Learning Features that Predict Cue Usage

Barbara Di Eugenio; Johanna D. Moore; Massimo Paolucci

Learning Features that Predict Cue Usage

Barbara Di Eugenio, Johanna D. Moore, Massimo Paolucci

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

Our goal is to identify the features that predict the occurrence and placement of discourse cues in tutorial explanations in order to aid in the automatic generation of explanations. Previous attempts to devise rules for text generation were based on intuition or small numbers of constructed examples. We apply a machine learning program, C4.5, to induce decision trees for cue occurrence and placement from a corpus of data coded for a variety of features previously thought to affect cue usage. Our experiments enable us to identify the features with most predictive power, and show that machine learning can be used to induce decision trees useful for text generation.

Original language	English
Title of host publication	35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, 7-12 July 1997, Universidad Nacional de Educación a Distancia (UNED), Madrid, Spain.
Publisher	Cornell University Press
Pages	80-87
Number of pages	8
Publication status	Published - Jul 1997

Access to Document

Di Eugenio Moore ET AL 1997 Learning Features that Predict Cue UsageFinal published version, 163 KB

Cite this

Eugenio, B. D., Moore, J. D., & Paolucci, M. (1997). Learning Features that Predict Cue Usage. In 35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, 7-12 July 1997, Universidad Nacional de Educación a Distancia (UNED), Madrid, Spain. (pp. 80-87). Cornell University Press.

Eugenio, Barbara Di ; Moore, Johanna D. ; Paolucci, Massimo. / Learning Features that Predict Cue Usage. 35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, 7-12 July 1997, Universidad Nacional de Educación a Distancia (UNED), Madrid, Spain.. Cornell University Press, 1997. pp. 80-87

@inproceedings{38120e2052b844278a6cde9ec48ae07c,

title = "Learning Features that Predict Cue Usage",

abstract = "Our goal is to identify the features that predict the occurrence and placement of discourse cues in tutorial explanations in order to aid in the automatic generation of explanations. Previous attempts to devise rules for text generation were based on intuition or small numbers of constructed examples. We apply a machine learning program, C4.5, to induce decision trees for cue occurrence and placement from a corpus of data coded for a variety of features previously thought to affect cue usage. Our experiments enable us to identify the features with most predictive power, and show that machine learning can be used to induce decision trees useful for text generation.",

author = "Eugenio, {Barbara Di} and Moore, {Johanna D.} and Massimo Paolucci",

year = "1997",

month = jul,

language = "English",

pages = "80--87",

booktitle = "35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, 7-12 July 1997, Universidad Nacional de Educaci{\'o}n a Distancia (UNED), Madrid, Spain.",

publisher = "Cornell University Press",

}

Eugenio, BD, Moore, JD & Paolucci, M 1997, Learning Features that Predict Cue Usage. in 35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, 7-12 July 1997, Universidad Nacional de Educación a Distancia (UNED), Madrid, Spain.. Cornell University Press, pp. 80-87.

Learning Features that Predict Cue Usage. / Eugenio, Barbara Di; Moore, Johanna D.; Paolucci, Massimo.
35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, 7-12 July 1997, Universidad Nacional de Educación a Distancia (UNED), Madrid, Spain.. Cornell University Press, 1997. p. 80-87.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Learning Features that Predict Cue Usage

AU - Eugenio, Barbara Di

AU - Moore, Johanna D.

AU - Paolucci, Massimo

PY - 1997/7

Y1 - 1997/7

N2 - Our goal is to identify the features that predict the occurrence and placement of discourse cues in tutorial explanations in order to aid in the automatic generation of explanations. Previous attempts to devise rules for text generation were based on intuition or small numbers of constructed examples. We apply a machine learning program, C4.5, to induce decision trees for cue occurrence and placement from a corpus of data coded for a variety of features previously thought to affect cue usage. Our experiments enable us to identify the features with most predictive power, and show that machine learning can be used to induce decision trees useful for text generation.

AB - Our goal is to identify the features that predict the occurrence and placement of discourse cues in tutorial explanations in order to aid in the automatic generation of explanations. Previous attempts to devise rules for text generation were based on intuition or small numbers of constructed examples. We apply a machine learning program, C4.5, to induce decision trees for cue occurrence and placement from a corpus of data coded for a variety of features previously thought to affect cue usage. Our experiments enable us to identify the features with most predictive power, and show that machine learning can be used to induce decision trees useful for text generation.

M3 - Conference contribution

SP - 80

EP - 87

BT - 35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, 7-12 July 1997, Universidad Nacional de Educación a Distancia (UNED), Madrid, Spain.

PB - Cornell University Press

ER -

Eugenio BD, Moore JD, Paolucci M. Learning Features that Predict Cue Usage. In 35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, 7-12 July 1997, Universidad Nacional de Educación a Distancia (UNED), Madrid, Spain.. Cornell University Press. 1997. p. 80-87

Learning Features that Predict Cue Usage

Abstract / Description of output

Access to Document

Fingerprint

Cite this