DyREx: Dynamic Query Representation for Extractive Question Answering
This addresses a specific bottleneck in extractive question answering for NLP applications, but is incremental as it builds on existing transformer-based methods.
The paper tackles the bottleneck in extractive question answering where static query vectors lack input context, proposing DyREx to dynamically compute query vectors using attention, which consistently improves performance over the standard approach.
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}.