deepct / README.md

Sean MacAvaney

initial commit

1f3d61a almost 4 years ago

809 Bytes

language:
  - en
tags:
  - retrieval
  - document-rewriting
datasets:
  - irds:msmarco-passage
library_name: transformers

A DeepCT model based on bert-base-uncased and trained on MS MARCO. This is a version of the checkpoint released by the original authors, converted to pytorch format and ready for use in PyTerrier.

References

[Dai19]: Zhuyun Dai, Jamie Callan. Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval. https://arxiv.org/abs/1910.10687
[Macdonald20]: Craig Macdonald, Nicola Tonellotto. Declarative Experimentation in Information Retrieval using PyTerrier. Craig Macdonald and Nicola Tonellotto. In Proceedings of ICTIR 2020. https://arxiv.org/abs/2007.14271