# Multimodal Routing: Improving Local and Global Interpretability of Multimodal Language Analysis

arXiv: https://arxiv.org/abs/2004.14198 · HTML: https://mlsanity.com/paper/2004.14198/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2020.

## Built on by (most cited first, 1 of 1)

- [Video Sentiment Analysis with Bimodal Information-augmented Multi-Head Attention](https://mlsanity.com/paper/2103.02362/) (2021)

## Abstract (arXiv)

The human language can be expressed through multiple sources of information known as modalities, including tones of voice, facial gestures, and spoken language. Recent multimodal learning with strong performances on human-centric tasks such as sentiment analysis and emotion recognition are often black-box, with very limited interpretability. In this paper we propose Multimodal Routing, which dynamically adjusts weights between input modalities and output representations differently for each input sample. Multimodal routing can identify relative importance of both individual modalities and cross-modality features. Moreover, the weight assignment by routing allows us to interpret modality-prediction relationships not only globally (i.e. general trends over the whole dataset), but also locally for each single input sample, meanwhile keeping competitive performance compared to state-of-the-art methods.