# Understanding How Encoder-Decoder Architectures Attend

arXiv: https://arxiv.org/abs/2110.15253 · HTML: https://mlsanity.com/paper/2110.15253/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 28 Oct 2021.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [State-of-the-art Speech Recognition With Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.01769/) (2017)
- [The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?](https://mlsanity.com/paper/2010.05607/) (2020)
- [Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics](https://mlsanity.com/paper/1906.10720/) (2019)
- [What does Attention in Neural Machine Translation Pay Attention to?](https://mlsanity.com/paper/1710.03348/) (2017)
- [Capacity and Trainability in Recurrent Neural Networks](https://mlsanity.com/paper/1611.09913/) (2016)
- [Saliency-driven Word Alignment Interpretation for Neural Machine Translation](https://mlsanity.com/paper/1906.10282/) (2019)
- [How recurrent networks implement contextual processing in sentiment analysis](https://mlsanity.com/paper/2004.08013/) (2020)
- [The geometry of integration in text classification RNNs](https://mlsanity.com/paper/2010.15114/) (2020)

## Built on by (most cited first, 2 of 2)

- [TranDRL: A Transformer-Driven Deep Reinforcement Learning Enabled Prescriptive Maintenance Framework](https://mlsanity.com/paper/2309.16935/) (2023)
- [Implementing Deep Learning-Based Approaches for Article Summarization in Indian Languages](https://mlsanity.com/paper/2212.05702/) (2022)

## Abstract (arXiv)

Encoder-decoder networks with attention have proven to be a powerful way to solve many sequence-to-sequence tasks. In these networks, attention aligns encoder and decoder states and is often used for visualizing network behavior. However, the mechanisms used by networks to generate appropriate attention matrices are still mysterious. Moreover, how these mechanisms vary depending on the particular architecture used for the encoder and decoder (recurrent, feed-forward, etc.) are also not well understood. In this work, we investigate how encoder-decoder networks solve different sequence-to-sequence tasks. We introduce a way of decomposing hidden states over a sequence into temporal (independent of input) and input-driven (independent of sequence position) components. This reveals how attention matrices are formed: depending on the task requirements, networks rely more heavily on either the temporal or input-driven components. These findings hold across both recurrent and feed-forward architectures despite their differences in forming the temporal components. Overall, our results provide new insight into the inner workings of attention-based encoder-decoder networks.