TY - GEN
T1 - Deep convolutional neural network textual features and multiple kernel learning for utterance-level multimodal sentiment analysis
AU - Poria, Soujanya
AU - Cambria, Erik
AU - Gelbukh, Alexander
N1 - Publisher Copyright:
© 2015 Association for Computational Linguistics.
PY - 2015
Y1 - 2015
N2 - We present a novel way of extracting features from short texts, based on the activation values of an inner layer of a deep convolutional neural network. We use the extracted features in multimodal sentiment analysis of short video clips representing one sentence each. We use the combined feature vectors of textual, visual, and audio modalities to train a classifier based on multiple kernel learning, which is known to be good at heterogeneous data. We obtain 14% performance improvement over the state of the art and present a parallelizable decision-level data fusion method, which is much faster, though slightly less accurate.
AB - We present a novel way of extracting features from short texts, based on the activation values of an inner layer of a deep convolutional neural network. We use the extracted features in multimodal sentiment analysis of short video clips representing one sentence each. We use the combined feature vectors of textual, visual, and audio modalities to train a classifier based on multiple kernel learning, which is known to be good at heterogeneous data. We obtain 14% performance improvement over the state of the art and present a parallelizable decision-level data fusion method, which is much faster, though slightly less accurate.
UR - http://www.scopus.com/inward/record.url?scp=84943617823&partnerID=8YFLogxK
U2 - 10.18653/v1/d15-1303
DO - 10.18653/v1/d15-1303
M3 - Contribución a la conferencia
AN - SCOPUS:84943617823
T3 - Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing
SP - 2539
EP - 2544
BT - Conference Proceedings - EMNLP 2015
PB - Association for Computational Linguistics (ACL)
T2 - Conference on Empirical Methods in Natural Language Processing, EMNLP 2015
Y2 - 17 September 2015 through 21 September 2015
ER -