Smart Contracts Implementation Based on Bidirectional Encoder Representations from Transformers
Author | Aejas, Bajeela |
Author | Bouras, Abdelaziz |
Author | Belhi, Abdelhak |
Author | Gasmi, Houssem |
Available date | 2023-04-09T08:34:46Z |
Publication Date | 2022 |
Publication Name | IFIP Advances in Information and Communication Technology |
Resource | Scopus |
Abstract | The distribution and immutability properties of blockchains made it possible to use them in various fields, such as Supply Chain, finance and health. The automation of the creation and execution of transactions in a blockchain in a decentralized and transparent manner is realized through Smart Contracts programming codes. This paper presents the implementation of Smart Contracts in specific manufacturing Supply Chains and discusses their life cycle and impact on the Supply Chain management. The presented application deals with the possibility of transforming natural language contracts of a given Supply Chain to automated Smart Contracts that makes the Supply Chain management faster and safer. A first solution is proposed based on Bidirectional Encoder Representations from Transformers (BERT) model and limited to the implementation of Smart Contracts of the Supply Chain legal contracts. Also described here is the ways of extracting contract elements from legal contracts by applying the BERT Deep Learning method on annotated contract dataset of a corpus of 13000 annotations over 510 contracts. 2022, IFIP International Federation for Information Processing. |
Sponsor | Acknowledgement. This research is part of the National Priority Research Program (NPRP) research project: NPRP11S-1227-170135, funded by the Qatar National Research Fund (QNRF). |
Language | en |
Publisher | Springer Science and Business Media Deutschland GmbH |
Subject | BERT Blockchain NLP Smart Contract Supply chain |
Type | Conference Paper |
Pagination | 293-304 |
Volume Number | 639 IFIP |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |
This item appears in the following Collection(s)
-
Computer Science & Engineering [2284 items ]