Abstract
This paper introduces a novel task of detecting turning points in the engineering process of large-scale projects, wherein the turning points signify significant transitions occurring between phases. Given the complexities involving diverse critical events and limited comprehension in individual news reports, we approach the problem by treating the sequence of related news streams as a window with multiple instances. To capture the evolution of changes effectively, we adopt a deep Multiple Instance Learning (MIL) framework and employ the multiple instance ranking loss to discern the transition patterns exhibited in the turning point window. Extensive experiments consistently demonstrate the effectiveness of our proposed approach on the constructed dataset compared to baseline methods. We deployed the proposed mode and provided a demonstration video to illustrate its functionality. The code and dataset are available on GitHub.- Anthology ID:
- 2023.emnlp-demo.16
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Yansong Feng, Els Lefever
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 177–185
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-demo.16
- DOI:
- 10.18653/v1/2023.emnlp-demo.16
- Cite (ACL):
- Qi Wu, WenHan Chao, Xian Zhou, and Zhunchen Luo. 2023. TP-Detector: Detecting Turning Points in the Engineering Process of Large-scale Projects. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 177–185, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- TP-Detector: Detecting Turning Points in the Engineering Process of Large-scale Projects (Wu et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2023.emnlp-demo.16.pdf