Multi-level Multiple Attentions for Contextual Multimodal Sentiment Analysis
Soujanya PoriaTemasek Laboratories, Nanyang Technological University, SingaporeErik CambriaSchool of Computer Science and Engineering, Nanyang Technological University, SingaporeDevamanyu HazarikaSchool of Computing, National University of Singapore, SingaporeNavonil MazumderCentro de Investigación en Computación, Instituto Politécnico Nacional, MexicoAmir ZadehLanguage Technologies Institute, Carnegie Mellon University, USALouis‐Philippe MorencyLanguage Technologies Institute, Carnegie Mellon University, USA
2017en
ABI
Abstract
Multimodal sentiment analysis involves identifying sentiment in videos and is a developing field of research. Unlike current works, which model utterances individually, we propose a recurrent model that is able to capture contextual information among utterances. In this paper, we also introduce attentionbased networks for improving both context learning and dynamic feature fusion. Our model shows 6-8% improvement over the state of the art on a benchmark dataset.
Identifiers
Citations and references
Cited by 20 references