Khoi P. N. Nguyen, Terrence Li, Derek Lou Zhou, Gabriel Xiong, Pranav Balu, Nandhan Alahari, Alan Huang, Tanush Chauhan, Harshavardhan Bala, Emre Guzelordu, Affan Kashfi, Aaron Xu, Suyesh Shrestha, Megan Vu, Jerry Wang, Vincent Ng. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Computational Meme Understanding, which concerns the automated comprehension of memes, has garnered interest over the last four years and is facing both substantial opportunities and challenges.We survey this emerging area of research by first introducing a comprehensive taxonomy for memes along three dimensions -forms, functions, and topics.Next, we present three key tasks in Computational Meme Understanding, namely, classification, interpretation, and explanation, and conduct a comprehensive review of existing datasets and models, discussing their limitations.Finally, we highlight the key challenges and recommend avenues for future work. 1

Monte-Carlo Tree Search (MCTS) is a search paradigm that first found prominence with its success in the domain of computer Go. Early theoretical work established the soundness and convergence bounds for Upper Confidence bounds applied to Trees (UCT), the most popular instantiation of MCTS; however, there remain notable gaps in our understanding of how UCT behaves in practice. In this work, we address one such gap by considering the question of whether UCT can exhibit lookahead pathology in adversarial settings --- a paradoxical phenomenon first observed in Minimax search where greater search effort leads to worse decision-making. We introduce a novel family of synthetic games that offer rich modeling possibilities while remaining amenable to mathematical analysis. Our theoretical and experimental results suggest that UCT is indeed susceptible to pathological behavior in a range of games drawn from this family.

Jeongsik Park, Khoi P. N. Nguyen, Terrence Li, Suyesh Shrestha, Megan Kim Vu, Jerry Yining Wang, Vincent Ng. Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2024.

Current Automatic Speech Recognition (ASR) systems, like Google Assistant, Apple's Siri, or Amazon's Alexa, continue to only support a small number of languages (English, Mandarin, Arabic, etc.), primarily those spoken in developed nations with abundant resources. While these languages have been able to reap the benefits of having such technology at their disposal, places like Ethiopia, and Vietnam are still far behind. This work represents a global collaboration to create a framework for customizing ASR systems for low resource languages (LRLs), or languages with limited human and financial resources. This paper describes the methodology for using an existing application (Kaldi) to implement an ASR system for two such languages, Amharic and Vietnamese, with the least amount of annotated speech. The languages are chosen to leverage available student expertise and create cross-cultural connections. The objective of the research is to create a procedure by which, given enough training records and annotation, any language can be added.