Information Engineering Express

A Study on Emergency Response Management for System Failures using Project Management Knowledge

Atsushi Shimoda — 2026-01-12

Many companies prepare action procedures for emergency responses to system failures. Traditionally, these are based on procedures stipulated in international standards and best practices. However, they present only procedures and do not provide specific perspectives that organizations should consider in uncertain situations. Therefore, if an event that is not described in the action procedure manual occurs, there is a possibility that the site will be confused and rational judgment will not be possible. In this research, by utilizing project management knowledge, specific viewpoints that organizations should keep in mind in uncertain situations are presented. The effectiveness of the proposed method is shown by a case study of system failure.

Adaptable Expression Search Framework with Customizable Pattern Matching for Language Studies

Tatsuya Katsura — 2026-02-11

This study introduces a novel design for a pattern matching system capable of extracting select words or phrases from texts. In the process of learning a foreign language, searching for instances of usage or grammatical structures within texts is a common requirement. While numerous systems, particularly concordancers, have been proposed in prior research, many of them lacked flexibility and posed challenges when attempting to combine specific search patterns. To address this limitation, we developed a new phrase search system that allows users to craft their search patterns by merging basic search templates. This paper presents a system that leverages Prolog predicates as a fundamental data structure, utilizing SWI-Prolog for processing. The system is capable of performing searches that integrate regular expressions with other combined patterns. Our performance test demonstrates the system can process 10,000 sentences without errors. User evaluation employing system usability scale indicates that while the current usability of our system requires enhancement, the feedback gathered from these evaluations not only confirms the system’s robustness but also provides valuable insights for future improvements.

Offensive Language Detection on Social Media Using Three Language Models and Three Datasets

ZHENMING LI — 2026-01-12

There are more and more offensive posts on Social Media nowadays. Those posts are harmful and should be treated seriously. The most efficient way to detect offensive posts is to fine-tune a Large Language Model (LLM) on an offensive language dataset. In our research, we focus on maximizing the capacity of LLMs on offensive language detection tasks on Social Media. We select three LLMs with different attributes (DeepMoji, Bert, and HateBert) and three offensive language datasets (OLID, Curious Cat, and Ask FM). We mainly discuss achieving the best performance by configuring the LLMs and datasets. Experimental results show that simply fine-tuning an LLM with larger data can not always achieve the best performance. The combination of LLMs was effective, especially the combination of DeepMoji and HateBert.

Link Prediction Model for Automated Extraction of Hypernym and Hyponym Relations in Multiple Languages

Kohei Iwakuma — 2026-02-10

In natural language processing, hypernym–hyponym relations are the core of the body of knowledge and are useful for many downstream tasks, for example, technical trend analysis and patent examination. However, it is very costly to manually maintain these relations between terms. In this paper, we extract hypernym–hyponym relations from patent text data written in Japanese, English, and Chinese, and automatically construct a multilingual thesaurus. The proposed method consists of the following two steps. First, we use a generative adversarial network (GAN) to identify the terms in a hypernym–hyponym relation. Then, ConvE and GraphSAGE are combined to predict links on the graph of hypernym–hyponym relations constructed in the previous step, and to predict missing edges that should be in a hypernym–hyponym relation. In experiments conducted to demonstrate the effectiveness of the proposed method, it was found that our method outperformed previous methods in both the identification of hypernym–hyponym relations using GAN and link prediction using a combination of ConvE and GraphSAGE. We constructed a classifier that can discriminate between hypernym–hyponym relations using a trained Discriminator with GAN. In our experiments, we achieved a recall rate of 0.936 in English. And we propose a new method that can automatically complement missing hypernym–hyponym relations. The proposed model achieved a score of 97.3 on the H@10 evaluation index with respect to the prediction of Chinese hypernym–hyponym relations.