/tensor-tree-nn

A framework to develop recursive models by leveraging tensor decompositions.

Primary LanguagePython

Tensor Recursive Model

We provide an extension neural and probabilistic models of recursive models for tree-structure data based on tensor theory.

List of publication based on this repository:

Code Structure

The code is structured as follows:

  • data contains the BoolSent dataset
  • models contains the implementation of the recursive models (both probabilistic and neural);
  • preprocessing contains the code to preprocess the datasets;
  • tasks contains all the files to execute the experiments; there is a readme files for each task;
  • tree_utils contains utils code.

Also, two other repositories are used:

  • exputils provides the utils to run an experiment, train a model, parse configuration, etc..
  • thlogprob provides a minimal library to handle distribution using pytorch.

See the readme for more information.

How to run an experiment

  1. download the raw data (see next section);

  2. in NLP tasks, sentences should be parsed running the command:

    python tasks/task_name/parse_raw_data raw_data_folder output_folder

  3. Run the preprocessor using the command:

    python preprocess.py --config-file preproc_config_file,
    where preproc_config_file can be found in the folder tasks/task_name/config_files

  4. Run the experiment using the command:

    python run.py --config-file run_config_file,
    where run_config_file can be found in the folder tasks/task_name/config_files.

Where to download the dataset