Towards idea mining: Problem-solution phrase extraction from text

Liu, Haixia; Brailsford, Tim; Goulding, James; Maul, Tomas; Tan, Tao; Chaudhuri, Debanjan

Abstract

This paper investigates the feasibility of problem-solution phrases extraction from scientific publications using neural network approaches. Bidirectional Long Short-Term Memory with Conditional Random Fields (Bi-LSTM-CRFs) and Bidirectional Encoder Representations from Transformers (BERT) were evaluated on two datasets, one of which was created by University of Cambridge Computer Laboratory containing 1000 positive examples of problems and solutions (UCCL1000) with the corresponding phrases annotated. The F1-scores computed on the UCCL1000 dataset indicate that BERT is an effective approach to extract solution phrases (with an F1-score of 97%) and problem phrases (with an F1-score of 83%). To test the model’s robustness on a different corpus with a different annotation scheme, a dataset consisting of 488 problem-solution samples from the Conference on Neural Information Processing Systems (NIPS488) was collected and annotated by human readers. Both Bi-LSTM-CRFs and BERT performances were dramatically lower for NIPS488 in comparison with UCCL1000.

• Presentation Conference Type: Conference Paper (published)
• Conference Name: ADMA 2022: International Conference on Advanced Data Mining and Applications
• Start Date: Nov 30, 2022
• End Date: Dec 2, 2022
• Acceptance Date: Aug 19, 2022
• Online Publication Date: Nov 24, 2022
• Publication Date: Jan 16, 2023
• Deposit Date: Jan 16, 2023
• Publicly Available Date: Nov 25, 2024
• Publisher: Springer Verlag
• Volume: 13726 LNAI
• Pages: 3-14
• Series Title: Lecture Notes in Computer Science book series (LNAI,volume 13726)
• Series ISSN: 0302-9743; 1611-3349
• Book Title: Advanced Data Mining and Applications 18th International Conference, ADMA 2022, Brisbane, QLD, Australia, November 28–30, 2022, Proceedings, Part II
• ISBN: 9783031221361
• DOI: https://doi.org/10.1007/978-3-031-22137-8_1
• Keywords: Text mining; Problem-solution extraction; NLP
• Public URL: https://uwe-repository.worktribe.com/output/10339175
• Publisher URL: https://link.springer.com/chapter/10.1007/978-3-031-22137-8_1
• Related Public URLs: https://link.springer.com/book/10.1007/978-3-031-22137-8; ; https://www.springer.com/series/558
• Additional Information: First Online: 24 November 2022; Conference Acronym: ADMA; Conference Name: International Conference on Advanced Data Mining and Applications; Conference City: Brisbane, QLD; Conference Country: Australia; Conference Year: 2022; Conference Start Date: 30 November 2022; Conference End Date: 2 December 2022; Conference Number: 18; Conference ID: adma2022; Conference URL: https://adma2022.uqcloud.net/index.html; Type: Single-blind; Conference Management System: CMT3; Number of Submissions Sent for Review: 198; Number of Full Papers Accepted: 72; Number of Short Papers Accepted: 0; Acceptance Rate of Full Papers: 36% - The value is computed by the equation "Number of Full Papers Accepted / Number of Submissions Sent for Review * 100" and then rounded to a whole number.; Average Number of Reviews per Paper: 5; Average Number of Papers per Reviewer: 3; External Reviewers Involved: No