B. J. Grosz, "The representation and use of focus in a system for understanding dialogs," in Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI '77), pp. 67--76, 1977. Reprinted in [37].  Home/Search   Document Not in Database   Summary   Related Articles   Check

....or semantic networks) and the usefulness of clarification dialogue in disambiguating a user s query. Recent research has addressed various dialogue issues in order to enhance the elegance of the database interactions. Such research includes attempts to resolve anaphoric references in queries [2,4,14,1], to track the user s focus of attention [2,4,14,15] and to generate cooperative responses. In particular, the CO OP system [7] is able to analyze presumptions of the user in order to generate appropriate explanations for answers that may mislead the user. Janas [5] takes a similar approach to ....

....dialogue in disambiguating a user s query. Recent research has addressed various dialogue issues in order to enhance the elegance of the database interactions. Such research includes attempts to resolve anaphoric references in queries [2,4,14,1] to track the user s focus of attention [2,4,14,15], and to generate cooperative responses. In particular, the CO OP system [7] is able to analyze presumptions of the user in order to generate appropriate explanations for answers that may mislead the user. Janas [5] takes a similar approach to generate indirect answers instead of proriding direct ....

Grosz B.J., "The Representation and the Use of Focus in a System for Understanding Dialogues", Proc. 5th IJCAI, Cambridge, 1977, 57-76.

....away ) Shifts in rule 3 signal a new discourse segment. Just as TF can refer to points or intervals of time, SF can refer to either a point in space ( At 23 latitude 5 longitude ) a region (e.g. In Chesterville today . or a set of points or regions (analogous to discourse focus spaces [Grosz, 1977]) After each utterance, by examining the underlying propositional content TEXPLAN updates global registers that encode the past, current, and potential spatial loci. In the current implementation, the system prefers topical over causal over temporal over spatial orderings. The next sections ....

Grosz, B. J. "The Representation and Use of Focus in a System for Understanding Dialogs." Proceedings of the Fifth Annual IJCAI, Cambridge, MA, 1977.67-76.

....concepts to be learned, provide focus in a busy environment, or facilitate the communication of essential knowledge. PMMs share themes with research into computational dialogue and ITS. PMMs are intimately connected to ideas of instructional and dialogue focus, the latter of which was explored by Grosz [1977], who stated that task oriented dialogue could be organized into focus spaces, each containing a subset of the dialogue s purposes and entities. The collection of focus spaces created by the changing dynamics of a dialogue could be gathered together into a focusing structure which assisted in ....

....domain knowledge for an educational purpose. It is possible that we always use 156 some kind of alternate interpretation or misrepresentation to mediate between our knowledge and other dialogue participants. Focusing structure has traditionally been used in interpretation: in several projects ([Grosz 1977], Sidner 1983] context structures are shown to be useful in tasks like pronoun resolution or anaphora resolution. Pragmatic contexts, such as those created by a PMM, can direct generation of discourse as well. They are active reflections of the larger situation, rather than local ....

Grosz, B. "The Representation and Use of Focus in a System for Understanding Dialogs" in Proceedings of the 11 th International Joint Conference on Artificial Intelligence, Cambridge, Massachusetts, 1977, pp. 67-76.

....This subsection gives a very general treatment of actions, just enough to support the ISA rules proposed. The account of actions is taken from the OWL I representation scheme (Szolovits et al. 27] and Brown [3,6] 3 and it has counterparts in work by Bruce [7] Schank and Abelson [23] Grosz [14], and Moore, Levin, and Mann [18,19] Some of these approaches differ in the type of action modelled, and all of them differ in the details, but each of the approaches is open to the treatment of action representations as general knowledge. Thus, action representations are not merely programs for ....

Grosz, B. "The Representation and Use of Focus in a System for Understanding Dialogs," Proceedings of the Fifth International Joint Conference on Artificial Intelligence, Cambridge, Mass. (August 1977).

....each candidate against the given intensional PSN structure. The pattern matching operation in PSN corresponds to deduction on meta language, that is, the defintion of match PSN. matches PSN if meta(PSN1) mplies meta(PSN2) In order to find the referent, various kinds of knowledge will be needed [5]. However, this topic is beyond the scope of this paper. The intensional PSN structure is replaced by a PSN structure found. For example, consider the following two sentences: This paper describes a system . 1) The system analyzes programs . 2) After the interpretation of the sentence ....

B. J. Grosz, The representation and use of focus in a system for understanding dialogs, in Proc. IJCAI-77, 1977, 67-76.

....of fuzzy knowledge, including the generation of linguistic hedges, is of major importance for our system. A certain degree of communicative competence is embodied in the generation component of the system. Thus the form of the system output is determined in part by the current focus of attention [4]. 2. The Handling of Spatial Relations Spatial relationships are often mentioned in the dialogue situation described above, on the one hand because they form the topic of certain questions, e.g. How many people are standing to the right of the old woman , and on the other hand because they are ....

Grosz, B.J. (1977) : The Representation and Use of Focus in a System for Understanding Dialogs. Proceedings of the 5th IJCAI, Cambridge, Mass., 67-76

....interface that did not provide feedback. Conversations with the human tutor were recorded and transcribed, with the students GUI actions interleaved at the correct points. These human human physics tutorial dialogues generally share the hierarchical structure of task oriented dialogues (Grosz 1977). Furthermore, a main building block of the discourse hierarchy, corresponding to the transaction level in Conversation Analysis (Stenstrm 1994) matches the tutoring episode defined by VanLehn et al. 1998) A tutoring episode consists of the turns necessary to help the student make one correct ....

Grosz, B. J. 1977. The Representation and Use of Focus in a System for Understanding Dialogs. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence (IJCAI '77), Cambridge, MA, 67--76.

....means end planning. Second, the conversation is in a certain sense the trace of the plan. In other words, we care much more about the actions generated by the planner than the states involved, whether implicitly or explicitly specified. Finally, we view dialogues as having a hierarchical structure (Grosz 1977), and we use the hierarchy information in preconditions as one way to maintain coherence. In this paper we will describe APE (the Atlas Planning Engine) a reactive dialogue planner we have built for Atlas, a conversation manager for intelligent tutoring systems (Freedman 1998) APE is a ....

....( recipe ( primitive (say utterance) hiercx ( Figure 2 (continued) Sample discourse operators 5 Figure 1 shows an example of text that can be generated with APE. It contains the text of one tutoring episode, i.e. it teaches the student one piece of domain knowledge. Following Grosz (1977), each tutoring episode is seen to be a subdialogue of the complete tutoring session. Although the generated text is real, it should be noted that the dialogue is not realistic in the sense that genuine students do not usually make so many consecutive distinct errors. In this episode, the content ....

Grosz, B. J. 1977. The Representation and Use of Focus in a System for Understanding Dialogs. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence (IJCAI '77), Cambridge, MA, 67--76.

....of both items, and to repair misunderstandings, the sizes must be associated with the proper item. Rather than force the pizza and soft drink to be specified in separate taskboxes, we plan on having the dialogue manager understand the hierarchical domain knowledge and keep track of the focus (c.f. [6]) The need for hierarchical reasoning becomes even more apparent for taking multiple orders, where each pizza can have different ingredients. Second, we are planning on incorporating robust parsing techniques, such as used by Phoenix [20] Rather than use a grammar recognizer for speech ....

B. Grosz. The representation and use of focus in a system for understanding dialogs. In Proceedings of the International Joint Conference on Artificial Intelligence, pages 67--76, 1977.

....One of the first uses of view like structures for natural language processing was a method developed by Grosz for structuring background knowledge with focus spaces. Focus spaces guide dialog comprehension by restricting the comprehender s attention to relevant portions of background knowledge [Gro86] This approach assumes that background knowledge is encoded as a semantic network; it uses a semantic network partition to define each focus space. Hendrix developed network partitions called spaces to represent abstractions, hypothetical situations, and the scoping of quantified variables ....

B.J. Grosz. The representation and use of focus in a system for understanding dialogs. In B.J. Grosz, K. Sparck Jones, and B.L. Webber, editors, Readings in Natural Language Processing. Morgan Kaufmann Publishers, Inc., 1986.

....of interest. Resolving pronominal referents is a subset of the coreference problem. The ability to identify the person, object, place, time, event, or concept that is a referent of a pronoun is necessary to follow the concepts being communicated and to maintain the general focus of the discourse (Grosz and Sidner 1986). There are some resolution algorithms outlined by Hobbs (1986) that perform well, but these algorithms require a properly parsed sentence. The process identified by this paper only requires that the words be tagged for part of speech with the single enhancement of identifying plural noun phrases ....

Grosz, Barbara J. 1986. The representation and use of focus in a system for understanding dialogs, In Readings in Natural language processing. Morgan Kaufmann Publishers, Los Altos, CA, pages 352-362.

....size of Cyc. Furthermore, NL research uses contexts to account for the phenomena that the meaning of an English sentence depends on the context in which it is uttered. They have identified various properties and characterizations of such contexts. For example, Barbara Grosz in her Ph.D. thesis, [33], implicitly captures the context of a discourse by focusing on the objects and actions which are most relevant to the discourse. This notion is similar to an ATMS context, 23] which is simply a list of propositions that are assumed by the reasoning system. Although contexts have been ....

Barbara J. Grosz. A representation and use of focus in a system for understanding dialogs. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence. Morgan Kaufmann Publishers Inc., 1977.

....them. The anaphora problem is determining when two or more phrases, often containing different words, are referring to the same object. Such an occurrence is called co reference. To date, work on the anaphora problem has been concerned with getting the correct answer in all situations ( 6] [7], 13] 15] Not surprisingly this requires a large amount of knowledge of all types (syntactic, semantic and world) In fact it has been shown that the problem requires an arbitrarily large amount of knowledge [1] 2] Consequently the solutions implemented so far have only been for very limited ....

Grosz, Barbara "The Representation and Use of Focus in a System for Understanding Dialogs" Proceedings of the Fifth International Joint Conference on Artificial Intelligence Cambridge, MA, 1977

....appropriate definite descriptions. The second corresponds to the notion of a focus space. It is used for anaphora resolution and generation and models the local movement of topic within a discourse segment. We will explore each separately. Global discourse context A semantic net model Grosz [31] outlined a representation of global focus in the context of work on task oriented dialog. This representation distinguishes between explicitly and implicitly focused items, and allows one to view an item from different points of view. The knowledge base is represented as a semantic network that ....

B. Grosz. The representation and use of focus in a system for understanding dialogs. IJCAI, 1977.

....do the reassessment, and produces the message Do a peritoneal lavage immediately as part of ruling out abdominal bleeding. Use the results of the peritoneal lavage to decide whether or not to reassess the patient in 6 to 24 hours. Other Influences on Effective Messages The Role of Focus Focus (Grosz, 1977; McKeown, 1985) has been the objective of much discourse research, and it plays several roles in our generation of messages. As noted earlier, trailing comments capture communicative goals that relate to previously mentioned actions, and cue words are used to shift focus back to the earlier ....

B. Grosz (1977). The representation and use of focus in a system for understanding dialogs. In Proceedings of the International Joint Conference on Artificial Intelligence, 67--76.

....structure. It models the attentional state and coordinates the linguistic and intentional structures as well. Focusing will be elaborated in the upcoming section. 2.3.2 Focusing Focusing, like anaphora, is a discourse phenomenon. Prior to Sidner s study, the concept of focusing was used by Grosz [17]. Grosz also used focusing as the main tool for anaphora resolution. She developed the concept of focus space in her study which later influenced Sidner s work. In the literature, several researchers mention focusing [42] which, after Grosz and Sidner s work, has become a widely accepted tool. ....

....In the late 1970s, studies were carried out on the use of domain knowledge in discourse, and on discourse phenomena other than pronoun understanding. The systems built in this era were still not general purpose. Some examples are SAM [8] GUS [2] and the Task Dialogue Understanding System [17]. The last one made the distinction among domain knowledge, discourse information, and intention recognition. At the end of this period, it was realized that a complete system cannot be constructed only by putting mechanisms for these three parts together, and that the interaction among these ....

[Article contains additional citation context not shown here]

B. J. Grosz. The representation and use of focus in a system for understanding dialogs. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence, Cambridge, MA, 1977.

....attached to the new information. Trivial implications are eliminated by the operating characteristics of the deductive device. Haslett ( has argued that one of the limitations of the Sperber and Wilson Model is that it has no notion of communicative goal. In other areas of linguistic research (Grosz 1977 for e.g. goals have been important constructs for shaping the context and determining reference. Within H CI goals have been central to an understanding of task. Arguably then, Sperber and Wilson s model were it to be applied in the H CI or CSCW context might need to incorporate some such ....

Grosz, B. (1977) The representation and use of focus in a system for understanding dialogs. IJCAI 5.

....should be useful for developing a spoken language interface to several computer applications, where each application defines its own context. We have introduced a method for incorporating context specific constraints into the parsing process. However, we have not discussed how discourse structure [8, 9] would impact the system. It would be very helpful for tracking interactions between a user and the general purpose interface to multiple applications and is a topic which we plan to study in the future. Also, it is important to handle multiple valid interacting contexts. For example, suppose you ....

B. J. Grosz. The representation and use of focus in a system of understanding dialogs. In Proceedings of the International Joint Conference on Artificial Intelligence, pages 67--76, 1977.

....in a well connected manner: The dinosaur extinctions may have been caused by a huge meteorite. Evidence for such a meteorite is provided by an unusual concentration of iridium found in KT boundary rocks. Two ordering strategies are needed to exploit and extend local focus of attention (Grosz 1977; Sidner 1979) one strategy to constrain the transition from a topic concept to other concepts, and another to constrain the transitions between propositions that share concepts. The first, strategy 12, ensures that some topic t is introduced before non topics. The second, strategy 13, introduces ....

Grosz, B. 1977. The representation and use of focus in a system for understanding dialogs.

....experiments are being carried out on the PlaNet PDP platform [Miyata, 1991] In the first instance, only 5 out of the set of 80 features were employed, namely: 1. Focus change (a or 0) this records a shift from topic A of the previous sentence to topic B or to a subtopic of A in the current one [Grosz, 1986]. 2. Explanation (a or 0) and 3. Contrast (a or 0) are both rhetorical types of relations holding between two different sentences or two clauses in the same sentence [cf. Mann and Thompson, 1987] 4. Generalisation (a or 0) is a reference to permanent states or habitual, recurring events, rather ....

Grosz, B. J. (1986). The representation and use of focus in a system for understanding dialogs. In Grosz, B. J., Sparck Jones, K., and Webber, B. L., editors, Readings In Natural Language Processing. Morgan Kaufmann Publishers, California.

....Furthermore, computational linguists use contexts to account for the phenomena that the meaning of an English sentence depends on the context in which it is uttered. They have identified various properties and characterizations of such contexts. For example, Barbara Grosz in her Ph.D. thesis, [11], implicitly captures the context of a discourse by focusing on the objects and actions which are most relevant to the discourse. This notion is similar to an ATMS context, 8] which is simply a list of propositions that are assumed by the reasoning system. However, until now no formal ....

Barbara J. Grosz. A representation and use of focus in a system for understanding dialogs. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence. Morgan Kaufmann Publishers Inc., 1977.

No context found.

B. J. Grosz, "The representation and use of focus in a system for understanding dialogs," in Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI '77), pp. 67--76, 1977. Reprinted in [37].

No context found.

Grosz, B. The Representation and Use of Focus in a System for Understanding Dialogs. In Elements of Discourse Understanding, A. loshi, B. Webber & I. Sag (eds.), Cambridge: Cambridge Univ. Press, 1981.

No context found.

Grosz,B.J., "The Representation and Use of Focus in a System for Understanding Dialogs", IJCAI, ]977 O. Grosz,B.J., Joshi, A.K., and Weinstein,S., "Providing a Unified Account of Definite Noun Phrases in Discourse ", Proceedings 2 rst Annual Meeting of ACL, 983 . Hendrix, O.G., E.D. Sacerdoti, and J.Slocum, "Developing a Natural Language Interface to Complex Data", SRI International, 976

No context found.

Grosz, Barbara J. (1977), "The Representation and Use of Focus in a System for Understanding Dialogs," Proceedings of the 5th International Joint Conference on Artificial Intelligence (IJCAI-77, MIT) (Los Altos, CA: Morgan Kaufmann): 67--76.

No context found.

Barbara J. Grosz. The representation and use of focus in a system for understanding dialog. In IJCAI-77 [503], pages 67--76.

No context found.

Grosz, B.I., (1977) The representation and use of focus in a system for understanding dialog, in: Proceedings 5 th IJCAI-77.

No context found.

B.J. Grosz. The representation and use of focus in a system for understanding dialogs. In Proceedings of the International Joint Conference on Artificial Intelligence, IJCAI-77, 67--76, 1983.

No context found.

Grosz, Barbara J. 1977. "The Representation and Use of Focus in a System for Understanding Dialogs." Proceedings of the 5 th International Joint Conference on Artificial Intelligence (IJCAI-77). Cambridge, Mass., Vol. 1. 67--76.

No context found.

B.J. Grosz, "The Representation and Use of Focus in a System for Understanding Dialogs," Proceedings of the Fifth International Joint Conference on Artificial Intelligence (IJCAI-77), Vol. 1, Aug. 2225, 1977, Cambridge, MA, Carnegie Mellon Computer Science Department, Pittsburgh, pp. 67-76.

No context found.

Barbara J. Grosz. The representation and use of focus in a system for understanding dialogs. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI '77), pages 67-76. 1977.

No context found.

Grosz, Barbara J. 1977a. The representation and use of focus in a system for understanding dialogs. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC