Research on Comfortable Web Utilization Support Using Natural Language Processing Technology

2023 Fiscal Year Final Research Report

• Project/Area Number: 19K12241
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 62020:Web informatics and service informatics-related
• Research Institution: Ryukoku University
• Principal Investigator: Ma Qing 龍谷大学, 先端理工学部, 教授 (30358882)
• Co-Investigator(Kenkyū-buntansha): 南條 浩輝 滋賀大学, データサイエンス学系, 教授 (50388162)
• Project Period (FY): 2019-04-01 – 2024-03-31
• Keywords: Web検索支援 / 日本語学習支援 / プログラミング学習支援 / 情報獲得 / 用語抽出 / 系列ラベリング / 深層学習 / 対照学習

Outline of Final Research Achievements

This research aims to construct a foundation for natural language processing technology to support comfortable Web usage targeting specific groups such as foreigners with insufficient language processing abilities, the elderly, and children. The study focuses on various issues, including Web search assistance through the extraction of search terms from unstructured documents, support for Japanese learners through the detection of grammatical errors and the classification and transformation of incorrect and correct sentences, support for programming learners based on the extraction of key points from programming task statements, utilizing knowledge communities, and supporting information acquisition from social media networks (SNS).
In these studies, approaches based on machine learning and deep learning were adopted, and their effectiveness was confirmed through validation using large-scale real data, leading to the successful development of various methods and systems.

Free Research Field

知能情報学

Academic Significance and Societal Importance of the Research Achievements

本研究成果は、言語処理能力が不十分な外国人、高齢者、子供など特定の層の人々に快適なWeb利用を支援する自然言語処理技術の基盤形成に大きく貢献している。複数の科研基盤などで得られた研究成果・技術を融合している点、すなわち、情報検索・情報抽出・意味処理などの単独の応用ではなく、それらの諸自然言語処理技術と、Web関連技術・統計技術・機械学習などを融合的に利用している点が本研究成果の学術的な特色である。また、本研究成果は、他の関連研究の基本要素技術の発展に寄与できる可能性が高く、関連して得られる知見は、人間の言語獲得・理解のメカニズム解明の重要なヒントとなり得ると考える。