Multi-attention Recurrent Network for Human Communication Comprehension

2018-02-08

Proceedings of the AAAI Conference on Artificial Intelligence, 32

Volume

Thirty-Second AAAI Conference on Artificial Intelligence 2018

Main Track: NLP and Machine Learning

Human face-to-face communication is a complex multimodal signal. We use words (language modality), gestures (vision modality) and changes in tone (acoustic modality) to convey our intentions. Humans easily process and understand face-to-face communication, however, comprehending this form of communication remains a significant challenge for Artificial Intelligence (AI). AI must understand each modality and the interactions between them that shape the communication. In this paper, we present a novel neural architecture for understanding human communication called the Multi-attention Recurrent Network (MARN). The main strength of our model comes from discovering interactions between modalities through time using a neural component called the Multi-attention Block (MAB) and storing them in the hybrid memory of a recurrent component called the Long-short Term Hybrid Memory (LSTHM). We perform extensive comparisons on six publicly available datasets for multimodal sentiment analysis, speaker trait recognition and emotion recognition. MARN shows state- of-the-art results performance in all the datasets.

10.1609/aaai.v32i1.12024