search

AdeDZY / DeepCT

DeepCT and HDCT uses BERT to generate novel, context-aware bag-of-words term weights for documents and queries.
BSD 3-Clause "New" or "Revised" License
312 stars 46 forks source link

compared with sentence embedding ann search #10

Open hrdxwandg opened 4 years ago

hrdxwandg commented 4 years ago

Hi, thanks for your excellent job. I have a question about The First Stage Retrieval (recall)

the first method: as described in the paper, we improve the term match with better term re-weight algorithm the second method: classic BM25 + sentence embedding ann search As multi-channel recall

which method is better？