Dr. Danqi Chen
Princeton University
Associate Professor of Computer Science at Princeton University and Director of the Princeton NLP Group. Pioneered Dense Passage Retrieval (DPR) for open-domain question answering and contrastive sentence representation (SimCSE), laying the bedrock for modern semantic search and dense embedding retrieval.
Areas of focus
Professional niches
Proof of Work
SimCSE: Simple Contrastive Learning of Sentence Embeddings
Created SimCSE, an unsupervised contrastive learning framework that uses standard dropout as data augmentation to learn state-of-the-art sentence embeddings, advancing semantic retrieval without labeled pairs.
Sentence embeddings compress entire paragraphs into single fixed-size vectors, losing granular token-level context.
Context: BERT and RoBERTa backends with contrastive temperature scaling.
View missionDense Passage Retrieval for Open-Domain Question Answering (DPR)
Published the landmark EMNLP 2020 paper demonstrating that dual-encoder BERT architectures trained on contrastive negative passages dramatically outperform classic BM25 and TF-IDF sparse retrieval in question answering.
Pure dense retrieval can struggle on out-of-domain lexical keywords and acronyms compared to hybrid dense-sparse search.
Context: Dual BERT encoders, dot-product similarity search over FAISS vector indices.
View mission