Neural Skill Transfer from Supervised Language Tasks to Reading Comprehension

TL;DR

This paper introduces a neural skill transfer method that leverages knowledge from various lower-level language tasks to enhance reading comprehension, demonstrating improved performance especially with limited training data.

Contribution

The paper presents a novel neural skill transfer approach that integrates multiple language skills into reading comprehension models, showing significant empirical improvements.

Findings

Skill transfer improves reading comprehension performance.

Transfer is effective with limited training data.

Token-wise deep label supervision enhances transfer learning.

Abstract

Reading comprehension is a challenging task in natural language processing and requires a set of skills to be solved. While current approaches focus on solving the task as a whole, in this paper, we propose to use a neural network `skill' transfer approach. We transfer knowledge from several lower-level language tasks (skills) including textual entailment, named entity recognition, paraphrase detection and question type classification into the reading comprehension model. We conduct an empirical evaluation and show that transferring language skill knowledge leads to significant improvements for the task with much fewer steps compared to the baseline model. We also show that the skill transfer approach is effective even with small amounts of training data. Another finding of this work is that using token-wise deep label supervision for text classification improves the performance of transfer learning.