A Fully Attention-Based Information Retriever

Abstract

Recurrent neural networks are now the state-ofthe-art in natural language processing because they can build rich contextual representations and process texts of arbitrary length. However, recent developments on attention mechanisms have equipped feedforward networks with similar capabilities, hence enabling faster computations due to the increase in the number of operations that can be parallelized. We explore this new type of architecture in the domain of question-answering and propose a novel approach that we call Fully Attention Based Information Retriever (FABIR). We show that FABIR achieves competitive results in the Stanford Question Answering Dataset (SQuAD) while having fewer parameters and being faster at both learning and inference than rival methods.

Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study

“…Investigating data efficiency of similar solutions to tasks like QA (Question Answering, Correia et al, 2018) with standard datasets such as SQuAD (Rajpurkar et al, 2018) could also be valuable.…”