Shiv Shankar


2022

pdf bib
Multimodal fusion via cortical network inspired losses
Shiv Shankar
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Information integration from different modalities is an active area of research. Human beings and, in general, biological neural systems are quite adept at using a multitude of signals from different sensory perceptive fields to interact with the environment and each other. Recent work in deep fusion models via neural networks has led to substantial improvements over unimodal approaches in areas like speech recognition, emotion recognition and analysis, captioning and image description. However, such research has mostly focused on architectural changes allowing for fusion of different modalities while keeping the model complexity manageable.Inspired by neuroscientific ideas about multisensory integration and processing, we investigate the effect of introducing neural dependencies in the loss functions. Experiments on multimodal sentiment analysis tasks with different models show that our approach provides a consistent performance boost.

2018

pdf bib
Surprisingly Easy Hard-Attention for Sequence to Sequence Learning
Shiv Shankar | Siddhant Garg | Sunita Sarawagi
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

In this paper we show that a simple beam approximation of the joint distribution between attention and output is an easy, accurate, and efficient attention mechanism for sequence to sequence learning. The method combines the advantage of sharp focus in hard attention and the implementation ease of soft attention. On five translation tasks we show effortless and consistent gains in BLEU compared to existing attention mechanisms.