TY - GEN
T1 - Automatic Decision Detection in Meeting Speech
AU - Hsueh, Pei-Yun
AU - Moore, Johanna D.
PY - 2008
Y1 - 2008
N2 - Decision making is an important aspect of meetings in organisational settings, and archives of meeting recordings constitute a valuable source of information about the decisions made. However, standard utilities such as playback and keyword search are not sufficient for locating decision points from meeting archives. In this paper, we present the AMI DecisionDetector, a system that automatically detects and highlights where the decision-related conversations are. In this paper, we apply the models developed in our previous work [1], which detects decision-related dialogue acts (DAs) from parts of the transcripts that have been manually annotated as extract-worthy, to the task of detecting decision-related DAs and topic segments directly from complete transcripts. Results show that we need to combine features extracted from multiple knowledge sources (e.g., lexical, prosodic, DA-related, and topical class) in order to yield the model with the highest precision. We have provided a quantitative account of the feature class effects. As our ultimate goal is to operate AMI DecisionDetector in a fully automatic fashion, we also investigate the impacts of using automatically generated features, for example, the 5-class DA features obtained in [2].
AB - Decision making is an important aspect of meetings in organisational settings, and archives of meeting recordings constitute a valuable source of information about the decisions made. However, standard utilities such as playback and keyword search are not sufficient for locating decision points from meeting archives. In this paper, we present the AMI DecisionDetector, a system that automatically detects and highlights where the decision-related conversations are. In this paper, we apply the models developed in our previous work [1], which detects decision-related dialogue acts (DAs) from parts of the transcripts that have been manually annotated as extract-worthy, to the task of detecting decision-related DAs and topic segments directly from complete transcripts. Results show that we need to combine features extracted from multiple knowledge sources (e.g., lexical, prosodic, DA-related, and topical class) in order to yield the model with the highest precision. We have provided a quantitative account of the feature class effects. As our ultimate goal is to operate AMI DecisionDetector in a fully automatic fashion, we also investigate the impacts of using automatically generated features, for example, the 5-class DA features obtained in [2].
KW - argumentation modelling
KW - meeting tracking and analysis
KW - spoken language understanding
U2 - 10.1007/978-3-540-78155-4_15
DO - 10.1007/978-3-540-78155-4_15
M3 - Conference contribution
SN - 978-3-540-78154-7
T3 - Lecture Notes in Computer Science
SP - 168
EP - 179
BT - Machine Learning for Multimodal Interaction
PB - Springer
ER -