Ming-Wei Chang
Artificial Intelligence · 2004–2022
A researcher in the Science corpus: 34 papers; trusts 2,011 researchers and is trusted by 12,747 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 833 citations into it; #60 of 36,961 by trust here, #42 by citations
- Natural Language Processing — 580 citations into it; #15 of 5,725 by trust here, #18 by citations
- Computer Vision and Pattern Recognition — 277 citations into it; #2,470 of 21,973 by trust here, #784 by citations
- Evaluation & Benchmarks — 144 citations into it; #1,187 of 3,155 by trust here, #134 by citations
- Information Retrieval & Search — 104 citations into it; #21 of 1,022 by trust here, #2 by citations
- Information Systems — 101 citations into it; #1,595 of 9,233 by trust here, #1,929 by citations
- Representation & Self-Supervised Learning — 82 citations into it; #777 of 3,156 by trust here, #812 by citations
- Large Language Models — 55 citations into it; #2 of 810 by trust here, #8 by citations
Whom Ming-Wei Chang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Michael Collins
- Geoffrey E. Hinton
- Yoshua Bengio
- Ilya Sutskever
- Diederik P. Kingma
- Alex Krizhevsky
- Tomas Mikolov
- Christopher D. Manning
- Yann LeCun
- Richard Socher
Who trusts Ming-Wei Chang overall
- Percy Liang
- Mohit Bansal
- Yi Tay
- Jianfeng Gao
- Zhe Gan
- Luke S. Zettlemoyer
- Timo Schick
- Luyu Gao
- Yoshua Bengio
- Yonatan Belinkov
Papers from Ming-Wei Chang's perspective
Ordered by how strongly the researchers Ming-Wei Chang trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (2019) — 118,136 citations
- Natural Questions: A Benchmark for Question Answering Research (2019) — 4,925 citations
- REALM: Retrieval-Augmented Language Model Pre-Training (2020) — 3,207 citations
- BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions (2019) — 2,559 citations
- Latent Retrieval for Weakly Supervised Open Domain Question Answering (2019) — 1,173 citations
- Driving Semantic Parsing from the World’s Response (2010) — 263 citations
- Search-based Neural Structured Learning for Sequential Question Answering (2017) — 278 citations
- A Knowledge-Grounded Neural Conversation Model (2017) — 591 citations
- Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base (2015) — 835 citations
- The Value of Semantic Parse Labeling for Knowledge Base Question Answering (2016) — 725 citations
- Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both? (2020) — 197 citations
- Question Answering Using Enhanced Lexical Semantic Models (2013) — 266 citations
- Well-Read Students Learn Better: On the Importance of Pre-training Compact Models (2019) — 775 citations
- Guiding Semi-Supervision with Constraint-Driven Learning (2007) — 240 citations
- Handling Divergent Reference Texts when Evaluating Table-to-Text Generation (2019) — 225 citations
- Well-Read Students Learn Better: The Impact of Student Initialization on Knowledge Distillation (2019) — 250 citations
- Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding (2022) — 473 citations
- Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations (2021) — 72 citations
- Open Domain Question Answering via Semantic Enrichment (2015) — 116 citations
- Discriminative Learning over Constrained Latent Representations (2010) — 83 citations