skip to main content
10.1145/3632754.3632757acmotherconferencesArticle/Chapter ViewAbstractPublication PagesfireConference Proceedingsconference-collections
research-article

CricGPT: A GPT-aided Question-Answering system for Cricket

Published: 12 February 2024 Publication History

Abstract

Cricket is a popular sport with avid followers across the globe. This paper presents a cricket Question-Answering (QA) system, viz. CricGPT, that leverages the publicly available ESPNCricinfo API data, OpenAI language model, SQLite database, and EJS templates to provide users with a comprehensive and interactive platform for accessing and analyzing cricket statistics on players. The proposed system comprises two distinct functionalities: Field Search and Free Text Search. The Field Search page allows users to explore field-wise statistics through dropdown menus; while the Free Text Search page enables users to input free-text queries and receive accurate responses using the OpenAI language model. For the latter, the system dynamically constructs SQLite queries using OpenAI based on user selections and executes them on the ESPNCricinfo API dataset stored in the SQLite database. The retrieved data is then presented to the user using EJS templates, ensuring a visually appealing and structured representation of cricket statistics. This research contributes to the field of cricket analytics by offering an intuitive and efficient means of accessing and analyzing cricket data using GPT. To our knowledge, no prior work has deployed GPTs for a QA system in cricket. On a set comprising simple and complex free-text questions, the proposed system attains an accuracy of around 85%. Especially on complex questions, CricGPT handsomely outperforms state-of-the-art search systems like ChatGPT, Google and Bing.

Supplementary Material

ZIP File (FIRE_cricGPT.zip)
Paper

References

[1]
[n. d.]. https://ai.facebook.com/blog/large-language-model-llama-meta-ai/. ([n. d.]).
[2]
[n. d.]. https://huggingface.co/bigscience/bloom. ([n. d.]).
[3]
[n. d.]. https://huggingface.co/google/flan-t5-xxl. ([n. d.]).
[4]
Eleni Adamopoulou and Lefteris Moussiades. 2020. An overview of chatbot technology. In IFIP international conference on artificial intelligence applications and innovations. Springer, 373–383.
[5]
Ali Mohamed Nabil Allam and Mohamed Hassan Haggag. 2012. The question answering systems: A survey. International Journal of Research and Reviews in Information Sciences (IJRRIS) 2, 3 (2012).
[6]
Andrew Blair-Stanek, Nils Holzenberger, and Benjamin Van Durme. 2023. Can GPT-3 Perform Statutory Reasoning?https://arxiv.org/abs/2302.06100
[7]
Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.). Vol. 33. Curran Associates, Inc., 1877–1901. https://proceedings.neurips.cc/paper_files/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf
[8]
Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. arxiv:2005.14165 [cs.CL]
[9]
Philipp Christmann, Rishiraj Saha Roy, and Gerhard Weikum. 2022. Beyond NED: Fast and Effective Search Space Reduction for Complex Question Answering over Knowledge Bases. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining (Virtual Event, AZ, USA) (WSDM ’22). Association for Computing Machinery, New York, NY, USA, 172–180. https://doi.org/10.1145/3488560.3498488
[10]
Zhen Jia, Soumajit Pramanik, Rishiraj Saha Roy, and Gerhard Weikum. 2021. Complex Temporal Question Answering on Knowledge Graphs. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management (Virtual Event, Queensland, Australia) (CIKM ’21). Association for Computing Machinery, New York, NY, USA, 792–802. https://doi.org/10.1145/3459637.3482416
[11]
Daniel Martin Katz, Michael James Bommarito, Shang Gao, and Pablo Arredondo. 2023. GPT-4 Passes the Bar Exam. https://dx.doi.org/10.2139/ssrn.4389233
[12]
J. Li and A. Smith. 2021. Healthcare Chatbots using ChatGPT. Journal of Medical Informatics 20, 3 (2021), 345–360.
[13]
Kanpur India Manish Verma.cientist D DMSRDE, DRDO. [n. d.]. Integration of AI-Based Chatbot(ChatGPT) And Supply Chain Management Solution To Enhance Tracking And Queries Response. ([n. d.]).
[14]
Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schütze. 2008. Introduction to Information Retrieval. Cambridge University Press. https://nlp.stanford.edu/IR-book/information-retrieval-book.html
[15]
Ha-Thanh Nguyen, Randy Goebel, Francesca Toni, Kostas Stathis, and Ken Satoh. 2023. How well do SOTA legal reasoning models support abductive reasoning?arxiv:2304.06912 [cs.LO]
[16]
S. Prakash and R. Singh. 2023. Artificial intelligence-based ChatGPT chatbot responses for patient and parent questions on vernal keratoconjunctivitis. Graefe’s Archive for Clinical and Experimental Ophthalmology (2023).
[17]
Yiming Tan, Dehai Min, Yu Li, Wenbo Li, Nan Hu, Yongrui Chen, and Guilin Qi. 2023. Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of GPT family LLMs’ Question Answering Performance. arxiv:2303.07992 [cs.CL]
[18]
Shuai Wang, Harrisen Scells, Bevan Koopman, and Guido Zuccon. 2023. Can ChatGPT Write a Good Boolean Query for Systematic Review Literature Search?. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (Taipei, Taiwan) (SIGIR ’23). Association for Computing Machinery, New York, NY, USA, 1426–1436. https://doi.org/10.1145/3539618.3591703
[19]
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In NeurIPS. http://papers.nips.cc/paper_files/paper/2022/hash/9d5609613524ecf4f15af0f7b31abca4-Abstract-Conference.html
[20]
Fangyi Yu, Lee Quartey, and Frank Schilder. 2022. Legal Prompting: Teaching a Language Model to Think Like a Lawyer. arxiv:2212.01326 [cs.CL]

Index Terms

  1. CricGPT: A GPT-aided Question-Answering system for Cricket
            Index terms have been assigned to the content through auto-classification.

            Recommendations

            Comments

            Information & Contributors

            Information

            Published In

            cover image ACM Other conferences
            FIRE '23: Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation
            December 2023
            170 pages
            Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

            Publisher

            Association for Computing Machinery

            New York, NY, United States

            Publication History

            Published: 12 February 2024

            Permissions

            Request permissions for this article.

            Check for updates

            Author Tags

            1. Cricket
            2. GPT
            3. Question-Answering
            4. SQLite

            Qualifiers

            • Research-article
            • Research
            • Refereed limited

            Conference

            FIRE 2023

            Acceptance Rates

            Overall Acceptance Rate 19 of 64 submissions, 30%

            Contributors

            Other Metrics

            Bibliometrics & Citations

            Bibliometrics

            Article Metrics

            • 0
              Total Citations
            • 65
              Total Downloads
            • Downloads (Last 12 months)65
            • Downloads (Last 6 weeks)6
            Reflects downloads up to 06 Jan 2025

            Other Metrics

            Citations

            View Options

            Login options

            View options

            PDF

            View or Download as a PDF file.

            PDF

            eReader

            View online with eReader.

            eReader

            HTML Format

            View this article in HTML Format.

            HTML Format

            Media

            Figures

            Other

            Tables

            Share

            Share

            Share this Publication link

            Share on social media