Code Monkey home page Code Monkey logo

nre's Introduction

Neural relation extraction aims to extract relations from plain text with neural models, which has been the state-of-the-art methods for relation extraction. In this project, we provide our implementations of CNN [Zeng et al., 2014] and PCNN [Zeng et al.,2015] and their extended version with sentence-level attention scheme [Lin et al., 2016] .

Evaluation Results

Precion/recall curves of CNN, CNN+ONE, CNN+AVE, CNN+ATT

image

Precion/recall curves of PCNN, PCNN+ONE, PCNN+AVE, PCNN+ATT

image

Data

We provide NYT10 dataset we used for the task relation extraction in data/ directory. We preprocess the original data to make it satisfy the input format of our codes. The original data of NYT10 can be downloaded from:

Relation Extraction: NYT10 is originally released by the paper "Sebastian Riedel, Limin Yao, and Andrew McCallum. Modeling relations and their mentions without labeled text." [Download]

Pre-Trained Word Vectors are learned from New York Times Annotated Corpus (LDC Data LDC2008T19), which should be obtained from LDC (https://catalog.ldc.upenn.edu/LDC2008T19).

To run our code, the dataset should be put in the folder data/ using the following format, containing six files

  • train.txt: training file, format (fb_mid_e1, fb_mid_e2, e1_name, e2_name, relation, sentence).

  • test.txt: test file, same format as train.txt.

  • entity2id.txt: all entities and corresponding ids, one per line.

  • relation2id.txt: all relations and corresponding ids, one per line.

  • vec.bin: the pre-train word embedding file

Codes

The source codes of various methods are put in the folders CNN+ONE/, CNN+ATT/, PCNN+ONE/, PCNN+ATT/.

Compile

Just type "make" in the corresponding folders.

Train

For training, you need to type the following command in each model folder:

./train

The training model file will be saved in folder out/ .

Test

For testing, you need to type the following command in each model folder:

./test

The testing result which reports the precision/recall curve will be shown in pr.txt.

Cite

If you use the code, please cite the following paper:

[Lin et al., 2016] Yankai Lin, Shiqi Shen, Zhiyuan Liu, Huanbo Luan, and Maosong Sun. Neural Relation Extraction with Selective Attention over Instances. In Proceedings of ACL.[pdf]

Reference

[Zeng et al., 2014] Daojian Zeng, Kang Liu, Siwei Lai, Guangyou Zhou, and Jun Zhao. Relation classification via convolutional deep neural network. In Proceedings of COLING.

[Zeng et al.,2015] Daojian Zeng,Kang Liu,Yubo Chen,and Jun Zhao. Distant supervision for relation extraction via piecewise convolutional neural networks. In Proceedings of EMNLP.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.