This is a Demo Server. Data inside this system is only for test purpose.
 

Automatic question generation using natural language processing techniques

No Thumbnail Available

Date

2018-07

Journal Title

Journal ISSN

Volume Title

Publisher

Izmir Institute of Technology

Open Access Color

Green Open Access

Yes

OpenAIRE Downloads

OpenAIRE Views

Publicly Funded

No

Research Projects

Organizational Units

Journal Issue

Abstract

This thesis proposes a new rule based approach to automatic question generation. The proposed approach focuses on analysis of both syntactic and semantic structure of a sentence. The design and implementation of the proposed approach are also explained in detail. Although the primary objective of the designed system is question generation from sentences, automatic evaluation results shows that, it also achieves great performance on reading comprehension datasets, which focus on question generation from paragraphs. With respect to human evaluations, the designed system significantly outperforms all other systems and generated the most natural (human-like) questions.
Bu tez otomatik soru üretimi için yeni bir kural tabanlı yaklaşım önermektedir. Önerilen yaklaşım, bir cümlenin hem sözdizimsel hem de semantik yapısının analizine odaklanmaktadır. Ayrıca, önerilen yaklaşımın tasarımı ve uygulanması ayrıntılı olarak açıklanmıştır. Tasarlanan sistemin temel amacı cümlelerden soru üretmek olmasına rağmen, otomatik değerlendirme sonuları, sistemin anlama becerisi gerektiren paragraflar üzerinde de büyük bir performans sergilediğini gösterdi. İnsan değerlendirmelerine gelince, tasarlanan sistem diğer tüm sistemlerden önemli ölçüde daha iyi bir performans gösterdi ve en doğal (insan benzeri) soruları üretti.

Description

Thesis (Master)--Izmir Institute of Technology, Computer Engineering, Izmir, 2018
Includes bibliographical references (leaves: 37-41)
Text in English; Abstract: Turkish and English

Keywords

Question generation, Named Entity Recognition, Question answering, Automatic evaluation, Semantic role labeling, Computer Engineering and Computer Science and Control, Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol

Turkish CoHE Thesis Center URL

Fields of Science

Citation

WoS Q

Scopus Q

Source

Volume

Issue

Start Page

End Page

Collections