Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices

TL;DR

This survey reviews the evolution, challenges, datasets, and evaluation metrics in the question answering field, emphasizing deep learning advancements and open research issues across various question types and sources.

Contribution

It provides a comprehensive overview of QA research directions, challenges, datasets, and evaluation methods, highlighting recent deep learning impacts and unresolved issues.

Findings

Deep learning models have significantly improved QA performance.

Open challenges include automatic question generation and low-resource language support.

A detailed survey of datasets and evaluation metrics is provided.

Abstract

The usage and amount of information available on the internet increase over the past decade. This digitization leads to the need for automated answering system to extract fruitful information from redundant and transitional knowledge sources. Such systems are designed to cater the most prominent answer from this giant knowledge source to the user query using natural language understanding (NLU) and thus eminently depends on the Question-answering(QA) field. Question answering involves but not limited to the steps like mapping of user question to pertinent query, retrieval of relevant information, finding the best suitable answer from the retrieved information etc. The current improvement of deep learning models evince compelling performance improvement in all these tasks. In this review work, the research directions of QA field are analyzed based on the type of question, answer type, source of evidence-answer, and modeling approach. This detailing followed by open challenges of the field like automatic question generation, similarity detection and, low resource availability for a language. In the end, a survey of available datasets and evaluation measures is presented.