# Attention-based Conditioning Methods for External Knowledge Integration

arXiv: https://arxiv.org/abs/1906.03674 · HTML: https://mlsanity.com/paper/1906.03674/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2019.

## Built on by (most cited first, 8 of 8)

- [Hopper: Multi-hop Transformer for Spatiotemporal Reasoning](https://mlsanity.com/paper/2103.10574/) (2021)
- [Dual Conditioned Diffusion Models for Out-Of-Distribution Detection: Application to Fetal Ultrasound Videos](https://mlsanity.com/paper/2311.00469/) (2023)
- [Using Knowledge-Embedded Attention to Augment Pre-trained Language Models for Fine-Grained Emotion Recognition](https://mlsanity.com/paper/2108.00194/) (2021)
- [Enabling High-Level Machine Reasoning with Cognitive Neuro-Symbolic Systems](https://mlsanity.com/paper/2311.07759/) (2023)
- [Breaking the Resource Wall: Geometry-Guided Sequence Modeling for Efficient Semantic Segmentation](https://mlsanity.com/paper/2604.23399/) (2026)
- [Depression detection in social media posts using affective and social norm features](https://mlsanity.com/paper/2303.14279/) (2023)
- [TPK: Trustworthy Trajectory Prediction Integrating Prior Knowledge For Interpretability and Kinematic Feasibility](https://mlsanity.com/paper/2505.06743/) (2025)
- [Attention-based conditioning methods using variable frame rate for style-robust speaker verification](https://mlsanity.com/paper/2206.13680/) (2022)

## Abstract (arXiv)

In this paper, we present a novel approach for incorporating external knowledge in Recurrent Neural Networks (RNNs). We propose the integration of lexicon features into the self-attention mechanism of RNN-based architectures. This form of conditioning on the attention distribution, enforces the contribution of the most salient words for the task at hand. We introduce three methods, namely attentional concatenation, feature-based gating and affine transformation. Experiments on six benchmark datasets show the effectiveness of our methods. Attentional feature-based gating yields consistent performance improvement across tasks. Our approach is implemented as a simple add-on module for RNN-based models with minimal computational overhead and can be adapted to any deep neural architecture.