Don't Read Too Much into It: Adaptive Computation for Open-Domain Question Answering

by   Yuxiang WU, et al.

Most approaches to Open-Domain Question Answering consist of a light-weight retriever that selects a set of candidate passages, and a computationally expensive reader that examines the passages to identify the correct answer. Previous works have shown that as the number of retrieved passages increases, so does the performance of the reader. However, they assume all retrieved passages are of equal importance and allocate the same amount of computation to them, leading to a substantial increase in computational cost. To reduce this cost, we propose the use of adaptive computation to control the computational budget allocated for the passages to be read. We first introduce a technique operating on individual passages in isolation which relies on anytime prediction and a per-layer estimation of an early exit probability. We then introduce SkylineBuilder, an approach for dynamically deciding on which passage to allocate computation at each step, based on a resource allocation policy trained via reinforcement learning. Our results on SQuAD-Open show that adaptive computation with global prioritisation improves over several strong static and adaptive methods, leading to a 4.3x reduction in computation while retaining 95


page 1

page 2

page 3

page 4


Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints

Adaptive Computation (AC) has been shown to be effective in improving th...

Decoupled Transformer for Scalable Inference in Open-domain Question Answering

Large transformer models, such as BERT, achieve state-of-the-art results...

Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?

Recent state-of-the-art open-domain QA models are typically based on a t...

PonderNet: Learning to Ponder

In standard neural networks the amount of computation used grows with th...

Adaptive Document Retrieval for Deep Question Answering

State-of-the-art systems in deep question answering proceed as follows: ...

Improving Question Answering Performance through Manual Annotation: Costs, Benefits and Strategies

Recently proposed systems for open-domain question answering (OpenQA) re...

Please sign up or login with your details

Forgot password? Click here to reset