Skip to content
Tag-enhanced Tree-Structured NN for discourse relation classification.
Branch: master
Clone or download
Latest commit 9b94421 Dec 6, 2017
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data
src
.gitignore open source Nov 24, 2017
LICENSE Create LICENSE Nov 24, 2017
README.md update the readme Dec 6, 2017

README.md

TagNN-PDTB

This repo contains the code for a state-of-the-art discourse relation classifier, trained and tested on PDTB V2.

Here We implemented the Tree-LSTM and Tree-GRU models and enhanced them with pos-tag information. You can find more details in our paper at IJCNLP 2017: Tag-Enhanced Tree-Structured Neural Networks for Implicit Discourse Relation Classification.

Data

We trained and and tested our models on PDTB V2 dataset. You should download them and convert the PDTB into a "pipe" delimited file using the built-in tool in the dataset.

Usage

To run the program, you can use the following command for preprocessing the data, prepare the formatted dataset and train the models:

python main.py [--preprocess] [--prepare] [--train]

For detailed usage, run python main.py -h to see the list of options.

License

MIT license

You can’t perform that action at this time.