Bài báo: “Domain Adaptation in Nested Named Entity Recognition From Scientific Articles in Agriculture”
Sinh viên thực hiện:
Phan Doãn Thái Bình – 20520043 – KHTN2020 – Tác giả chính
Lê Phước Vĩnh Linh – 20521531 – KHTN2020 - Tác giả chính
Giảng viên hướng dẫn:
TS. Ngô Quốc Hưng
TS. Lương Ngọc Hoàng
Tóm tắt bài báo:
In the realm of digital agriculture, the ability to make timely, profitable, and actionable decisions depends on agronomists using agricultural data and related cultivated data, including text sources such as news articles, farm notes, and agricultural scientific reports. Named entity recognition (NER) and agricultural entity recognition (AGER) facilitate semantic understanding, enabling precise identification, categorization of farming components, and knowledge discovery. However, current approaches to agricultural entity recognition encounter limitations due to limited resources. Moreover, the necessity to identify nested named entities emerges from the complexities inherent in the agricultural domain. Relevant information often traverses multiple interconnected elements rather than residing as isolated entities. For instance, comprehending a target farming practice might necessitate pinpointing the crop, the associated nutrients, or diseases—each constituting a nested entity within a broader context. Consequently, agricultural entity recognition from unstructured text gives high importance to information retrieval and knowledge construction within this domain. This study constructs the SAGRI dataset, incorporating a novel tagset for AGER that encompasses prevalent agricultural and scientific concepts, methodically established through annotation. This tagset enables the extraction of domain-independent concepts from scien- tific article abstracts. This study also introduces a cutting-edge deep learning baseline with an advanced Triaffine attention mechanism for robust entity extraction. Additionally, it presents a pioneering few-shot learning strategy that optimizes cross-domain categoriza- tion, mainly when dealing with scarce training data. Notably, this strategy achieves high F1 scores compared to the baseline, underscoring its potential to curtail required training data considerably.
"Chúng em xin gửi lời cảm ơn đến Thầy Ngô Quốc Hưng – Khoa Khoa học Máy tính hiện đang làm việc tại University College Dublin và thầy Lương Ngọc Hoàng – Khoa Khoa học Máy tính đã tận tình hướng dẫn và chỉ ra những mặt hạn chế của chúng em trong quá trình nghiên cứu và công bố bài báo khoa học quốc tế này"
SOICT 2023 is an international symposium covering significant research areas that include AI
Foundations and Big Data, Network Communication and Security, Image and Natural Language Processing, Software Engineering and Digital Technology, Blockchain, and Operations Research trends. Following the past successful symposium SOICT 2022, which received submissions from 14 countries, the 12th International Symposium on Information and Communication Technology (SOICT 2023) will be held in Ho Chi Minh City, Vietnam on 7-8 December 2023. The symposium aims to provide an academic forum for researchers and graduate students to share their latest research findings and identify future computer science challenges. The symposium will include tutorials and keynotes given by world-class speakers. SOICT 2023 proceedings will be published in the International Conference Proceedings Series by ACM as an ICPS volume in the ACM Digital Library (ISBN: 979-8-4007-0891-6), which will be archived in the ACM Digital Library. SOICT 2023 will be indexed by DBLP, Ei Compendex, Scopus and Clarivate Analytics Web of Science (ISI Web of Science).
This year, the SOICT 2023 is organized by School of Information and Communication Technology
– Hanoi University of Science and Technology, Hochiminh University of Science – Vietnam
National University, Laboratory Informatics, Modelling and Optimisation System (LIMOS), The French National Centre for Scientific Research (CNRS) and Vietnam Institute for Advanced Study in Mathematics. SOICT 2023 is organized in conjunction with The Third Vietnam Operations Research Network Meeting (VORN 2023).
Thông tin chi tiết: https://www.facebook.com/UIT.Fanpage/posts/pfbid09pMH91yccUKC5LR8w72kpTetfZ7iHgKMduMjSsbH2XMt34nLtrX5uawqjHnZ4s7Vl
Hải Băng - Cộng tác viên Truyền thông trường Đại học Công nghệ Thông tin
