Automatic Title Generation in Scientific Articles for Authorship Assistance: A Summarization Approach
Journal Title: Journal of ICT Research and Applications - Year 2017, Vol 11, Issue 3
Abstract
This paper presents a study on automatic title generation for scientific articles considering sentence information types known as rhetorical categories. A title can be seen as a high-compression summary of a document. A rhetorical category is an information type conveyed by the author of a text for each textual unit, for example: background, method, or result of the research. The experiment in this study focused on extracting the research purpose and research method information for inclusion in a computer-generated title. Sentences are classified into rhetorical categories, after which these sentences are filtered using three methods. Three title candidates whose contents reflect the filtered sentences are then generated using a template-based or an adaptive K-nearest neighbor approach. The experiment was conducted using two different dataset domains: computational linguistics and chemistry. Our study obtained a 0.109-0.255 F1-measure score on average for computer-generated titles compared to original titles. In a human evaluation the automatically generated titles were deemed ‘relatively acceptable’ in the computational linguistics domain and ‘not acceptable’ in the chemistry domain. It can be concluded that rhetorical categories have unexplored potential to improve the performance of summarization tasks in general.
Authors and Affiliations
Masayu Leylia Khodra
Keywords
Related Articles
- EP ID EP326323
- DOI 10.5614/itbj.ict.res.appl.2017.11.3.3
- Views 127
- Downloads 0
A Comprehensive Performance Analysis of IEEE 802.11p based MAC for Vehicular Communications Under Non-saturated Conditions
Reliable and efficient data broadcasting is essential in vehicular networks to provide safety-critical and commercial service messages on the road. There is still no comprehensive analysis of IEEE 802.11p based MAC that...
An Energy Aware Unequal Clustering Algorithm using Fuzzy Logic for Wireless Sensor Networks
In wireless sensor networks, clustering provides an effective way of organising the sensor nodes to achieve load balancing and increasing the lifetime of the network. Unequal clustering is an extension of common clusteri...
Design of Triple-Band Bandpass Filter Using Cascade Tri-Section Stepped Impedance Resonators
In this research, a triple-band bandpass filter (BPF) using a cascade tri section step impedance resonator (TSSIR), which can be operated at 900 MHz, 1,800 MHz, and 2,600 MHz simultaneously, was designed, fabricated and...
Mining High Utility Itemsets with Regular Occurrence
High utility itemset mining (HUIM) plays an important role in the data mining community and in a wide range of applications. For example, in retail business it is used for finding sets of sold products that give high pro...
Efficient CFO Compensation Method in Uplink OFDMA for Mobile WiMax
Mobile WiMax uses Orthogonal Frequency Division Multiple Access (OFDMA) in uplink where synchronization is a complex task as each user presents a different carrier frequency offset (CFO). In the Data Aided Phase Incremen...