S. Germesin, and T. Wilson. Proceedings of the 11th International Conference on Multimodal Interfaces and the 6th Workshop on Machine Learning for Multimodal Interfaces (ICMI-MLMI '09), Cambridge, MA, USA, page 7-14. (2009)
DOI: 10.1145/1647314.1647319
Abstract
This paper presents a system for the automatic detection of agreements in multi-party conversations. We investigate various types of features that are useful for identifying agreements, including lexical, prosodic, and structural features. This system is implemented using supervised machine learning techniques and yields competitive results: Accuracy of 98.1 percent and a kappa value of 0.4. We also begin to explore the novel task of detecting the addressee of agreements (which speaker is being agreed with). Our system for this task achieves an accuracy of 80.3 percent, a 56 percent improvement over the baseline.
Proceedings of the 11th International Conference on Multimodal Interfaces and the 6th Workshop on Machine Learning for Multimodal Interfaces (ICMI-MLMI '09), Cambridge, MA, USA
year
2009
pages
7-14
file
ACM Digital Library:2009/GermesinWilson09ICMI.pdf:PDF
%0 Conference Paper
%1 GermesinWilson09ICMI
%A Germesin, Sebastian
%A Wilson, Theresa
%B Proceedings of the 11th International Conference on Multimodal Interfaces and the 6th Workshop on Machine Learning for Multimodal Interfaces (ICMI-MLMI '09), Cambridge, MA, USA
%D 2009
%K v1205 acm paper ai dfki interface multimodal user interaction team dialog analysis learn
%P 7-14
%R 10.1145/1647314.1647319
%T Agreement Detection in Multiparty Conversation
%X This paper presents a system for the automatic detection of agreements in multi-party conversations. We investigate various types of features that are useful for identifying agreements, including lexical, prosodic, and structural features. This system is implemented using supervised machine learning techniques and yields competitive results: Accuracy of 98.1 percent and a kappa value of 0.4. We also begin to explore the novel task of detecting the addressee of agreements (which speaker is being agreed with). Our system for this task achieves an accuracy of 80.3 percent, a 56 percent improvement over the baseline.
@inproceedings{GermesinWilson09ICMI,
abstract = {This paper presents a system for the automatic detection of agreements in multi-party conversations. We investigate various types of features that are useful for identifying agreements, including lexical, prosodic, and structural features. This system is implemented using supervised machine learning techniques and yields competitive results: Accuracy of 98.1 percent and a kappa value of 0.4. We also begin to explore the novel task of detecting the addressee of agreements (which speaker is being agreed with). Our system for this task achieves an accuracy of 80.3 percent, a 56 percent improvement over the baseline.},
added-at = {2012-05-30T10:46:25.000+0200},
author = {Germesin, Sebastian and Wilson, Theresa},
biburl = {https://www.bibsonomy.org/bibtex/269c6819f3560d214c59dd1a5ad2c5ff7/flint63},
booktitle = {Proceedings of the 11th International Conference on Multimodal Interfaces and the 6th Workshop on Machine Learning for Multimodal Interfaces (ICMI-MLMI '09), Cambridge, MA, USA},
doi = {10.1145/1647314.1647319},
file = {ACM Digital Library:2009/GermesinWilson09ICMI.pdf:PDF},
groups = {public},
interhash = {398a83a80dfd7575d02ca3c3c19179ca},
intrahash = {69c6819f3560d214c59dd1a5ad2c5ff7},
keywords = {v1205 acm paper ai dfki interface multimodal user interaction team dialog analysis learn},
pages = {7-14},
timestamp = {2018-04-16T12:15:49.000+0200},
title = {Agreement Detection in Multiparty Conversation},
username = {flint63},
year = 2009
}