Papers by Vincent Nguyen

8 papers
MemeInterpret: Towards an All-in-One Dataset for Meme Understanding (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing research has not explored meme captioning's decomposition into subtasks or its connections to other CMU tasks.
Approach: a new meme corpus is built upon the Facebook Hateful Memes dataset . it contains meme captions, corresponding surface messages and relevant background knowledge .
Outcome: a new corpus of meme captions and surface messages unifies three major categories of CMU tasks for the first time.
Align then Summarize: Automatic Alignment Methods for Summarization Corpus Creation (2020.lrec-1)

Copied to clipboard

Challenge: Summarizing text is not a straightforward task.
Approach: They propose to use automated transcriptions to generate reports from automatic transcriptions as a dataset for neural summarization.
Outcome: The proposed model improves on publicmeetings corpus on a dataset of aligned public meetings.
Question Answering in Climate Adaptation for Agriculture: Model Development and Evaluation with Expert Feedback (2025.findings-acl)

Copied to clipboard

Challenge: Existing domain-specific question answering systems have generative capabilities, but their ability to answer climate adaptation questions remains unclear.
Approach: They propose an iterative framework that enables LLMs to dynamically aggregate information from heterogeneous sources, such as climate literature and structured tabular climate data from climate model projections and historical observations.
Outcome: The proposed framework enables LLMs to dynamically aggregate information from heterogeneous sources, such as text from climate literature and structured tabular climate data from climate model projections and historical observations.
MemeQA: Holistic Evaluation for Meme Understanding (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for meme understanding only concern narrow aspects of meme semantics.
Approach: They propose to use multiple-choice questions to evaluate meme comprehension . they use a dataset of over 9,000 multiple-question questions to assess meme comprehension.
Outcome: The proposed model outperforms existing models on meme comprehension . the model makes many errors on memes where proper understanding requires going beyond sentiment .
Computational Meme Understanding: A Survey (2024.emnlp-main)

Copied to clipboard

Challenge: Computational Meme Understanding (CMU) is a collection of tasks involving the automated comprehension of memes.
Approach: They propose a comprehensive taxonomy for memes along three dimensions – forms, functions, and topics and introduce three key tasks for Computational Meme Understanding, namely classification, interpretation, and explanation.
Outcome: The proposed model is based on a taxonomy of memes along three dimensions and is compared to existing models and datasets.
Question Answering in the Biomedical Domain (P19-2)

Copied to clipboard

Challenge: False positive questions require specific knowledge, common sense or a procedure due to ambiguity or the scope of the question.
Approach: False q is a question answering technique that uses natural language to find an answer . Falsity is based on a lexical gap and quality of answer spans .
Outcome: Using the proposed system, patients can self-diagnose without sacrificing quality of answer spans.
My Climate CoPilot: A Question Answering System for Climate Adaptation in Agriculture (2025.acl-demo)

Copied to clipboard

Challenge: Accurately answering climate science questions requires scientific literature and climate data.
Approach: They propose to provide climate adaptation experts with information on adaptation practices relevant to a specific commodity and location.
Outcome: My Climate CoPilot is a platform that assists users to mitigate and adapt to projected climate change by providing answers grounded in evidence.
Referring to Screen Texts with Voice Assistants (2023.acl-industry)

Copied to clipboard

Challenge: a new approach to voice assistants is limited in their ability to understand context of the user.
Approach: They propose a general purpose model that allows users to refer to phone numbers, addresses, email addresses, urls, and dates on their phone screens.
Outcome: The proposed model is lightweight, offering flexibility, better interpretability and efficient run time memory.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations