Automatic Subject-Object-Verb relation extraction

• Published in: 2012 International Symposium on Innovations in Intelligent Systems and Applications pp. 1 - 4
• Main Authors: Temizer, M., Diri, B.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-07-2012
• Subjects: Algorithm design and analysis; Artificial intelligence; Computers; Data mining; dependency analysis; Feature extraction; Java; subject-object-verb relation extraction; Support vector machines
• ISBN: 1467314463; 9781467314466
• DOI: 10.1109/INISTA.2012.6246943

Artificial Intelligence is one of the key concepts of today's technology. As it is known, AI's aim is to developing technology that can learn by itself. Also, Natural Language Processing is another key concept as a significant contributor to AI in the field of natural languages. Considering the AI and NLP together brings us to teach computers to learn on their own about the natural languages and human derived words with their relationship. This paper aims to transfer a considerable amount of information to computers' world by presenting a way to extract Subject-Object-Verb relation extraction from Turkish documents automatically. Through three main steps the goal is achieved: (1) morphological analysis, (2) dependency analysis, (3) triplet extraction. As a result, an independent triplets graph can be generated for each text input, and verbs-nouns relation can be viewed.