Classifying Text in Citation Context as Relevant or Irrelevant to the Cited Paper
Journal Title: International Journal of Innovations in Science and Technology - Year 2024, Vol 6, Issue 3
Abstract
Citation contexts, whether in the form of full citing sentences or text within a fixed window around the citation, have been widely used in various citation analysis applications. However, the absence of precise techniques to identify the exact span of text describing citations forces these applications to rely on extended texts as citation contexts. In this paper, we introduced new features combined with baseline features to accurately identify text that characterizes citations. Specifically, we utilized a Conditional Random Field (CRF) sequence classifier to categorize the surrounding text of citations as relevant or irrelevant. The integration of these features enhances the precision, recall, and F-measure scores for the Relevant (R) class. Although the average values of all measures are similar to those obtained with baseline features alone. Our approach significantly improves the extraction of relevant text.
Authors and Affiliations
Afsheen Khalid, Dilawar Khan, Shaukat Ali
Keywords
Related Articles
- EP ID EP760367
- DOI -
- Views 25
- Downloads 0
Analyzing the Impacts of Soapstone Dust on Respiratory System of Mine Workers Through Structural Equation Modelling Technique: A Case Study of Sherwan Soapstone Mines, Abbottabad, Pakistan
Dust produced in mining has a substantial impact on worker’s health resulting in severe respiratory diseases. Researchers mainly focused on the dust problems faced in surface mining whereas the dust produced in undergr...
An Advanced 2-Output DNN Model for Impulse Noise Mitigation in NOMA-Enabled Smart Energy Meters
he next-generation power grid enables information exchange between consumers and suppliers through advanced metering infrastructure. However, the performance of the smart meter degrades due to impulse noise present in...
Codebook-Based Feature Engineering for Human Activity Recognition Using Multimodal Sensory Data
Recently, Human Activity Recognition (HAR) using sensory data from various devices has become increasingly vital in fields like healthcare, elderly care, and smart home systems. However, many existing HAR systems face...
AI-Based Predictive Tool-Life Computation in Manufacturing Industry
For maximum productivity and optimal utilization of tools, predictive maintenance serves as a standard operation procedure in the manufacturing industry. However, unnecessary or delayed maintenance both causes increas...
Applying Agile Principles and Methods in Industries Outside IT Landscape: A Systematic Literature Review
Agile methods have become increasingly popular in various industries because of many benefits over the common waterfall like methodologies. Whereas, there are still many issues and uncertainties faced by co-workers, or...