Workshop: Second Workshop on Efficient Natural Language and Speech Processing (ENLSP-II)

Dynamic Query Representation for Extractive Question Answering

Urchade Zaratiana · Niama El Khbir · Dennis Núñez-Fernández · Pierre Holat · Nadi Tomeh · Thierry Charnois

Keywords: [ ENLSP-Main ]


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 in the supplementary materials.

Chat is not available.