Understanding question-answering systems: Evolution, applications, trends, and challenges

Amer Farea; Frank Emmert-Streib

doi:10.1016/j.engappai.2025.110997

Understanding question-answering systems: Evolution, applications, trends, and challenges

Amer Farea
, Frank Emmert-Streib^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › Scientific › peer-review

1 Citation (Scopus)

36 Downloads (Pure)

Abstract

Question answering (QA) systems have garnered significant attention in recent years due to their potential to bridge the gap between human language understanding and machine intelligence. Consequently, a wide variety of approaches have been developed, each tailored to specific tasks. In this survey paper, we provide a comprehensive overview of three prominent QA paradigms: Extractive, generative, and Visual QA. We discuss the underlying principles, methodologies, applications, challenges, and recent trends in each of these areas. By synthesizing insights from the existing literature and research findings, we aim to provide a holistic understanding of extractive, generative, and Visual QA systems and offer insights into their strengths, limitations, and future directions.

Original language	English
Article number	110997
Journal	Engineering Applications of Artificial Intelligence
Volume	156
Issue number	Part A
DOIs	https://doi.org/10.1016/j.engappai.2025.110997
Publication status	Published - 15 Sept 2025
Publication type	A1 Journal article-refereed

Keywords

Extractive Question Answering
Generative Question Answering
Machine learning
Natural language processing
Neural networks
Visual Question Answering

Publication forum classification

Publication forum level 2

ASJC Scopus subject areas

Control and Systems Engineering
Artificial Intelligence
Electrical and Electronic Engineering

Access to Document

10.1016/j.engappai.2025.110997Licence: CC BY

1-s2.0-S0952197625009972-mainFinal published version, 1.06 MBLicence: CC BY

https://urn.fi/URN:NBN:fi:tuni-202507047543Licence: CC BY

Cite this

@article{0e4992b530994af7bd8512ed998f7a42,

title = "Understanding question-answering systems: Evolution, applications, trends, and challenges",

abstract = "Question answering (QA) systems have garnered significant attention in recent years due to their potential to bridge the gap between human language understanding and machine intelligence. Consequently, a wide variety of approaches have been developed, each tailored to specific tasks. In this survey paper, we provide a comprehensive overview of three prominent QA paradigms: Extractive, generative, and Visual QA. We discuss the underlying principles, methodologies, applications, challenges, and recent trends in each of these areas. By synthesizing insights from the existing literature and research findings, we aim to provide a holistic understanding of extractive, generative, and Visual QA systems and offer insights into their strengths, limitations, and future directions.",

keywords = "Extractive Question Answering, Generative Question Answering, Machine learning, Natural language processing, Neural networks, Visual Question Answering",

author = "Amer Farea and Frank Emmert-Streib",

note = "Publisher Copyright: {\textcopyright} 2025 The Authors",

year = "2025",

month = sep,

day = "15",

doi = "10.1016/j.engappai.2025.110997",

language = "English",

volume = "156",

journal = "Engineering Applications of Artificial Intelligence",

issn = "0952-1976",

publisher = "Elsevier Limited",

number = "Part A",

}

TY - JOUR

T1 - Understanding question-answering systems

T2 - Evolution, applications, trends, and challenges

AU - Farea, Amer

AU - Emmert-Streib, Frank

PY - 2025/9/15

Y1 - 2025/9/15

N2 - Question answering (QA) systems have garnered significant attention in recent years due to their potential to bridge the gap between human language understanding and machine intelligence. Consequently, a wide variety of approaches have been developed, each tailored to specific tasks. In this survey paper, we provide a comprehensive overview of three prominent QA paradigms: Extractive, generative, and Visual QA. We discuss the underlying principles, methodologies, applications, challenges, and recent trends in each of these areas. By synthesizing insights from the existing literature and research findings, we aim to provide a holistic understanding of extractive, generative, and Visual QA systems and offer insights into their strengths, limitations, and future directions.

AB - Question answering (QA) systems have garnered significant attention in recent years due to their potential to bridge the gap between human language understanding and machine intelligence. Consequently, a wide variety of approaches have been developed, each tailored to specific tasks. In this survey paper, we provide a comprehensive overview of three prominent QA paradigms: Extractive, generative, and Visual QA. We discuss the underlying principles, methodologies, applications, challenges, and recent trends in each of these areas. By synthesizing insights from the existing literature and research findings, we aim to provide a holistic understanding of extractive, generative, and Visual QA systems and offer insights into their strengths, limitations, and future directions.

KW - Extractive Question Answering

KW - Generative Question Answering

KW - Machine learning

KW - Natural language processing

KW - Neural networks

KW - Visual Question Answering

U2 - 10.1016/j.engappai.2025.110997

DO - 10.1016/j.engappai.2025.110997

M3 - Article

AN - SCOPUS:105005598376

SN - 0952-1976

VL - 156

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

IS - Part A

M1 - 110997

ER -

Understanding question-answering systems: Evolution, applications, trends, and challenges

Abstract

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this