Query-Reduction Networks for Question Answering

TL;DR

The paper introduces Query-Reduction Networks (QRN), a novel RNN variant that improves reasoning over multiple facts in question answering tasks, achieving state-of-the-art results and enhanced computational efficiency.

Contribution

QRN effectively models both short-term and long-term dependencies, reducing queries as it processes context, and enables parallelization for faster training and inference.

Findings

Achieves state-of-the-art results on bAbI QA and dialog tasks.

Reduces training and inference time complexity significantly.

Successfully applied to real goal-oriented dialog datasets.

Abstract

In this paper, we study the problem of question answering when reasoning over multiple facts is required. We propose Query-Reduction Network (QRN), a variant of Recurrent Neural Network (RNN) that effectively handles both short-term (local) and long-term (global) sequential dependencies to reason over multiple facts. QRN considers the context sentences as a sequence of state-changing triggers, and reduces the original query to a more informed query as it observes each trigger (context sentence) through time. Our experiments show that QRN produces the state-of-the-art results in bAbI QA and dialog tasks, and in a real goal-oriented dialog dataset. In addition, QRN formulation allows parallelization on RNN's time axis, saving an order of magnitude in time complexity for training and inference.