Condenser: a Pre-training Architecture for Dense Retrieval

By Luyu Gao, Jamie Callan. 2021

308 citations recorded by the source corpus.

Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient text comparison and retrieval. However, dense encoders require a lot of data and sophisticated techniques to effectively train and suffer in low data situations. This paper finds a key reason is that standard LMs’ internal attention structure is not ready-to-use for dense encoders, which needs to aggregate text information into the dense representation. We propose to pre-train towards dense encoder with a novel Transformer architecture, Condenser, where LM prediction CONditions on DENSE Representation. Our experiments show Condenser improves over standard LM by large margins on various text retrieval and similarity tasks.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Retrieval-Augmented Generation, Information Retrieval & Search

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Luke S. Zettlemoyer
  2. Furu Wei
  3. Mohit Bansal
  4. Sebastian Riedel
  5. Wen-tau Yih
  6. Jianfeng Gao
  7. Percy Liang
  8. Hannaneh Hajishirzi

In Computer Vision and Pattern Recognition

  1. Furu Wei
  2. Sebastian Riedel
  3. Wen-tau Yih
  4. Luc Van Gool
  5. Luke S. Zettlemoyer
  6. Dacheng Tao
  7. Jonathan Berant
  8. Jianfeng Gao

In Retrieval-Augmented Generation

  1. Sebastian Riedel
  2. Luyu Gao
  3. Wen-tau Yih
  4. Jamie Callan
  5. Fabio Petroni
  6. Jonathan Berant
  7. Ruiyang Ren
  8. Jing Liu

In Information Retrieval & Search

  1. Luyu Gao
  2. Jamie Callan
  3. Sebastian Riedel
  4. Jing Liu
  5. Ruiyang Ren
  6. Wen-tau Yih
  7. Ji-rong Wen
  8. Wayne Xin Zhao

Citations in the corpus