Text-Based Causal Inference on Irony and Sarcasm Detection

2022
Çekinel, Recep Fırat
Karagoz, Pinar
Show full item record
158
views
0
downloads
The state-of-the-art NLP models’ success advanced significantly as their complexity increased in recent years. However, these models tend to consider the statistical correlation between features which may lead to bias. Therefore, to build robust systems, causality should be considered while estimating the given task’s data generating process. In this study, we explore text-based causal inference on the irony and sarcasm detection problem. Additionally, we model the latent confounders by performing unsupervised data analysis, particularly clustering and topic modeling. The obtained results also provide insight for the causal explainability in irony detection.
Irony detection , Causal inference , Clustering , Topic modeling
https://hdl.handle.net/11511/99767
24th International Conference on Big Data Analytics and Knowledge Discovery, 22-24 August 2022
Department of Computer Engineering, Conference / Seminar

Suggestions

Human crowd simulation as an evaluation tool for generative temporary site organization
Kruşa, Müge; Sorguç, Arzu; Computational Design and Fabrication Technologies in Department of Architecture (2013)
The advents in computational technologies enabled designers to produce data derived generic models in order to deal with complex design problems. One of the significant data regarding context of a project is the user experiencing the building and the site. Although crowd simulation algorithms have been used as accurate models in movie and game industry, when the computational cost concerned for complex architectural problems, these tools are not suggested to be used within/throughout in design process. With...
Software reliability assessment
Kaya, Deniz; Bilgen, Semih; Department of Electrical and Electronics Engineering (2005)
In spite of the fact that software reliability studies have attracted great deal of attention from different disciplines in 1970s, applications of the subject have rarely been involved in the software industry. With the rise of technological advances especially in the military electronics field, reliability of software systems gained importance. In this study, a company in the defense industries is inspected for their abilities and needs regarding software reliability, and an improvement proposal with metri...
Closed-form sample probing for learning generative models in Zero-shot Learning
Çetin, Samet; Baran, Orhun Buğra; Cinbiş, Ramazan Gökberk (2022-04-25)
Generative model based approaches have led to significant advances in zero-shot learning (ZSL) over the past few years. These approaches typically aim to learn a conditional generator that synthesizes training samples of classes conditioned on class definitions. The final zero-shot learning model is then obtained by training a supervised classification model over the real and/or synthesized training samples of seen and unseen classes, combined. Therefore, naturally, the generative model needs to produce not...
Performance comparison of pattern discovery methods on web log data
Bayir, Murat Ali; Toroslu, İsmail Hakkı; Coşar, Ahmet (2006-03-11)
One of the popular trends in computer science has been development of intelligent web-based systems. Demand for such systems forces designers to make use of knowledge discovery techniques on web server logs. Web usage mining has become a major area of knowledge discovery on World Wide Web. Frequent pattern discovery is one of the main issues in web usage mining. These frequent patterns constitute the basic information source for intelligent web-based systems. In this paper; frequent pattern mining algorithm...
Learning with infinitely many kernels via semi-infinite programming
Oezoeguer-Akyuez, Suereyya; Weber, Gerhard Wilhelm (2008-05-23)
In recent years, learning methods are desirable because of their reliability and efficiency in real-world problems. We propose a novel method to find infinitely many kernel combinations for learning problems with the help of infinite and semi-infinite optimization regarding all elements in kernel space. This will provide to study variations of combinations of kernels when considering heterogeneous data in real-world applications. Looking at all infinitesimally fine convex combinations of the kernels from th...
Citation Formats
R. F. Çekinel and P. Karagoz, “Text-Based Causal Inference on Irony and Sarcasm Detection,” Vienna, Austria, 2022, p. 31, Accessed: 00, 2022. [Online]. Available: https://hdl.handle.net/11511/99767.
METU IIS - Integrated Information Service open@metu.edu.tr