# Conflict as an Inverse of Attention in Sequence Relationship

## TL;DR

This paper introduces a Conflict model that complements attention mechanisms by focusing on sequence repulsion, improving performance in contrastive or dissimilar sequence relationship tasks.

## Contribution

It proposes a novel Conflict model that emphasizes sequence repulsion, addressing limitations of traditional attention in non-matching or contrastive sequence relationships.

## Key findings

- Conflict model enhances performance when sequences are dissimilar.
- Combining Conflict with attention improves overall accuracy.
- Empirical results demonstrate effectiveness across tasks.

## Abstract

Attention is a very efficient way to model the relationship between two sequences by comparing how similar two intermediate representations are. Initially demonstrated in NMT, it is a standard in all NLU tasks today when efficient interaction between sequences is considered. However, we show that attention, by virtue of its composition, works best only when it is given that there is a match somewhere between two sequences. It does not very well adapt to cases when there is no similarity between two sequences or if the relationship is contrastive. We propose an Conflict model which is very similar to how attention works but which emphasizes mostly on how well two sequences repel each other and finally empirically show how this method in conjunction with attention can boost the overall performance.