ISS-MULT: Intelligent Sample Selection for Multi-Task Learning in Question Answering

TL;DR

This paper introduces ISS-MULT, an intelligent sample selection method that enhances transfer learning for question answering tasks, demonstrating significant improvements especially in answer triggering across multiple datasets.

Contribution

The paper proposes a novel ISS-MULT method to improve transfer learning in question answering, extending the existing MULT approach with intelligent sample selection.

Findings

Transfer learning improves performance with related corpora.

ISS-MULT significantly enhances the MULT method.

Improvements are more notable in answer triggering tasks.

Abstract

Transferring knowledge from a source domain to another domain is useful, especially when gathering new data is very expensive and time-consuming. Deep networks have been well-studied for question answering tasks in recent years; however, no prominent research for transfer learning through deep neural networks exists in the question answering field. In this paper, two main methods (INIT and MULT) in this field are examined. Then, a new method named Intelligent sample selection (ISS-MULT) is proposed to improve the MULT method for question answering tasks. Different datasets, specificay SQuAD, SelQA, WikiQA, NewWikiQA and InforBoxQA, are used for evaluation. Moreover, two different tasks of question answering - answer selection and answer triggering - are evaluated to examine the effectiveness of transfer learning. The results show that using transfer learning generally improves the performance if the corpora are related and are based on the same policy. In addition, using ISS-MULT could finely improve the MULT method for question answering tasks, and these improvements prove more significant in the answer triggering task.