gpl
gpl copied to clipboard
UKPLab
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation o...
Hi, General problem with multilingual models: give unequal performance among languages if the proportion of docs in lang A is greatly superior to the proportion of docs in lang B....
Tried to run the toy example on Azure, and I believe I made it all the way through training on the generated. My logs abruptly cut off so not sure...
First of all thanks a lot for bringing out this unique paper. After going through the paper I wanted to try out this approach but am little confused with the...
Hello! https://gpl.sbert.net/ seems to throw `ERR_TOO_MANY_REDIRECTS`
Hi, I have created a custom corpus.jsonl in the format structure as instructed. I am successfully able to install the library the gpl library on mac machine. I use the...
@kwang2049 Hi, thanks for your amazing work! I wonder if the TSDAE + GPL mentioned in the paper refers to: fine-tuning the distilbert-base PLM with training order of (1)TSDAE on...
I see in the code that two models (distilbert-base-uncased, msmarco-distilbert-margin-mse) are recommended to use as initial checkpoints. I tried to use other Sentence-Transformers models like all-mpnet-base-v2 but it didn't work....
There exists a version conflict in the dependencies of GPL. GPL requires `easy-elasticsearch>=0.0.7` (`0.0.7` is the latest version of `easy-elasticsearch`). `easy-elasticsearch` requires `elasticsearch==7.12.1` but beir, which GPL depends on at...
I'm not able to complete the gpl install due to this known issue: https://github.com/cvangysel/pytrec_eval/issues/32 I'm running python 3.9 and windows 10. Any suggestions? Update: I tried running python 3.6-3.9 to...
Hi , I am facing a key error while pseudo labeling. Looks like pos_pid selected is not found in the corpus. ```python INFO [gpl.toolkit.pl.run:60] Begin pseudo labeling ..... File ~gpl/toolkit/dataset.py:78,...
