Yuanyuan Lei
PhD student in Computer Science
Natural Language Processing Lab
Department of Computer Science and Engineering
Office: 330 Peterson Building, TAMU, College Station, TX 77843
Email: yuanyuan@tamu.edu
About Me
I am a fourth-year PhD student in the Department of Computer Science at Texas A&M University, advised by Prof. Ruihong Huang. Before starting PhD, I received my Master degree in Statistics (Data Science track) from Columbia University, and Bachelor degree in Mathematics and Applied Mathematics, as well as a double Bachelor degree in Computer Science from the University of Science and Technology of China (USTC).
My research direction is Natural Language Processing (NLP), with the focus on information extraction, misinformation, biased information, and subjective information. More specifically, I develop algorithms for (1) extracting salient and structured information from text (2) identifying misinformation and disinformation (3) detecting biased information such as societal bias or political bias (4) mining subjective information such as opinions or arguments. Additionally, I aim to address the truthfulness challenges of Large Language Models (LLMs), such as hallucinations, societal bias, misinformation, misuse within LLMs, to ensure factuality and truthfulness in the information extraction and reasoning process.
Research Interests
My research focus on information extraction, misinformation, biased information, and subjective information. My long-term research goal is to mitigate societal bias and misinformation within language modeling, promoting factual and truthful information extraction.
Information Extraction and Reasoning: extracting salient and structured information from news articles, social media text, and legal document
Misinformation Detection: identifying unwanted, polluted, and harmful information, such as conspiracy theory, propaganda, logical fallacy
Societal Bias Detection: detecting and mitigating biased information in human language, such as media bias, political bias, content framing bias
Opinions and Arguments Mining: analyzing and mining subjective information in text, such as opinions, arguments, morality, political stances
Truthfulness of LLMs: addressing the truthfulness challenges of LLMs, such as hallucinations, societal bias, misinformation, misuse within LLMs
Education
Texas A&M University, College Station TX, Sep 2020 - present
PhD in Computer Science, Natural Language Processing, Advisor: Prof. Ruihong Huang
Columbia University, New York NY, Sep 2017 - May 2019
Master in Statistics, Data Science
University of Science and Technology of China, Hefei, Sep 2013 - June 2017
Bachelor in Mathematics and Applied Mathematics
Double degree in Computer Science
Awards
Rising Stars in Data Science, University of Chicago and University of California San Diego, 2023
Future Research Leaders in Data Science and Artificial Intelligence, University of Michigan - Ann Arbor, 2023
Alumni Honor Roll, Columbia University, 2022
Travel Grant Award, Texas A&M University, 2024
Scholarship for Master students, Columbia University, Fall 2018
Scholarship for Master students, Columbia University, Spring 2018
The First Prize in National Mathematical Modeling Contest in China, Fall 2016
News
Mar 2024: One paper on sentence-level media bias detection was accepted by NAACL 2024
Mar 2024: One paper on event-level moral opinions in news articles was accepted by NAACL 2024, check our new dataset EMONA
Mar 2024: One paper on mitigating polarity bias in opinion summarization was accepted by NAACL 2024
Nov 2023: I was awarded with Rising Stars in Data Science by the University of Chicago and University of California San Diego
Oct 2023: One paper on conspiracy theories news detection was accepted by EMNLP 2023
Oct 2023: One paper on fine-grained propaganda analysis was accepted by EMNLP 2023
April 2023: I was awarded with Future Research Leaders in Data Science and Artificial Intelligence by the University of Michigan - Ann Arbor
Dec 2022: One paper on multi-modality emotion recognition was accepted by IEEE Transactions on Affective Computing
Oct 2022: I was awarded on Alumni Honor Roll by Columbia University
Oct 2022: One paper on sentence-level media bias in political news was accepted by EMNLP 2022
Oct 2022: One paper on few-shot (dis)agreement identification in social media was accepted by EMNLP 2022