Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors


  • Yansen Wang Tsinghua University
  • Ying Shen Carnegie Mellon University
  • Zhun Liu Carnegie Mellon University
  • Paul Pu Liang Carnegie Mellon University
  • Amir Zadeh Carnegie Mellon University
  • Louis-Philippe Morency Carnegie Mellon University




Humans convey their intentions through the usage of both verbal and nonverbal behaviors during face-to-face communication. Speaker intentions often vary dynamically depending on different nonverbal contexts, such as vocal patterns and facial expressions. As a result, when modeling human language, it is essential to not only consider the literal meaning of the words but also the nonverbal contexts in which these words appear. To better model human language, we first model expressive nonverbal representations by analyzing the fine-grained visual and acoustic patterns that occur during word segments. In addition, we seek to capture the dynamic nature of nonverbal intents by shifting word representations based on the accompanying nonverbal behaviors. To this end, we propose the Recurrent Attended Variation Embedding Network (RAVEN) that models the fine-grained structure of nonverbal subword sequences and dynamically shifts word representations based on nonverbal cues. Our proposed model achieves competitive performance on two publicly available datasets for multimodal sentiment analysis and emotion recognition. We also visualize the shifted word representations in different nonverbal contexts and summarize common patterns regarding multimodal variations of word representations.




How to Cite

Wang, Y., Shen, Y., Liu, Z., Liang, P. P., Zadeh, A., & Morency, L.-P. (2019). Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 7216-7223. https://doi.org/10.1609/aaai.v33i01.33017216



AAAI Technical Track: Natural Language Processing