Search Results for author: Gene Louis Kim

Found 8 papers, 5 papers with code

Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes

1 code implementation26 Apr 2024 Mahammed Kamruzzaman, Gene Louis Kim

We also use human and machine personas to determine whether the effects of dual process theory in LLMs are based on modeling human cognition or inherent to the system.

BanMANI: A Dataset to Identify Manipulated Social Media News in Bangla

1 code implementation5 Nov 2023 Mahammed Kamruzzaman, Md. Minul Islam Shovon, Gene Louis Kim

Initial work has been done to address fake news detection and misrepresentation of news in the Bengali language.

Fake News Detection

Efficient Sentiment Analysis: A Resource-Aware Evaluation of Feature Extraction Techniques, Ensembling, and Deep Learning Models

1 code implementation3 Aug 2023 Mahammed Kamruzzaman, Gene Louis Kim

While reaching for NLP systems that maximize accuracy, other important metrics of system performance are often overlooked.

Sentiment Analysis

A Transition-based Parser for Unscoped Episodic Logical Forms

1 code implementation IWCS (ACL) 2021 Gene Louis Kim, Viet Duong, Xin Lu, Lenhart Schubert

"Episodic Logic:Unscoped Logical Form" (EL-ULF) is a semantic representation capturing predicate-argument structure as well as more challenging aspects of language within the Episodic Logic formalism.

Montague Grammar Induction

no code implementations15 Oct 2020 Gene Louis Kim, Aaron Steven White

We propose a computational modeling framework for inducing combinatory categorial grammars from arbitrary behavioral data.

Towards Natural Language Story Understanding with Rich Logical Schemas

no code implementations WS 2019 Gene Louis Kim, Lane Lawley, Lenhart Schubert

The idea of our approach to this problem is to provide a learning system with a {``}head start{''} consisting of a semantic parser, some basic ontological knowledge, and most importantly, a small set of very general schemas about the kinds of patterns of events (often purposive, causal, or socially conventional) that even a one- or two-year-old could reasonably be presumed to possess.

A Type-coherent, Expressive Representation as an Initial Step to Language Understanding

no code implementations WS 2019 Gene Louis Kim, Lenhart Schubert

A growing interest in tasks involving language understanding by the NLP community has led to the need for effective semantic parsing and inference.

Semantic Parsing

Cannot find the paper you are looking for? You can Submit a new open access paper.