sordonia / hred-qs Goto Github PK

I trained and tested on AOL data

But the results after running samply.py is not very good.

Can you help me analyze it?

Or can you teach me how to use "Learning to Rank" method in this experiment.

Hi, Sordonj, Thanks for your great work.
I have some problem running the convert-text2dict.py,
I know [session file] means query serises, how about [rank_file]?

Hi! sordonia,Thanks for your comment in the last issue.
But a NameError problem occured when running suggest.py

error message:
Traceback (most recent call last):
File "suggest.py", line 110, in
main()
File "suggest.py", line 102, in main
seqs = context_to_indices(lines, model)
NameError: global name 'context_to_indices' is not defined

Hi,
Can you please provide the processed train and test data that you used in the paper

First, I would like to thank you for releasing this great work as open-source.

Would you please mind adding some documentation to the project (docstring for functions and modules, comments in the code, wiki of the project, Project wiki, explanation of the order of execution, etc..) to improve reproducibility.

It's really time-consuming to read all the project line by line and try to infer the meaning of every variable.

Thank you in advance!

hi：
When I run your project,（ python train.py --prototype prototype_test）I encountered the following error，how should I change, thank you！

Traceback (most recent call last):
File "train.py", line 204, in
main(args)
File "train.py", line 93, in main
model = SessionEncoderDecoder(state)
File "/home/dixin/work/hred-qs/session_encdec.py", line 586, in init
self.encoder.build_encoder(training_x, xmask=training_hs_mask)
File "/home/dixin/work/hred-qs/session_encdec.py", line 167, in build_encoder
f_enc, sequences=[xe, xmask], outputs_info=o_enc_info)
File "/home/work/anaconda/lib/python2.7/site-packages/theano/scan_module/scan.py", line 1041, in scan
scan_outs = local_op(*scan_inputs)
File "/home/work/anaconda/lib/python2.7/site-packages/theano/gof/op.py", line 611, in call
node = self.make_node(*inputs, **kwargs)
File "/home/work/anaconda/lib/python2.7/site-packages/theano/scan_module/scan_op.py", line 538, in make_node
inner_sitsot_out.type.dtype))
ValueError: When compiling the inner function of scan the following error has been encountered: The initial state (outputs_info in scan nomenclature) of variable IncSubtensor{Set;:int64:}.0 (argument number 2) has dtype float32, while the result of the inner function (fn) has dtype float64. This can happen if the inner function of scan results in an upcast or downcast.

Hello dear sordonia
you wrote;

we sort the query log by query timestamp and we use the queries submitted before 1 May,
2006 as our background data to estimate the proposed model and the baselines. The next two weeks of data are used as a training set for tuning the ranking models. The remaining two weeks are split into the validation and the test set.

what does it mean background data? why didnt you use in training phase background data.

I want to reproduce your work, but when running the code encountered some problems. I hope you can give a more detailed readme.

So that I can run these programs step by step：）

Hello,
Good idea. Bu I wonder about preprocess. You wrote on the paper "apply a spelling corrector". which spell corrector did you use?

Looks like the evaluation file is missing

Traceback (most recent call last):
File "train.py", line 7, in
from evaluation import *
ImportError: No module named evaluation