A Question-Answering System that Can Count

This paper proposes a conceptual architectural design of Question- Answering (QA) system that can solve “counting” problem. Counting problem is the inability of QA system to produce numerical answer based on retrieved rationale (in text passage) containing list of items. For example, consider “How m...

Full description

Bibliographic Details
Main Authors: Abbas Saliimi, Lokman, Mohamed Ariff, Ameedeen, Ngahzaifa, Ab. Ghani
Format: Conference or Workshop Item
Language:English
Published: Springer, Singapore 2021
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/35064/1/A%20Question-Answering%20System%20that%20Can%20Count.pdf
_version_ 1825824155285585920
author Abbas Saliimi, Lokman
Mohamed Ariff, Ameedeen
Ngahzaifa, Ab. Ghani
author_facet Abbas Saliimi, Lokman
Mohamed Ariff, Ameedeen
Ngahzaifa, Ab. Ghani
author_sort Abbas Saliimi, Lokman
collection UMP
description This paper proposes a conceptual architectural design of Question- Answering (QA) system that can solve “counting” problem. Counting problem is the inability of QA system to produce numerical answer based on retrieved rationale (in text passage) containing list of items. For example, consider “How many items are on sale?” as question and “Currently shampoo, soap and conditioner are on sale” as retrieved rationale from text passage. Normally, system will produce “shampoo, soap and conditioner” as an answer while the ground truth answer is “three”. In other words, system is simply unable to perform the counting process needed in order to correctly answer such questions. To solve this problem, QA system architecture with following components is proposed: (1) A classifier to determine if given question requires a counting answer, (2) A classifier to determine if current system’s answer is not numeric, and (3) A counting method to produce numerical answer based on given rationale. Despite looking like a whole system, the proposed architecture is actually a modular system whereby each component can operate independently (allowing each component to be separately implemented by other systems). In essence, this paper intents to demonstrate a general idea of how the defined problem can be solved using a modular system, that hopefully also opens up more flexible enhancements in the future.
first_indexed 2024-03-06T12:59:49Z
format Conference or Workshop Item
id UMPir35064
institution Universiti Malaysia Pahang
language English
last_indexed 2024-03-06T12:59:49Z
publishDate 2021
publisher Springer, Singapore
record_format dspace
spelling UMPir350642022-09-05T09:00:12Z http://umpir.ump.edu.my/id/eprint/35064/ A Question-Answering System that Can Count Abbas Saliimi, Lokman Mohamed Ariff, Ameedeen Ngahzaifa, Ab. Ghani QA75 Electronic computers. Computer science QA76 Computer software This paper proposes a conceptual architectural design of Question- Answering (QA) system that can solve “counting” problem. Counting problem is the inability of QA system to produce numerical answer based on retrieved rationale (in text passage) containing list of items. For example, consider “How many items are on sale?” as question and “Currently shampoo, soap and conditioner are on sale” as retrieved rationale from text passage. Normally, system will produce “shampoo, soap and conditioner” as an answer while the ground truth answer is “three”. In other words, system is simply unable to perform the counting process needed in order to correctly answer such questions. To solve this problem, QA system architecture with following components is proposed: (1) A classifier to determine if given question requires a counting answer, (2) A classifier to determine if current system’s answer is not numeric, and (3) A counting method to produce numerical answer based on given rationale. Despite looking like a whole system, the proposed architecture is actually a modular system whereby each component can operate independently (allowing each component to be separately implemented by other systems). In essence, this paper intents to demonstrate a general idea of how the defined problem can be solved using a modular system, that hopefully also opens up more flexible enhancements in the future. Springer, Singapore 2021 Conference or Workshop Item PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/35064/1/A%20Question-Answering%20System%20that%20Can%20Count.pdf Abbas Saliimi, Lokman and Mohamed Ariff, Ameedeen and Ngahzaifa, Ab. Ghani (2021) A Question-Answering System that Can Count. In: Computational Science and Technology: 7th ICCST 2020 , 29-30 August 2020 , Pattaya, Thailand. pp. 61-70., 724. ISBN 978-981-33-4068-8 (Published) https://doi.org/10.1007/978-981-33-4069-5_6
spellingShingle QA75 Electronic computers. Computer science
QA76 Computer software
Abbas Saliimi, Lokman
Mohamed Ariff, Ameedeen
Ngahzaifa, Ab. Ghani
A Question-Answering System that Can Count
title A Question-Answering System that Can Count
title_full A Question-Answering System that Can Count
title_fullStr A Question-Answering System that Can Count
title_full_unstemmed A Question-Answering System that Can Count
title_short A Question-Answering System that Can Count
title_sort question answering system that can count
topic QA75 Electronic computers. Computer science
QA76 Computer software
url http://umpir.ump.edu.my/id/eprint/35064/1/A%20Question-Answering%20System%20that%20Can%20Count.pdf
work_keys_str_mv AT abbassaliimilokman aquestionansweringsystemthatcancount
AT mohamedariffameedeen aquestionansweringsystemthatcancount
AT ngahzaifaabghani aquestionansweringsystemthatcancount
AT abbassaliimilokman questionansweringsystemthatcancount
AT mohamedariffameedeen questionansweringsystemthatcancount
AT ngahzaifaabghani questionansweringsystemthatcancount