Matei Zaharia

Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval

2021 · arXiv (Cornell University)

Multi-hop reasoning (i.e., reasoning across two or more documents) is a key ingredient for NLP models that leverage large corpora to exhibit broad knowledge. To retrieve evidence passages, multi-hop models must contend with a fast-growing …

ColBERT

2020

Recent progress in Natural Language Understanding (NLU) is driving fast-paced advances in Information Retrieval (IR), largely owed to fine-tuning deep language models (LMs) for document ranking. While remarkably effective, the ranking models based on these …

ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT

2020 · arXiv (Cornell University)

Recent progress in Natural Language Understanding (NLU) is driving fast-paced advances in Information Retrieval (IR), largely owed to fine-tuning deep language models (LMs) for document ranking. While remarkably effective, the ranking models based on these …