The aim of this research work was to investigate the applicability of smart contracts in the context of automating the process of managing meeting minutes. To this end, smartMinutes, a proof-of-concept prototype of automating meeting minutes was designed, implemented, and validated with test cases. The smartMinutes framework improves current practices related to the meeting minutes process by providing automation in areas where possible, and doing so in a transparent, flexible, reliable, and tamper-proof manner. The last feature is of paramount importance due to the fact that meeting minutes offer legal protection, as they are considered official records of the actions taken by an organisation. Additionally, smartMinutes supports meeting agendas with non-voting items as well as voting items, offering a pool of three voting schemes, executing under three different configurations. A particular configuration, the hidden mode, provides for secrecy while at the same time guaranteeing transparency.

/pdf/smartminutes-a-blockchain-based-framework-for-automated-10qzg2bw.pdf

SmartMinutes - A Blockchain-Based Framework for Automated, Reliable, and Transparent Meeting Minutes Management

The information has grown at a rapid pace in the recent past. The overwhelming amount of data available may be a lot for the consumers to absorb and retain. Various methods have been developed over the years to tackle the issue of over-burdening consumers. The research has led to the topic of text summarization. Text summarization is the method of producing a concise version of text by retaining the most relevant information. The paper focuses on the extractive summarization of single documents. Majority of the previous studies revolve around unsupervised methods while the supervised methods mainly comprise of models trained on the DUC datasets. The proposed work in this paper provides a comparison of supervised and unsupervised methods. The base of the supervised model is on a convolutional neural network (CNN) whereas the base of the unsupervised method is on K-Means clustering. The proposed model is used to evaluate the BBC News Summary dataset. The performance is a comparison with the previously proposed systems.

Extractive Summarization of Text Using Supervised and Unsupervised Techniques

Meeting minutes contain many important decisions and fact from a meeting. Since meeting minutes are unstructured document, summarization should be conducted in order to easily get the main information. Some works in this research area have been done for meeting minutes in English, but have not conducted yet in Indonesian. Therefore, this paper aims to develop extractive summarization system on Indonesian parliamentary meeting minutes using rule-based information extraction with regular expression. Summary structure is defined based on summaries from the House of Representatives of the Republic of Indonesia. Regular expressions are designed to recognize patterns in meeting minutes and then to fill 24 slot values in summary templates. Our summarizer consists of four main processes i.e.: preprocessing, information extraction, postprocess, and template filling. Our experimental results evaluated by the ROUGE summarization metrics achieves performance in terms of ROUGE-2 F-measure of 0.718.

Mochamad Try Yulyanto

Papers

Automatic extractive summarization on Indonesian parliamentary meeting minutes