AdeDZY / DeepCT

DeepCT and HDCT uses BERT to generate novel, context-aware bag-of-words term weights for documents and queries.

AdeDZY/DeepCT Issues

how to choose K in top-K retrievement when using PRF(pseudo-relevance feedback)?
Updated 2 months ago1
train data file
Updated 2 years ago2
Can you provide a requirements.txt file for this project
Updated 2 years ago
HDCT
Updated 2 years ago
Training loss points in .tfevent differ from num_train_steps
Updated 2 years ago
Term weights non-deterministic?
Updated 3 years ago1
TRAIN_DATA_FILE
Updated 3 years ago
Question QTR & TR
Updated 3 years ago
comments/questions
Updated 3 years ago3
Why the text of a passage from msmarco is called `title`, and what does the field `position` of a doc mean?
Updated 3 years ago2
Question regarding quantization
Updated 3 years ago1
DeepCT-query instructions
Closed 4 years ago1
DeepCT-Query guidelines on how to use it
Updated 4 years ago2
Can we use DeepCT for other datasets apart from MSMARCO?
Closed 4 years ago2
compared with sentence embedding ann search
Updated 4 years ago
Does myalltrain.relevant.docterm_recall provide QTR(t,d) ?
Closed 4 years ago2
运行环境的说明能给一下嘛
Closed 5 years ago3
There are several bugs in code.
Closed 5 years ago1
TensorFlow version
Closed 5 years ago1