Using Process Knowledge in Understanding Task-Oriented Dialogs

Grosz, Barbara J.; Hendrix, Gary G.; Robinson, Ann E.

Using Process Knowledge in Understanding Task-Oriented Dialogs

Barbara J. Grosz, Gary G. Hendrix, Ann E. Robinson

Download BibTeX Cite

Proceedings of the Fifth International Joint Conference on Artificial Intelligence. Natural Language. Pages 90--1.

Abstract

Barbara G. The Structure of Task- oriented Dialogs. Contributed Papers IEEE Symposium on Speech Recognition. Carnegie Mellon University , Pittsburgh, Pennsylvania, 15- 19 April 1974.
Edited by Lee D. Erman. IEEE, New York, 1974, 250-254
Fikes, Richard E. and Hendrix, Gary G. A Network- Based Knowledge Representation and its Natural Deduction System. Advance Papers of the Fifth International Joint Conference on Artificial Intelligence, Cambridge, Massachusetts , 22-25 August, 1977 . IJCAI
Grosz, Barbara J. The Representation and Use of Focus in Dialogue Understanding. Ph.D. Thesis, University of California, Berkeley, California, June 1977 .
Grosz, Barbara J . The Representation and Use of Focus in a System for Understanding Dialogs. Advance Papers of the Fifth International Joint Conference on Artificial Intelligence, Cambridge, Massachusetts , 22-25 August, 1977 . IJCAI
Hendrix, Gary G. Partitioned Networks for the Mathematical Modeling of Natural Language Semantics. Technical Report NL-28, Department of Computer Sciences, University of Texas, Austin, Texas, 1975.
Sacerdoti, Earl D. A Structure for Plans and Behavior. Technical Note 109 , Artificial Intelligence Center, Stanford Research Institute, Menlo Park, California , 1975. ~li'lt11ral Lanl!;uage-4: r,rosz

References were extracted automatically from the PDF and may contain errors.

Full text extracted automatically from the PDF; figures, tables and equations may differ. The PDF is the version of record.

USING PROCESS KNOWLEDGE IN UNDERSTANDING TASK-ORIENTED DIALOGS

by Barbara J . Grosz, Gary G. Hendrix, and Ann E. Robinson SRI International Menlo Park, California 94025

This note outlines research on natural language communication between two parties * cooperating to accomplish a task. Our goal is to formalize the knowledge needed to understand task oriented dialogs and to develop techniques for representing and coordinating this knowledge in a computer system that can participate in the dialog. Encoding general process knowledge and the dynamics of specific tasks in a manner that is useful for the interpretation and generation of utterances in

a dialog is a central issue in this research.

A task orientation provides a framework for studying the influence of context on language. Our previous analyses of several task-oriented dialogs (e.g., Deutsch, 1974) indicate

The context of an utterance includes at least three discernable factors~ the preceding utterances in the dialog, the state of the task, and the physical environment of the dialog.
( 2) Task-·oriented dialogs have a structure that reflects the structure of the task.

The set of objects and actions that are most relevant to the conversation, and hence in the focus of attention of the dialog participants, changes as the task progresses. To follow such shifts in focus, a comp~tational system needs a model of the task being performed.

To meet this need, we have developed a representation scheme for encoding process knowledge and are using it to encode data about specific tasks. This scheme is used both to answer particular questions about the task and to guide linguistic processing. The representation combines features of the partitioned semantic networks of Hendrix (1975), the procedural networks of Sacerdoti (1975) , and the focus (i.e., context) mechanisms of Grosz (1977a, 1977b). Of particular interest is the fact that those objects that are in focus at a given time are clearly delineated.

*This work is supported by National Science Foundation Grant No. MCS76-22004

We are currently developing algorithms that use this representation of task knowledge to expand the use of context in the interpretation of inputs and the generation of responses, instructions, and requests. These algorithms include mechanisms that follow the shift of focus with the progress of the task.

Barbara J. Grosz, Gary G. Hendrix, and Ann E. Robinson. 1977. Using Process Knowledge in Understanding Task-Oriented Dialogs. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence, IJCAI-77. IJCAI, 90–-1. https://ijcai.org/proceedings/1977/16

@inproceedings{ijcai1977p16,
  title     = {Using Process Knowledge in Understanding Task-Oriented Dialogs},
  author    = {Grosz, Barbara J. and Hendrix, Gary G. and Robinson, Ann E.},
  booktitle = {Proceedings of the Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-77}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {Raj Reddy},
  pages     = {90---1},
  year      = {1977},
  note      = {Natural Language},
  url       = {https://ijcai.org/proceedings/1977/16},
}

TY  - CPAPER
TI  - Using Process Knowledge in Understanding Task-Oriented Dialogs
AU  - Grosz, Barbara J.
AU  - Hendrix, Gary G.
AU  - Robinson, Ann E.
T2  - Proceedings of the Fifth International Joint Conference on Artificial Intelligence, IJCAI-77
PB  - International Joint Conferences on Artificial Intelligence
PY  - 1977
SP  - 90
EP  - -1
UR  - https://ijcai.org/proceedings/1977/16
ER  -

[1] Barbara G. The Structure of Task- oriented Dialogs. Contributed Papers IEEE Symposium on Speech Recognition. Carnegie Mellon University , Pittsburgh, Pennsylvania, 15- 19 April 1974.

[2] Edited by Lee D. Erman. IEEE, New York, 1974, 250-254

[3] Fikes, Richard E. and Hendrix, Gary G. A Network- Based Knowledge Representation and its Natural Deduction System. Advance Papers of the Fifth International Joint Conference on Artificial Intelligence, Cambridge, Massachusetts , 22-25 August, 1977 . IJCAI

[4] Grosz, Barbara J. The Representation and Use of Focus in Dialogue Understanding. Ph.D. Thesis, University of California, Berkeley, California, June 1977 .

[5] Grosz, Barbara J . The Representation and Use of Focus in a System for Understanding Dialogs. Advance Papers of the Fifth International Joint Conference on Artificial Intelligence, Cambridge, Massachusetts , 22-25 August, 1977 . IJCAI

[6] Hendrix, Gary G. Partitioned Networks for the Mathematical Modeling of Natural Language Semantics. Technical Report NL-28, Department of Computer Sciences, University of Texas, Austin, Texas, 1975.

[7] Sacerdoti, Earl D. A Structure for Plans and Behavior. Technical Note 109 , Artificial Intelligence Center, Stanford Research Institute, Menlo Park, California , 1975. ~li'lt11ral Lanl!;uage-4: r,rosz