# DyREx: Dynamic Query Representation for Extractive Question Answering

Source: [DyREx: Dynamic Query Representation for Extractive Question Answering](<https://www.sota2.com/research/paper/68fa6dc51e209131cea3c0a5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:43:27.144Z

Authors: Urchade Zaratiana, Niama El Khbir, Dennis N\\'u\\~nez, Pierre Holat, Nadi Tomeh, Thierry Charnois

Published: 2022-10-26T21:26:44.000Z

## Abstract

Extractive question answering (ExQA) is an essential task for Natural Language Processing. The dominant approach to ExQA is one that represents the input sequence tokens (question and passage) with a pre-trained transformer, then uses two learned query vectors to compute distributions over the start and end answer span positions. These query vectors lack the context of the inputs, which can be a bottleneck for the model performance. To address this problem, we propose \\textit{DyREx}, a generalization of the \\textit{vanilla} approach where we dynamically compute query vectors given the input, using an attention mechanism through transformer layers. Empirical observations demonstrate that our approach consistently improves the performance over the standard one. The code and accompanying files for running the experiments are available at \\url{https://github.com/urchade/DyReX}.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2210.15048>)

[PDF](<https://arxiv.org/pdf/2210.15048.pdf>)

[Implementation](<https://github.com/urchade/DyReX>)