Towards idea mining: Problem-solution phrases 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 : 18th International Conference on Advanced Data Mining and Applications
• Start Date: Nov 28, 2022
• End Date: Nov 30, 2022
• Acceptance Date: Sep 15, 2022
• Publication Date: Nov 24, 2022
• Deposit Date: Oct 6, 2022
• Publicly Available Date: Nov 25, 2024
• Publisher: Springer
• Volume: 13726
• Pages: 3–14
• Series Title: Lecture Notes in Computer Science book series (LNAI, Volume 13726)
• Book Title: ADMA 2022: Advanced Data Mining and Applications
• Chapter Number: 1
• ISBN: 978-3-031-22136-1
• 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/10021857
• 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/1244; ; https://www.springer.com/series/558