EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Chemical-Attribute Extraction via Inverse Reinforcement Learning with Sub-Reward Matching for Question Answering

Taiyu Zhang, Yuqing Ni, Xicheng Yang, Congyuan Xu, Xiaochen Liu

Applied Sciences · 03.06.2026 · 16 (11) · 5598

DOI: 10.3390/app16115598 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 03.06.2026. Verfasst von Taiyu Zhang und 4 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Basic Research Program of Jiangsu.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Globalization and international trade have increased the importance of customs authorities in ensuring national security. However, regulatory differences regarding substances such as cannabis derivatives, the emergence of new psychoactive substances (NPSs), and the limitations of detection technology challenge customs in identifying suspicious cross-border goods. Traditional attribute extraction methods struggle with professional terminology and cross-sentence reasoning, making it difficult to regulate unknown or emerging substances. To address this, we propose a generative question answering (QA) framework based on inverse reinforcement learning (IRL) that converts attribute extraction into natural language QA tasks. Our approach, CAESAR (Chemical-Attribute Extraction with Sub-rewArd Reinforcement), uses a customs database to match known profiles and cross-references extracted attributes with benchmarks to enhance detection. It integrates the BioBART model with multi-objective reward optimization, using QA templates to capture implicit attributes. IRL automates the learning of reward weights from expert annotations. Experiments show that CAESAR achieves a competitive F1 score of 77.82 on explicit attributes and obtains the highest BLEU score and the lowest perplexity among the compared generative methods. For implicit attributes, ROUGE-L and BLEU scores are 43.08 and 44.46, respectively, with a perplexity of 11.3. These results are obtained in an open-ended generative QA setting rather than a closed-set classification setting, indicating that the proposed framework can provide practically useful attribute-level evidence for customs-oriented risk pre-screening and expert-assisted prioritization. This study offers an efficient solution for mining implicit knowledge in chemical texts and provides insights into multi-objective generative tasks.

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • Basic Research Program of Jiangsu
  • State Key Laboratory of Industrial Control Technology
  • 111 Project
  • Jiaxing City Science and Technology Project

Zitieren

APA

Zhang, T., Ni, Y., Yang, X., Xu, C., & Liu, X. (2026). Chemical-Attribute Extraction via Inverse Reinforcement Learning with Sub-Reward Matching for Question Answering. Applied Sciences, 16(11), 5598. https://doi.org/10.3390/app16115598

Vancouver

Zhang T, Ni Y, Yang X, Xu C, Liu X. Chemical-Attribute Extraction via Inverse Reinforcement Learning with Sub-Reward Matching for Question Answering. Applied Sciences. 2026;16(11):5598. doi:10.3390/app16115598

BibTeX
@article{Zhang2026,
  author = {Zhang, Taiyu and Ni, Yuqing and Yang, Xicheng and Xu, Congyuan and Liu, Xiaochen},
  title = {Chemical-Attribute Extraction via Inverse Reinforcement Learning with Sub-Reward Matching for Question Answering},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {11},
  pages = {5598},
  doi = {10.3390/app16115598}
}
Kostenlos starten →