Automatic prediction of discourse connectives

Eric Malmi; Daniele Pighin; Sebastian Krause; Mikhail Kozhevnikov

Automatic prediction of discourse connectives

Eric Malmi, Daniele Pighin, Sebastian Krause, Mikhail Kozhevnikov

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

6 Citations (Scopus)

Abstract

Accurate prediction of suitable discourse connectives (however, furthermore, etc.) is a key component of any system aimed at building coherent and fluent discourses from shorter sentences and passages. As an example, a dialog system might assemble a long and informative answer by sampling passages extracted from different documents retrieved from the Web. We formulate the task of discourse connective prediction and release a dataset of 2.9M sentence pairs separated by discourse connectives for this task. Then, we evaluate the hardness of the task for human raters, apply a recently proposed decomposable attention (DA) model to this task and observe that the automatic predictor has a higher F1 than human raters (32 vs. 30). Nevertheless, under specific conditions the raters still outperform the DA model, suggesting that there is headroom for future improvements.

Original language	English
Title of host publication	LREC 2018 - 11th International Conference on Language Resources and Evaluation
Editors	Hitoshi Isahara, Bente Maegaard, Stelios Piperidis, Christopher Cieri, Thierry Declerck, Koiti Hasida, Helene Mazo, Khalid Choukri, Sara Goggi, Joseph Mariani, Asuncion Moreno, Nicoletta Calzolari, Jan Odijk, Takenobu Tokunaga
Publisher	European Language Resources Association (ELRA)
Pages	1643-1648
Number of pages	6
ISBN (Electronic)	9791095546009
Publication status	Published - 1 Jan 2019
MoE publication type	A4 Article in a conference publication
Event	International Conference on Language Resources and Evaluation - Miyazaki, Japan Duration: 7 May 2018 → 12 May 2018 Conference number: 11

Conference

Conference	International Conference on Language Resources and Evaluation
Abbreviated title	LREC
Country	Japan
City	Miyazaki
Period	07/05/2018 → 12/05/2018

Keywords

Decomposable attention model
Discourse connectives
Discourse relation prediction

Access to Document

Link to publication in Scopus

Fingerprint Dive into the research topics of 'Automatic prediction of discourse connectives'. Together they form a unique fingerprint.

Cite this

Malmi, E., Pighin, D., Krause, S., & Kozhevnikov, M. (2019). Automatic prediction of discourse connectives. In H. Isahara, B. Maegaard, S. Piperidis, C. Cieri, T. Declerck, K. Hasida, H. Mazo, K. Choukri, S. Goggi, J. Mariani, A. Moreno, N. Calzolari, J. Odijk, & T. Tokunaga (Eds.), LREC 2018 - 11th International Conference on Language Resources and Evaluation (pp. 1643-1648). European Language Resources Association (ELRA).

Malmi, Eric ; Pighin, Daniele ; Krause, Sebastian ; Kozhevnikov, Mikhail. / Automatic prediction of discourse connectives. LREC 2018 - 11th International Conference on Language Resources and Evaluation. editor / Hitoshi Isahara ; Bente Maegaard ; Stelios Piperidis ; Christopher Cieri ; Thierry Declerck ; Koiti Hasida ; Helene Mazo ; Khalid Choukri ; Sara Goggi ; Joseph Mariani ; Asuncion Moreno ; Nicoletta Calzolari ; Jan Odijk ; Takenobu Tokunaga. European Language Resources Association (ELRA), 2019. pp. 1643-1648

@inproceedings{6436f2b415b74961bd547c0d20e73472,

title = "Automatic prediction of discourse connectives",

abstract = "Accurate prediction of suitable discourse connectives (however, furthermore, etc.) is a key component of any system aimed at building coherent and fluent discourses from shorter sentences and passages. As an example, a dialog system might assemble a long and informative answer by sampling passages extracted from different documents retrieved from the Web. We formulate the task of discourse connective prediction and release a dataset of 2.9M sentence pairs separated by discourse connectives for this task. Then, we evaluate the hardness of the task for human raters, apply a recently proposed decomposable attention (DA) model to this task and observe that the automatic predictor has a higher F1 than human raters (32 vs. 30). Nevertheless, under specific conditions the raters still outperform the DA model, suggesting that there is headroom for future improvements.",

keywords = "Decomposable attention model, Discourse connectives, Discourse relation prediction",

author = "Eric Malmi and Daniele Pighin and Sebastian Krause and Mikhail Kozhevnikov",

year = "2019",

month = jan,

day = "1",

language = "English",

pages = "1643--1648",

editor = "Hitoshi Isahara and Bente Maegaard and Stelios Piperidis and Christopher Cieri and Thierry Declerck and Koiti Hasida and Helene Mazo and Khalid Choukri and Sara Goggi and Joseph Mariani and Asuncion Moreno and Nicoletta Calzolari and Jan Odijk and Takenobu Tokunaga",

booktitle = "LREC 2018 - 11th International Conference on Language Resources and Evaluation",

publisher = "European Language Resources Association (ELRA)",

note = "International Conference on Language Resources and Evaluation, LREC ; Conference date: 07-05-2018 Through 12-05-2018",

}

Malmi, E, Pighin, D, Krause, S & Kozhevnikov, M 2019, Automatic prediction of discourse connectives. in H Isahara, B Maegaard, S Piperidis, C Cieri, T Declerck, K Hasida, H Mazo, K Choukri, S Goggi, J Mariani, A Moreno, N Calzolari, J Odijk & T Tokunaga (eds), LREC 2018 - 11th International Conference on Language Resources and Evaluation. European Language Resources Association (ELRA), pp. 1643-1648, International Conference on Language Resources and Evaluation, Miyazaki, Japan, 07/05/2018.

Automatic prediction of discourse connectives. / Malmi, Eric; Pighin, Daniele; Krause, Sebastian; Kozhevnikov, Mikhail.

LREC 2018 - 11th International Conference on Language Resources and Evaluation. ed. / Hitoshi Isahara; Bente Maegaard; Stelios Piperidis; Christopher Cieri; Thierry Declerck; Koiti Hasida; Helene Mazo; Khalid Choukri; Sara Goggi; Joseph Mariani; Asuncion Moreno; Nicoletta Calzolari; Jan Odijk; Takenobu Tokunaga. European Language Resources Association (ELRA), 2019. p. 1643-1648.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Automatic prediction of discourse connectives

AU - Malmi, Eric

AU - Pighin, Daniele

AU - Krause, Sebastian

AU - Kozhevnikov, Mikhail

N1 - Conference code: 11

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Accurate prediction of suitable discourse connectives (however, furthermore, etc.) is a key component of any system aimed at building coherent and fluent discourses from shorter sentences and passages. As an example, a dialog system might assemble a long and informative answer by sampling passages extracted from different documents retrieved from the Web. We formulate the task of discourse connective prediction and release a dataset of 2.9M sentence pairs separated by discourse connectives for this task. Then, we evaluate the hardness of the task for human raters, apply a recently proposed decomposable attention (DA) model to this task and observe that the automatic predictor has a higher F1 than human raters (32 vs. 30). Nevertheless, under specific conditions the raters still outperform the DA model, suggesting that there is headroom for future improvements.

AB - Accurate prediction of suitable discourse connectives (however, furthermore, etc.) is a key component of any system aimed at building coherent and fluent discourses from shorter sentences and passages. As an example, a dialog system might assemble a long and informative answer by sampling passages extracted from different documents retrieved from the Web. We formulate the task of discourse connective prediction and release a dataset of 2.9M sentence pairs separated by discourse connectives for this task. Then, we evaluate the hardness of the task for human raters, apply a recently proposed decomposable attention (DA) model to this task and observe that the automatic predictor has a higher F1 than human raters (32 vs. 30). Nevertheless, under specific conditions the raters still outperform the DA model, suggesting that there is headroom for future improvements.

KW - Decomposable attention model

KW - Discourse connectives

KW - Discourse relation prediction

UR - http://www.scopus.com/inward/record.url?scp=85059902298&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85059902298

SP - 1643

EP - 1648

BT - LREC 2018 - 11th International Conference on Language Resources and Evaluation

A2 - Isahara, Hitoshi

A2 - Maegaard, Bente

A2 - Piperidis, Stelios

A2 - Cieri, Christopher

A2 - Declerck, Thierry

A2 - Hasida, Koiti

A2 - Mazo, Helene

A2 - Choukri, Khalid

A2 - Goggi, Sara

A2 - Mariani, Joseph

A2 - Moreno, Asuncion

A2 - Calzolari, Nicoletta

A2 - Odijk, Jan

A2 - Tokunaga, Takenobu

PB - European Language Resources Association (ELRA)

T2 - International Conference on Language Resources and Evaluation

Y2 - 7 May 2018 through 12 May 2018

ER -

Malmi E, Pighin D, Krause S, Kozhevnikov M. Automatic prediction of discourse connectives. In Isahara H, Maegaard B, Piperidis S, Cieri C, Declerck T, Hasida K, Mazo H, Choukri K, Goggi S, Mariani J, Moreno A, Calzolari N, Odijk J, Tokunaga T, editors, LREC 2018 - 11th International Conference on Language Resources and Evaluation. European Language Resources Association (ELRA). 2019. p. 1643-1648