Automatic generation of multi-modal dialogue from text based on discourse structure analysis

Helmut Prendinger, Paul Piwek, Mitsuru Ishizuka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

In this paper, we propose a novel method for generating engaging multi-modal content automatically from text. Rhetorical Structure Theory (RST) is used to decompose text into discourse units and to identify rhetorical discourse relations between them. Rhetorical relations are then mapped to question-answer pairs in an information preserving way, i.e., the original text and the resulting dialogue convey essentially the same meaning. Finally, the dialogue is "acted out" by two virtual agents. The network of dialogue structures automatically built up during this process, called DialogueNet, can be reused for other purposes, such as personalization or question-answering.

Original languageEnglish
Title of host publicationICSC 2007 International Conference on Semantic Computing
Pages27-34
Number of pages8
DOIs
Publication statusPublished - 2007
Externally publishedYes
EventICSC 2007 International Conference on Semantic Computing - Irvine CA
Duration: 2007 Sep 172007 Sep 19

Other

OtherICSC 2007 International Conference on Semantic Computing
CityIrvine CA
Period07/9/1707/9/19

ASJC Scopus subject areas

  • Computer Science(all)
  • Computer Science Applications

Cite this

Prendinger, H., Piwek, P., & Ishizuka, M. (2007). Automatic generation of multi-modal dialogue from text based on discourse structure analysis. In ICSC 2007 International Conference on Semantic Computing (pp. 27-34). [4338329] https://doi.org/10.1109/ICOSC.2007.4338329

Automatic generation of multi-modal dialogue from text based on discourse structure analysis. / Prendinger, Helmut; Piwek, Paul; Ishizuka, Mitsuru.

ICSC 2007 International Conference on Semantic Computing. 2007. p. 27-34 4338329.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Prendinger, H, Piwek, P & Ishizuka, M 2007, Automatic generation of multi-modal dialogue from text based on discourse structure analysis. in ICSC 2007 International Conference on Semantic Computing., 4338329, pp. 27-34, ICSC 2007 International Conference on Semantic Computing, Irvine CA, 07/9/17. https://doi.org/10.1109/ICOSC.2007.4338329
Prendinger H, Piwek P, Ishizuka M. Automatic generation of multi-modal dialogue from text based on discourse structure analysis. In ICSC 2007 International Conference on Semantic Computing. 2007. p. 27-34. 4338329 https://doi.org/10.1109/ICOSC.2007.4338329
Prendinger, Helmut ; Piwek, Paul ; Ishizuka, Mitsuru. / Automatic generation of multi-modal dialogue from text based on discourse structure analysis. ICSC 2007 International Conference on Semantic Computing. 2007. pp. 27-34
@inproceedings{685a9b7a7135448ebd0ceec0e637eb03,
title = "Automatic generation of multi-modal dialogue from text based on discourse structure analysis",
abstract = "In this paper, we propose a novel method for generating engaging multi-modal content automatically from text. Rhetorical Structure Theory (RST) is used to decompose text into discourse units and to identify rhetorical discourse relations between them. Rhetorical relations are then mapped to question-answer pairs in an information preserving way, i.e., the original text and the resulting dialogue convey essentially the same meaning. Finally, the dialogue is {"}acted out{"} by two virtual agents. The network of dialogue structures automatically built up during this process, called DialogueNet, can be reused for other purposes, such as personalization or question-answering.",
author = "Helmut Prendinger and Paul Piwek and Mitsuru Ishizuka",
year = "2007",
doi = "10.1109/ICOSC.2007.4338329",
language = "English",
isbn = "0769529976",
pages = "27--34",
booktitle = "ICSC 2007 International Conference on Semantic Computing",

}

TY - GEN

T1 - Automatic generation of multi-modal dialogue from text based on discourse structure analysis

AU - Prendinger, Helmut

AU - Piwek, Paul

AU - Ishizuka, Mitsuru

PY - 2007

Y1 - 2007

N2 - In this paper, we propose a novel method for generating engaging multi-modal content automatically from text. Rhetorical Structure Theory (RST) is used to decompose text into discourse units and to identify rhetorical discourse relations between them. Rhetorical relations are then mapped to question-answer pairs in an information preserving way, i.e., the original text and the resulting dialogue convey essentially the same meaning. Finally, the dialogue is "acted out" by two virtual agents. The network of dialogue structures automatically built up during this process, called DialogueNet, can be reused for other purposes, such as personalization or question-answering.

AB - In this paper, we propose a novel method for generating engaging multi-modal content automatically from text. Rhetorical Structure Theory (RST) is used to decompose text into discourse units and to identify rhetorical discourse relations between them. Rhetorical relations are then mapped to question-answer pairs in an information preserving way, i.e., the original text and the resulting dialogue convey essentially the same meaning. Finally, the dialogue is "acted out" by two virtual agents. The network of dialogue structures automatically built up during this process, called DialogueNet, can be reused for other purposes, such as personalization or question-answering.

UR - http://www.scopus.com/inward/record.url?scp=47749133810&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47749133810&partnerID=8YFLogxK

U2 - 10.1109/ICOSC.2007.4338329

DO - 10.1109/ICOSC.2007.4338329

M3 - Conference contribution

AN - SCOPUS:47749133810

SN - 0769529976

SN - 9780769529974

SP - 27

EP - 34

BT - ICSC 2007 International Conference on Semantic Computing

ER -