action pair)
Garrod & Pickering (2003)
Grosz & Sidner (1986)
Bratman (1999)
Clark (1996)
And here are the scores
Comparing approaches
![Page 48: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/48.jpg)
Coverage wrt the benchmark dialogue
Levin & Moore (1977) Idealizations required; (directive/action pair not covered;)Mann (1988) relation between segments unclear; result not plausibleMann (2002) (covers directive/action pair)
Garrod & Pickering (2003) (too early to decide)
Grosz & Sidner (1986)
Bratman (1999)
Clark (1996)
And here are the scores
Comparing approaches
![Page 49: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/49.jpg)
Coverage wrt the benchmark dialogue
Levin & Moore (1977) Idealizations required; (directive/action pair not covered;)Mann (1988) relation between segments unclear; result not plausibleMann (2002) (covers directive/action pair)
Garrod & Pickering (2003) (too early to decide)
Grosz & Sidner (1986) Idealizations required; stack regime must be changed
Bratman (1999)
Clark (1996)
And here are the scores
Comparing approaches
![Page 50: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/50.jpg)
Coverage wrt the benchmark dialogue
Levin & Moore (1977) Idealizations required; (directive/action pair not covered;)Mann (1988) relation between segments unclear; result not plausibleMann (2002) (covers directive/action pair)
Garrod & Pickering (2003) (too early to decide)
Grosz & Sidner (1986) Idealizations required; stack regime must be changed
Bratman (1999)
Clark (1996)
And here are the scores
Comparing approaches
![Page 51: Comparing approaches](https://reader035.fdocuments.in/reader035/viewer/2022081514/56814ea4550346895dbc4e96/html5/thumbnails/51.jpg)
Coverage wrt the benchmark dialogue
Levin & Moore (1977) Idealizations required; (directive/action pair not covered;)Mann (1988) relation between segments unclear; result not plausibleMann (2002) (covers directive/action pair)
Garrod & Pickering (2003) (too early to decide)
Grosz & Sidner (1986) Idealizations required; stack regime must be changed
Bratman (1999)
Clark (1996) Idealizations required
And here are the scores
Comparing approaches