Python
Need help with TextKBQA?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.
rajarshd
205 Stars 70 Forks BSD 3-Clause "New" or "Revised" License 27 Commits 0 Opened issues

Services available

Need anything else?

This repo contains the tensorflow implementation of the paper "Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks".

Dependencies

  • TensorFlow <= 0.12

Training

I have set up training with most default params on a very small dataset so that it is easier to get started. Just running the script should work.

/bin/bash run.sh ./config.sh

Data

The processed data (train/dev/test split) is stored in dataformatted/ directory. To download the KB files used for the project run, ``` sh getdata.sh ``` After downloading the data, you will have to change the appropriate entries in the config.sh file (kbfile and textkb_file).

Pretrained embeddings

The embeddings used for initializing the network can be downloaded from here

Model outputs

We are also releasing the output predictions of our model for comparison. Find them in the model_outputs directory.

Trained Model

We are also sharing our pretrained model. Get it here. The following will load the model and get the answers from the dev set. Please change the config appropriately.

sh run.sh ./test_from_saved_model.sh

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.