Dialogue Model

I thinked it was difficult for dialogue modelling. Although I had experienced so many mathematical modelling contests. As there were so many uncertain factors in dialogue.
I had collected three papers for the survey about dialogue model.

1. Title: Bridging the Gap Between Dialogue Management and Dialogue Models
Source: Proceedings of the Third SIGdial Workshop on Discourse and Dialogue,Philadelphia, July 2002, pp. 201-210. Association for Computational Linguistics.
Authors: Weiqun Xu and Bo Xu and Taiyi Huang and Hairong Xia
Organization: National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, 100080, P. R. China

2. Title: Probabilistic Dialogue Modelling
Source: Proceedings of the Third SIGdial Workshop on Discourse and Dialogue, Philadelphia, July 2002, pp. 125-128. Association for Computational Linguistics
Authors: Oliver Lemon(1), Prashant Parikh(2), Stanley Peters(1)
Organization: Stanford University(1), University of Pennsylvania(2)

3. Title: Survey of the State of the Art in Human Language Technology
Source: Cambridge Studies In Natural Language Processing Series; Vol. XII-XIII archive
Pages: 513
Editors: Ron Cole, Joseph Mariani, Hans Uszkoreit, Giovanni Batista Varile, Annie Zaenen, Antonio Zampolli, Victor Zue
Year of Publication: 1997
Chapter 6.2 Discourse Modeling
Chapter 6.3 Dialogue Modeling
URL: http://cslu.cse.ogi.edu/HLTsurvey/HLTsurvey.html


------------------------------------------------------------------------------------------
I have read the third one of chapter 6. The reading note is as following:

Chapter 6 Discourse and Dialogue
6.1 Overview
The problems addressed in discourse research aim to answer two general kinds of questions: (1) what information is contained in extended sequences of utterances that goes beyond the meaning of the individual utterances themselves? (2) how does the context in which an utterance is used affect the meaning of the individual utterances, or parts of them?
Computational work in discourse has focused on two different types of discourse: extended texts and dialogues, both spoken and written. Although there are clear overlaps between these---dialogues contain text-like sequences spoken by a single individual and texts may contain dialogues---the current state of the art leads research to focus on different questions for each. In addition, application opportunities and needs are different.
Text and dialogue have, however, two significant commonalities. First is a discourse segment. The segment boundaries need to be detected. Second, discourse research on the interpretation of referring expressions, including pronouns and definite descriptions, and the event reference aspect of verb phrase interpretation also is relevant to both text and dialogue.

6.2 Discourse Modeling
6.2.1 Overview: Discourse and Dialogue
Current approaches to discourse and dialogue from the field of artificial intelligence and computational linguistics are based on four predominant theories of discourse which emerged in the mid- to late-eighties:
[Hobbs1985]:
A theory of discourse coherence based on a small, limited set of coherence relations, applied recursively to discourse segments. This is part of a larger, still-developing theory of the relations between text interpretation and belief systems.
[Grosz and Sidner 1986]:
A tripartite organization of discourse structure according to the focus of attention of the speaker (the attentional state), the structure of the speaker's purposes (the intentional structure) and the structure of sequences of utterances (the linguistic structure); each of these three constituents deal with different aspects of the discourse.
[Mann and Thompson (1987) ]:
A hierarchical organization of text spans, where each span is either the nucleus (central) or satellite (support) of one of a set of discourse relations. This approach is commonly known as Rhetorical Structure Theory (RST).
[McKeown (1985) ]:
A hierarchical organization of discourse around fixed schemata which guarantee coherence and which drive content selection in generation.

[Hobbs1985] and [Grosz and Sidner 1986] are suitable for natural language processing,. However, [Mann and Thompson (1987) ] and [McKeown (1985) ] are more appropriate for natural language generation
One important aspect of dialogues is that the successive utterances which make it up are often interconnected by cross references of various sorts. (Anaphora resolution or coreference resolution)
6.2.2 Discourse Representation Theory(DRT)
Discourse Representation Theory (DRT) (cf. [Kam81,KR93]), a semantic theory developed for the express purpose of representing and computing trans-sentential anaphora and other forms of text cohesion, thus offers itself as a natural semantic framework for the design of sophisticated dialogue systems. DRT has already been used in the design of a number of question-answering systems, some of them of considerable sophistication.
DRT is being used as the semantic representation formalism in VERBMOBIL [Wah93], a project to develop a machine translation system for face-to-face spoken dialogue funded by the German Department of Science and Technology. Here the aim is to integrate DRT-like semantics with the various kinds of pragmatic information that are needed for translation purposes.

There are many implemented systems for discourse understanding and generation. Most involve hybrid approaches, selectively exploiting the power of existing theories. Available systems for handling dialogue tend either to have sophisticated discourse generation coupled to a crude discourse understanding systems or vice versa; attempts at full dialogue systems are only now beginning to appear.

6.3 Dialogue Modeling
6.3.1 Research Goals
Two related, but at times conflicting, research goals are often adopted by researchers of dialogue. First is the goal of developing a theory of dialogue, including, at least, a theory of cooperative task-oriented dialogue. A second research goal is to develop algorithms and procedures to support a computer's participation in a cooperative dialogue.
In general, no consensus exists on the appropriate research goals, methodologies, and evaluation procedures for modeling dialogue.

Three approaches to modeling dialogue---dialogue grammars, plan-based models of dialogue, and joint action theories of dialogue---will be discussed, both from theoretical and practical perspectives.
6.3.2 Dialogue Grammars
This approach is based on the observation that there exist a number of sequencing regularities in dialogue, termed adjacency pairs [SSJ78], describing such facts as that questions are generally followed by answers, proposals by acceptances, etc.
The rules state sequential and hierarchical constraints on acceptable dialogues, just as syntactic grammar rules state constraints on grammatically acceptable strings. The terminal elements of these rules are typically illocutionary act names [Aus62,Sea69], such as request, reply, offer, question, answer, propose, accept, reject, etc. The non-terminals describe various stages of the specific type of dialogue being modeled [SC75], such as initiating, reacting, and evaluating.
Just as syntactic grammar rules can be used in parsing sentences, it is often thought that dialogue grammar rules can be used in parsing the structure of dialogues. With a bottom-up parser and top-down prediction, it is expected that such dialogue grammar rules can predict the set of possible next elements in the sequence, given a prior sequence [GWF90].
The speech acts become the state transition labels. When the state machine variant of a dialogue grammar is used as a control mechanism for a dialogue system, the system first recognizes the user's speech act from the utterance, makes the appropriate transition, and then chooses one of the outgoing arcs to determine the appropriate response to supply. When the system performs an action, it makes the relevant transition, and uses the outgoing arcs from the resulting state to predict the type of response to expect from the user.
In summary, dialogue grammars are a potentially useful computational tool to express simple regularities of dialogue behavior. However, they need to function in concert with more powerful plan-based approaches (described below) in order to provide the input data, and to choose a cooperative system response. As a theory, dialogue grammars are unsatisfying as they provide no explanation of the behavior they describe, i.e., why the actions occur where they do, why they fit together into a unit, etc.

6.3.3 Plan-based Models of Dialogue
Plan-based models are founded on the observation that utterances are not simply strings of words, but rather are the observable performance of communicative actions, or speech acts [Sea69], such as requesting, informing, warning, suggesting, and confirming.
Plan-based theories of communicative action and dialogue [AP80,App85,Car90,CL90,CP79,PA80,Sad91,SI81] assume that the speaker's speech acts are part of a plan, and the listener's job is to uncover and respond appropriately to the underlying plan, rather than just to the utterance..
For example, in response to a customer's question of Where are the steaks you advertised?, a butcher's reply of How many do you want? is appropriate because the butcher has discovered that the customer's plan of getting steaks himself is going to fail. Being cooperative, he attempts to execute a plan to achieve the customer's higher-level goal of having steaks.
based theories of dialogue is to offer a generalization in which dialogue can be treated as a special case of other rational noncommunicative behavior. The primary elements are accounts of planning and plan-recognition, which employ various inference rules, action definitions, models of the mental states of the participants, and expectations of likely goals and actions in the context. The set of actions may include speech acts, whose execution affects the beliefs, goals, commitments, and intentions, of the conversants. Importantly, this model of cooperative dialogue solves problems of indirect speech acts as a side-effect [PA80].
Drawbacks of the Plan-based Approach
Illocutionary Act Recognition is Redundant
Discourse versus Domain Plans
Complexity of Inference
Lack of a Theoretical Base

6.3.4 joint action theories of dialogue
Plan-based approaches that model dialogue simply as a product of the interaction of plan generators and recognizers working in synchrony and harmony, do not explain why addressees ask clarification questions, why they confirm, or even, why they do not simply walk away during a conversation. A new theory of conversation is emerging in which dialogue is regarded as a joint activity, something that agents do together [CWG86,CL91b,GS90,GK93,Loc94,Sch81,Suc87]. The joint action model claims that both parties to a dialogue are responsible for sustaining it. Participating in a dialogue requires the conversants to have at least a joint commitment to understand one another, and these commitments motivate the clarifications and confirmations so frequent in ordinary conversation.

6.3.5 Future Directions
Typical areas in which such models are distinguished from individual plan-based models are dealing with reference and confirmations. Clark and colleagues [CWG86,Cla89] have argued that actual referring behavior cannot be adequately modeled by the simple notion that speakers simply provide noun phrases and listeners identify the referents. Rather, both parties offer noun phrases, refine previous ones, correct misidentifications, etc. They claim that people appear to be following the strategy of minimizing the joint effort involved in successfully referring. Computer models of referring based on this analysis are beginning to be developed [HH92,Edm93]. Theoretical models of joint action [CL91b,CL91a] have been shown to minimize the overall team effort in dynamic, uncertain worlds [JM92]. Thus, if a more general theory of joint action can be applied to dialogue as a special case, an explanation for numerous dialogue phenomena, such as collaboration on reference, confirmations, etc.) will be derivable. Furthermore, such a theory offers the possibility for providing a specification of what dialogue participants should do, which could be used to guide and evaluate dialogue management components for spoken language systems. Finally, future work in this area can also form the basis for protocols for communication among intelligent software agents.