Hi there, I’m Irene Li (李紫辉)! Welcome to my blog! 🙂
I want to share my learning journals, notes, and programming exercises with you. The topics include data science, statistics, machine learning, deep learning, AI applications, etc.
I am now an Assistant Professor at the Information Technology Center, University of Tokyo. Please contact me via ireneli[at]ds.itc.u-tokyo.ac.jp or irene.li[at]aya.yale.edu. I am starting my own Li-Lab at Tokyo University, working in AI, ML, and NLP. I am actively looking for research assistants to join our lab for collaboration. Please drop me an email for potential research projects.
Before moving to Japan, I worked in the LILY lab at Yale University. My Ph.D. advisor is Prof. Dragomir Radev. On March 2022, I passed my Ph.D. Defense on the topic of “Neural Graph Transfer Learning in Natural Language Processing Tasks”! 🎉
Graph Neural Networks for NLP
- LiGCN: Label-interpretable Graph Convolutional Networks for Multi-label Text Classification
Irene Li, Aosong Feng, Tianxiao Li, Hao Wu, Toyotaro Suzumura and Ruihai Dong
DLG4NLP Workshop, NAACL 2022.
- Variational Graph Autoencoding as Cheap Supervision for AMR Coreference Resolution
Irene Li, Linfeng Song, Kun Xu and Dong Yu
- Efficient Variational Graph Autoencoders for Unsupervised Cross-domain Prerequisite Chains
Irene Li, Vanessa Yan and Dragomir Radev
ENLSP Workshop, NeurIPS 2021.
- Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders
Irene Li, Vanessa Yan, Tianxiao Li, Rihao Qu and Dragomir Radev
ACL, 2021. Slides. Github.
- R-VGAE: Relational-variational Graph Autoencoder for Unsupervised Prerequisite Chain Learning
Irene Li, Alexander Fabbri, Swapnil Hingmire, and Dragomir Radev
COLING, 2020. Slides. Github.
- What Should I Learn First: Introducing LectureBank for NLP Education and Prerequisite Chain Learning
Irene Li, Alexander Fabbri, Robert Tung, and Dragomir Radev
AAAI, 2019. Dataset
Transfer Learning, Attention Models
- Surfer100: Generating Surveys From Web Resources, Wikipedia-style
Irene Li, Alexander Fabbri, Rina Kawamura, Yixin Liu, Xiangru Tang, Jaesung Tae, Chang Shen, Sally Ma, Tomoe Mizutani, Dragomir Radev
- Improving Cross-lingual Text Classification with Zero-shot Instance-Weighting
Irene Li, Prithviraj Sen, Huaiyu Zhu, Yunyao Li and Dragomir Radev
RepL4NLP Workshop, ACL, 2021
- A Neural Topic-Attention Model for Medical Term Abbreviation Disambiguation
Irene Li, Michihiro Yasunaga, Muhammed Yavuz Nuzumlalı, Cesar Caraballo, Shiwani Mahajan, Harlan Krumholz, and Dragomir Radev
Machine Learning for Health Workshop, NeurIPS 2019. Code
- Detecting Bias in Transfer Learning Approaches for Text Classification
arXiv preprint, 2021
- Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model
Alexander Fabbri, Irene Li, Tianwei She, Suyi Li, and Dragomir Radev
ACL 2019. Dataset and Code
- TutorialBank: Using a Manually-Collected Corpus for Prerequisite Chains, Survey Extraction and Resource Recommendation
Alexander Fabbri, Irene Li, Prawat Trairatvorakul, Yijiao He, Weitai Ting, Robert Tung, Caitlin Westerfield, and Dragomir Radev
ACL 2018. Dataset. BLOG.
- Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review
Irene Li, Jessica Pan, Jeremy Goldwasser, Neha Verma, Wai Pan Wong, Muhammed Yavuz Nuzumlalı, Benjamin Rosand, Yixin Li, Matthew Zhang, David Chang, R. Andrew Taylor, Harlan M. Krumholz and Dragomir Radev
Computer Science Review, volume 46, 2022
NLP for EHR, Covid
- Global Data Science Project for COVID-19 Summary Report
Dario Garcia-Gasulla, Sergio Alvarez Napagao, Irene Li, Hiroshi Maruyama, Hiroki Kanezashi, Raquel P’erez-Arnal, Kunihiko Miyoshi, Euma Ishii, Keita Suzuki, Sayaka Shiba, Mariko Kurokawa, Yuta Kanzawa, Naomi Nakagawa, Masatoshi Hanai, Yixin Li, Tianxiao Li
arXiv preprint, 2020
- What are We Depressed about When We Talk about COVID-19: Mental Health Analysis on Tweets Using Natural Language Processing
Irene Li, Yixin Li, Tianxiao Li, Sergio Alvarez-Napagao, Dario Garcia-Gasulla, Toyotaro Suzumura
Fortieth SGAI International Conference on Artificial Intelligence, 2020. Slides. Github
- SParC: Cross-Domain Semantic Parsing in Context
Tao Yu, Rui Zhang, Michihiro Yasunaga, Yi-Chern Tan, Xi Victoria Lin, Suyi Li, Heyang Er, Irene Li, Bo Pang, Tao Chen, Emily Ji, Shreya Dixit, David Proctor, Sungrok Shim, Jonathan Kraft, Vincent Zhang, Caiming Xiong, Richard Socher and Dragomir Radev
- ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks
Michihiro Yasunaga, Jungo Kasai, Rui Zhang, Alexander Fabbri, Irene Li, Dan Friedman, and Dragomir Radev
- Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task
Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang, and Dragomir Radev
EMNLP 2018 BLOG
Earlier Research Work (Before my PhD)
- Medical Text Classification Using Convolutional Neural Networks (Informatics for Health 2017), internship work at IBM Research
- Research of distributed search engine based on Hadoop (DSEH) (Applied Mechanics and Materials 2013), work during Undergraduate
📄 Recent Posts
- Deep Learning 22: Diffusion Models (2)
- Deep Learning 21: Diffusion Models (1)
- Deep Learning 20: graph batching in PyTorch Geometric
- AAN.how: All About NLP —— New 2022 Release: over 24,000 resources and over 7,000 lecture notes!
- Deep Learning 19: Training MLM on any pre-trained BERT models
- Slideshare (11): Graph Neural Networks and Applications in NLP
- Slideshare (10): Reading notes bout Text Generation, BERT, Knowledge Distillation…
- Paddle Serving: model-as-a-service! Triggered by a single command line, deployment finishes in 10 minutes
- Slideshare (9): Transfer learning tutorial 2.0
- Slideshare (8): Graph Neural Network Paper reading notes
- Slideshare (7): NeurIPS 2019 Notes on NLP and GCNs
- Expanded AAN.how: Learning NLP Made Much Easier!
- Slideshare (6): Cross-lingual Paper reading notes
- Slideshare (5): Graph Neural Networks
- Prepare for the Interviews!
- Deep Learning 18: GANs with PyTorch
- Deep Learning 17: text classification with BERT using PyTorch
- Understanding Variational Graph Auto-Encoders
- Resources for BioNLP: datasets and tools
- Understanding Graph Convolutional Networks
- LectureBank: a dataset for NLP Education and Prerequisite Chain Learning
- ELMo in Practice
- Slideshare (4): A brief Introduction on Transfer Learning
- Transfer Learning Materials
- Slideshare (3): Unsupervised Transfer Learning Methods
- TensorFlow 08: save and restore a subset of variables
- To copy or not, that is the question: copying mechanism
- What matters: attention mechanism
- What’s next: seq2seq models
- Deep Learning 16: Understanding Capsule Nets
- Book Translation: AI Blueprints: How to build and deploy AI business projects (Origin) in progress, the Chinese version is on sale now on jd.com (2022)
- Teaching Fellow for CPSC 477/577 Natural Language Processing at Yale (2020, Spring).
- Book Translation: Learning TensorFlow (O’Reilly Media) (Origin) Chinese version is on sale now on jd.com (2018).
- Deep Learning Meetup @ Dublin, Ireland: organizer and committee member (2016-2017)