Accompanying repository for our EMNLP 2017 paper (full paper). It contains the code to replicate the experiments and the pre-trained models for sentence-level relation extraction.
This repository contains experimental software and is published for the sole purpose of giving additional background details on the respective publication.
Please use the following citation:
@inproceedings{TUD-CS-2017-0119,
title = {Context-Aware Representations for Knowledge Base Relation Extraction},
author = {Sorokin, Daniil and Gurevych, Iryna},
booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
pages = {(to appear)},
year = {2017},
location = {Copenhagen, Denmark},
}
We demonstrate that for sentence-level relation extraction it is beneficial to consider other relations in the sentential context while predicting the target relation. Our architecture uses an LSTM-based encoder to jointly learn representations for all relations in a single sentence. We combine the context representations with an attention mechanism to make the final prediction. We use the Wikidata knowledge base to construct a dataset of multiple relations per sentence and to evaluate our approach. Compared to a baseline system, our method results in an average error reduction of 24% on a held-out set of relations.
Please, refer to the paper for more details.
The dataset described in the paper can be found here:
If you have any questions regarding the code, please, don't hesitate to contact the authors or report an issue.
You can try out the model on single sentences in our demo:
http://semanticparsing.ukp.informatik.tu-darmstadt.de:5000/
relation_extraction/
├── apply-model.py
├── eval.py
├── model-train-and-test.py
├── notebooks
├── optimization_space.py
├── parsing
│ ├── semanticparsing.py
│ └── sp_models.py
├── semanticgraph
│ ├── graph_utils.py
│ ├── io.py
│ └── vis_utils.py
├── stanford_tag_dataset.py
└── utils
├── embedding_utils.py
├── evaluation_utils.py
└── graph.py
resources/
└── property_blacklist.txt
File | Description |
---|---|
relation_extraction/ | Main Python module |
relation_extraction/parsing | Models for joint relation extraction |
relation_extraction/semanticgraph | IO and processing for relation graphs |
relation_extraction/utils | IO and evaluation utils |
resources/ | Necessary resources |
-
We recommend that you setup a new pip environment first: http://docs.python-guide.org/en/latest/dev/virtualenvs/
-
Check out the repository and run:
pip3 install -r requirements.txt
- Set the Keras (deep learning library) backend to Theano (even deeper deep learning library) with the following command:
export KERAS_BACKEND=theano
You can also permanently change Keras backend (read more: https://keras.io/backend/).
- Download the data, if you want to replicate the experiments from the paper
- You can download the models that were used in the experiments here
- We will soon make available updated models and will publish usage instructions
- Python 3.4
- See requirements.txt for library requirements.
- Apache License Version 2.0