Exploring Features and Classifiers for Dialogue Act Segmentation

Harm op den Akker; Hendrikus J.A. op den Akker; Christian Schulz

doi:10.1007/978-3-540-85853-9_18

Exploring Features and Classifiers for Dialogue Act Segmentation

Harm op den Akker, Hendrikus J.A. op den Akker, Christian Schulz

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

5 Citations (Scopus)

64 Downloads (Pure)

Abstract

This paper takes a classical machine learning approach to the task of Dialogue Act segmentation. A thorough empirical evaluation of features, both used in other studies as well as new ones, is performed. An explorative study to the effectiveness of different classification methods is done by looking at 29 different classifiers implemented in WEKA. The output of the developed classifier is examined closely and points of possible improvement are given.

Original language	Undefined
Title of host publication	Machine Learning for Multimodal Interaction, MLMI 2008
Editors	Andrei Popescu-Belis, Rainer Stiefelhagen
Place of Publication	Berlin / Heidelberg
Publisher	Springer
Pages	196-207
Number of pages	12
ISBN (Print)	978-3-540-85852-2
DOIs	https://doi.org/10.1007/978-3-540-85853-9_18
Publication status	Published - 20 Sept 2008
Event	5th International Workshop on Machine Learning and Multimodal Interaction, MLMI 2008: 5th Joint Workshop on Machine Learning and Multimodal Interaction - Utrecht, the Netherlands, Berlin Duration: 8 Sept 2008 → 10 Sept 2008

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Verlag
Volume	5237

Conference

Conference	5th International Workshop on Machine Learning and Multimodal Interaction, MLMI 2008
City	Berlin
Period	8/09/08 → 10/09/08
Other	8-10 September 2008

Keywords

HMI-MI: MULTIMODAL INTERACTIONS
EC Grant Agreement nr.: FP6/0033812
EWI-14954
IR-65340
Machine classification
METIS-255875
Conversational Analysis

Access to Document

10.1007/978-3-540-85853-9_18

MLMI2008_DA_Segmentation

Cite this

op den Akker, H., op den Akker, H. J. A., & Schulz, C. (2008). Exploring Features and Classifiers for Dialogue Act Segmentation. In A. Popescu-Belis, & R. Stiefelhagen (Eds.), Machine Learning for Multimodal Interaction, MLMI 2008 (pp. 196-207). Article 10.1007/978-3-540-85853-9_18 (Lecture Notes in Computer Science; Vol. 5237). Springer. https://doi.org/10.1007/978-3-540-85853-9_18

@inproceedings{8e82ba6d2cab442e80aafb175a7f00b3,

title = "Exploring Features and Classifiers for Dialogue Act Segmentation",

abstract = "This paper takes a classical machine learning approach to the task of Dialogue Act segmentation. A thorough empirical evaluation of features, both used in other studies as well as new ones, is performed. An explorative study to the effectiveness of different classification methods is done by looking at 29 different classifiers implemented in WEKA. The output of the developed classifier is examined closely and points of possible improvement are given.",

keywords = "HMI-MI: MULTIMODAL INTERACTIONS, EC Grant Agreement nr.: FP6/0033812, EWI-14954, IR-65340, Machine classification, METIS-255875, Conversational Analysis",

author = "{op den Akker}, Harm and {op den Akker}, {Hendrikus J.A.} and Christian Schulz",

note = "10.1007/978-3-540-85853-9_18 ; 5th International Workshop on Machine Learning and Multimodal Interaction, MLMI 2008 ; Conference date: 08-09-2008 Through 10-09-2008",

year = "2008",

month = sep,

day = "20",

doi = "10.1007/978-3-540-85853-9_18",

language = "Undefined",

isbn = "978-3-540-85852-2",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "196--207",

editor = "Andrei Popescu-Belis and Rainer Stiefelhagen",

booktitle = "Machine Learning for Multimodal Interaction, MLMI 2008",

address = "Germany",

}

op den Akker, H, op den Akker, HJA & Schulz, C 2008, Exploring Features and Classifiers for Dialogue Act Segmentation. in A Popescu-Belis & R Stiefelhagen (eds), Machine Learning for Multimodal Interaction, MLMI 2008., 10.1007/978-3-540-85853-9_18, Lecture Notes in Computer Science, vol. 5237, Springer, Berlin / Heidelberg, pp. 196-207, 5th International Workshop on Machine Learning and Multimodal Interaction, MLMI 2008, Berlin, 8/09/08. https://doi.org/10.1007/978-3-540-85853-9_18

Exploring Features and Classifiers for Dialogue Act Segmentation. / op den Akker, Harm; op den Akker, Hendrikus J.A.; Schulz, Christian.
Machine Learning for Multimodal Interaction, MLMI 2008. ed. / Andrei Popescu-Belis; Rainer Stiefelhagen. Berlin / Heidelberg: Springer, 2008. p. 196-207 10.1007/978-3-540-85853-9_18 (Lecture Notes in Computer Science; Vol. 5237).

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

TY - GEN

T1 - Exploring Features and Classifiers for Dialogue Act Segmentation

AU - op den Akker, Harm

AU - op den Akker, Hendrikus J.A.

AU - Schulz, Christian

N1 - 10.1007/978-3-540-85853-9_18

PY - 2008/9/20

Y1 - 2008/9/20

N2 - This paper takes a classical machine learning approach to the task of Dialogue Act segmentation. A thorough empirical evaluation of features, both used in other studies as well as new ones, is performed. An explorative study to the effectiveness of different classification methods is done by looking at 29 different classifiers implemented in WEKA. The output of the developed classifier is examined closely and points of possible improvement are given.

AB - This paper takes a classical machine learning approach to the task of Dialogue Act segmentation. A thorough empirical evaluation of features, both used in other studies as well as new ones, is performed. An explorative study to the effectiveness of different classification methods is done by looking at 29 different classifiers implemented in WEKA. The output of the developed classifier is examined closely and points of possible improvement are given.

KW - HMI-MI: MULTIMODAL INTERACTIONS

KW - EC Grant Agreement nr.: FP6/0033812

KW - EWI-14954

KW - IR-65340

KW - Machine classification

KW - METIS-255875

KW - Conversational Analysis

U2 - 10.1007/978-3-540-85853-9_18

DO - 10.1007/978-3-540-85853-9_18

M3 - Conference contribution

SN - 978-3-540-85852-2

T3 - Lecture Notes in Computer Science

SP - 196

EP - 207

BT - Machine Learning for Multimodal Interaction, MLMI 2008

A2 - Popescu-Belis, Andrei

A2 - Stiefelhagen, Rainer

PB - Springer

CY - Berlin / Heidelberg

T2 - 5th International Workshop on Machine Learning and Multimodal Interaction, MLMI 2008

Y2 - 8 September 2008 through 10 September 2008

ER -