edithal-14 / rdv-cnn Goto Github PK
View Code? Open in Web Editor NEWRDV-CNN model for document level novelty detection. Comparision of our model with baselines on three popular datasets.
RDV-CNN model for document level novelty detection. Comparision of our model with baselines on three popular datasets.
I have downloaded the DNLD dataset from "http://www.iitp.ac.in/~ai-nlp-ml/resources.html".
In make_dlnd_data.py:
In the first line "sys.path.append ()", I have put the path till the encoder directory of sentence_encoder.
I put the path of dataset in the place of dlnd_path,
I path the path of "model_2048_attn.pickle" in the infersent = torch.load(), and path of Glove in the glove_path line. While running it gives the error in loading the model . The error message is -
loading infersent...
Traceback (most recent call last):
File "make_dlnd_data.py", line 36, in
infersent = torch.load("/home/mtp-2/Desktop/New_Coling/A-Deep-Neural-Solution-To-Document-Level-Novelty-Detection-COLING-2018--master/sentence_encoder/encoder/model_2048_attn.pickle")
File "/home/mtp-2/anaconda2/lib/python2.7/site-packages/torch/serialization.py", line 358, in load
return _load(f, map_location, pickle_module)
File "/home/mtp-2/anaconda2/lib/python2.7/site-packages/torch/serialization.py", line 542, in _load
result = unpickler.load()
AttributeError: 'module' object has no attribute 'InnerAttentionNAACLEncoder'
I have searched for the solution of this error, but could not get the answer.
It would be great, if you will help me.
Hi,
First of all thank you for providing the code alongside your COLING paper. We wanted to run your provided code on the WEBIS data for a personal project. Unfortunately, I am running into several compatibility issues such as with CUDA, Tensorflow and Theano. Since, I had CUDA 9.0 installed I had to resort to Python 2.7, which now has issues with NLTK while running the codes. Can you kindly specify the versions of each of the following software/packages that are required to run your code?
Also, I noticed that in the Readme file, you have mentioned to use make_dlnd_data.py under WEBIS heading to fetch the sentence embeddings (see attached screenshot).
That doesn't seem right. Is the corresponding file missing for webis_cpc?
Because, when I try to run webis_sentence_embedding.py, it throws an error asking for path to _webis_data.pickle, which is supposed to be generated with some other code, right?
Corollary to the above question, could you kindly specify in the documentation or maybe as a command line exception, what arguments need to be passed for each python file? That would make our lives a lot easier.
Any additional help is welcome.
Thanking in anticipation,
Manajit
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.