Gated Self-Matching Networks for Reading Comprehension and Question Answering

TLDR

The paper introduces gated self‑matching networks designed to answer questions from a given passage in reading comprehension style question answering. The model uses gated attention‑based recurrent networks to create a question‑aware passage representation, applies a self‑matching attention mechanism to refine it by matching the passage against itself, and then employs pointer networks to locate answer positions, with extensive evaluation on the SQuAD dataset. The single model attains 71.3% exact match on the hidden test set, the ensemble reaches 75.9%, and the model was first on the SQuAD leaderboard for both configurations at submission.

Abstract

In this paper, we present the gated self-matching networks for reading comprehension style question answering, which aims to answer questions from a given passage. We first match the question and passage with gated attention-based recurrent networks to obtain the question-aware passage representation. Then we propose a self-matching attention mechanism to refine the representation by matching the passage against itself, which effectively encodes information from the whole passage. We finally employ the pointer networks to locate the positions of answers from the passages. We conduct extensive experiments on the SQuAD dataset. The single model achieves 71.3% on the evaluation metrics of exact match on the hidden test set, while the ensemble model further boosts the results to 75.9%. At the time of submission of the paper, our model holds the first place on the SQuAD leaderboard for both single and ensemble model.