I am a PhD student in Computational Linguistics at Stony Brook University (since Fall 2022) and a member of the Institute for Advanced Computational Science (IACS). My research interests are in Natural Language Processing, Computational Linguistics, Computational Social Science, Machine Learning, and Formal Language Theory. My advisors are Dr. Owen Rambow and Dr. Jeffrey Heinz.Over years, I have worked on projects that study actual language use at large scale as well as how and how well neural networks learn and generalize (explainable AI). I am currently working on detecting influence campaigns from social media and understanding the abilities of Large Language Models (LLMs) to capture people's cognitive states in conversation.
I am also a trainee (since May 2023) for the NSF BIAS-NRT project led by Dr. Susan Brennan that aims to detect and address bias in data, humans, and institutions.
I am looking for a ML/NLP/Data Science internship (research or engineering) for 2024 summer.
I was born and raised in Fuqing, a small southeastern town of China. Prior to coming to Stony Brook, I completed a bachelor's degree in Chinese Language and Literature from Hunan University, and a master's degree in Applied linguistics from University of Saskatchewan.
I am a proud self-taught and self-motivated programmer. I started learning programming in 2020, and have since managed to make programming relevant to and then part of my daily life. Looking back, I am glad to find my experiences with NLP align well with the three major phases of the field featured as: rule-based (symbolic) methods, statistical machine learning, and deep learning. If you take a look at my papers since my master's thesis, such a trajectory should be sensible.
Here is my Curriculum Vitae.
Modelling Influence Campaigns in Documents (DARPA INCAS)
Zhengxiang Wang, supervised by Owen Rambow
About: The goal of this ongoing project is to detect influence campagins from documents. For this purpose, I created and deployed an end-to-end generative LLM pipeline and a general clustering framework (to be released) to extract beliefs and cluster on belief targets using SBERT and various clustering algorithms (e.g., UMAP + HDBSCAN). Based on these, I built a classifer that detects cluster-level influence campagins with over 82% test set F1 score (mixed domains) and improving.
Learning Transductions and Alignments with RNN Seq2seq models
Zhengxiang Wang, ICGI 2023
About: I designed and conducted comprehensive experiments to examine the capabilities of Recurrent-Neural-Network sequence to sequence (RNN seq2seq) models in learning four transduction tasks of varying complexity and that can be described as learning alignments. The generalization abilities, the role of attention, the effect of RNN variants, and task complexity are studied.
Developing literature review writing skills through an online writing tutorial series: Corpus-based evidence
Zhi Li, Makarova Veronika, Zhengxiang Wang, Frontiers in Communication, 2023
About: By analyzing a cluster of linguistic features elicited from 29 L2 graduate students' writing samples over 3 months, we tried to track evidence of development in genre awareness and mastery of academic writing, which indicated the non-linear and dynamic nature of L2 learning.
Random Text Perturbations Work, but not Always
Zhengxiang Wang, AACL-IJCNLP 2022 Workshop Eval4NLP
About: As a continuation to my research on text augmentation, I examined the effectiveness and generalizability of random text perturbations in the context of text pair classification tasks for both Chinese and English, which revealed a complex nature of text augmentation and its evaluation.
Thirty-Two Years of IEEE VIS: Authors, Fields of Study and Citations
Hongtao Hao, Yumian Cui, Zhengxiang Wang, Yea-Seul Kim, IEEE Transactions on Visualization and Computer Graphics, 2022
About: IEEE VIS is the top-tier conference in the field of Visualization. The study marks the first effort to comprehensively examine and visualize the authors and fields of study of 3,240 VIS publications in the past 32 years. Temporal trends are also extensively investigated.
Linguistic Knowledge in Data Augmentation for Natural Language Processing: An Example on Chinese Question Matching
Zhengxiang Wang, ICNLSP 2022
About: As an effort to data-centric NLP, I explored the role of probabilistic linguistic knowledge in data augmentation for a binary Chinese question matching classification task. You can check out the source code, data, experimental results, and recent updates in this repository .
A macroscopic re-examination of language and gender: a corpus-based case study in the university classroom setting
MA thesis, University of Saskatchewan [Slides], 2021
About: The thesis compared the use of 87 syntactic and lexical linguistic features by university male and female instructors across four academic disciplines in a data-driven manner taking the complexity of language use into account. Linguistic Feature Extractor automates the feature extraction.
- PyTorch Tutorial : simple PyTorch Tutorial for a guest lecture I gave, suitable for beginners
- RNN Seq2seq transduction : customized pipeplines to model language transduction tasks using RNN seq2seq models
- RNN transduction : customized pipeplines to model language transduction tasks using RNNs
- Text matching explained & Text classification explained : building and training deep learning models for text (matching) classification tasks from scratch using paddle, PyTorch, and TensorFlow.
- Notes for Stanford CS224N : Natural Language Processing with Deep Learning.
- Hands on gradients derivations tutorials for common machine learning loss functions.
- Deep-learning-based Natural Language Processing using paddlenlp : covering a wide range of essential NLP tasks (both classification and non-classification) for industry and the SOTA practices.
- Word embedding resources, application, visualization, and training (word2vec in python).
- Text augmentation techniques : from random text-editing perturbations, back translation, to model-based transformations. Also see: data augmentation programs (plus ngram language model).
- Historical English Language Processing Toolkit : An efficient toolkit and a general framework for early modern & modern English Language Processing (multi-label annotation) in XML.
- Linguistic Feature Extractor : A corpus-linguistic tool to extract and search for linguistic features (with 95 builtin features), which generates both feature statistics and the extracted instances.
- Unfilled Pause Classifier : a rule-based syntactic parser classifying unfilled pauses based in the British Academic Spoken English corpus.
- Lstar Python : Python Implementation of the Lstar Algorithm by Angluin (1987).
- Google Scholar Analyzer : Auto-aggregating academic profiles of researchers on Google Scholar.
- YouTube Info Collector : An interface to scrape information (video titles, post dates, view counts, like counts, and comments etc.) from YouTube videos based on queries, video links, or channel links.
- Gender predictor : Predicting gender of given Chinese names with over 93% (up to 99%) test set accuracy using Naive Bayes, multi-class Logistic Regression, neural networks models.
- CCNC : A Comprehensive Chinese Name Corpus (3.65M unique name samples).
- Chinese Ngrams Counts : character-based and word-based from large-scale corpora.
- Corpus of Chinese synonyms : from multiple reputable sources with over 70k base examples.
- Corpus of Chinese fixed phrases and idioms : rich dictionary-like accounts for 30310 instances.