Code for technical report "An Improved Baseline for Sentence-level Relation Extraction".

Wenxuan Zhou

Last update: Nov 29, 2022

Related tags

Deep Learning RE_improved_baseline

Overview

RE_improved_baseline

Code for technical report "An Improved Baseline for Sentence-level Relation Extraction".

Requirements

torch >= 1.8.1
transformers >= 3.4.0
wandb
ujson
tqdm

The Pytorch version must be at least 1.8.1 as our code relies on the both the torch.cuda.amp and the torch.utils.checkpoint, which are introduced in the 1.8.1 release.

Dataset

The TACRED dataset can be obtained from this link. The TACREV and Re-TACRED dataset can be obtained following the instructions in tacrev and Re-TACRED, respectively. The expected structure of files is:

RE_improved_baseline
 |-- dataset
 |    |-- tacred
 |    |    |-- train.json        
 |    |    |-- dev.json
 |    |    |-- test.json
 |    |    |-- dev_rev.json
 |    |    |-- test_rev.json
 |    |-- retacred
 |    |    |-- train.json        
 |    |    |-- dev.json
 |    |    |-- test.json

Training and Evaluation

The commands and hyper-parameters for running experiments can be found in the scripts folder. For example, to train roberta-large, run

>> sh run_roberta_tacred.sh    # TACRED and TACREV
>> sh run_roberta_retacred.sh  # Re-TACRED

The evaluation results are synced to the wandb dashboard. The results on TACRED and TACREV can be obtained in one run as they share the same training set.

For all tested pre-trained language models, training can be conducted with one RTX 2080 Ti card.

Empirical Study of Transformers for Source Code & A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code

Transformers for variable misuse, function naming and code completion tasks The official PyTorch implementation of: Empirical Study of Transformers fo

56 Nov 15, 2022

Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pretrained models.

This repository is a toolkit to do machine learning for programming languages. It implements tokenization, dataset preprocessing, model training and m

408 Jan 1, 2023

Code for the prototype tool in our paper "CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning".

CoProtector Code for the prototype tool in our paper "CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning".

1 Oct 26, 2021

Low-code/No-code approach for deep learning inference on devices

EzEdgeAI A concept project that uses a low-code/no-code approach to implement deep learning inference on devices. It provides a componentized framewor

7 Apr 5, 2022

Code for all the Advent of Code'21 challenges mostly written in python

Advent of Code 21 Code for all the Advent of Code'21 challenges mostly written in python. They are not necessarily the best or fastest solutions but j

4 May 26, 2022

Code to use Augmented Shapiro Wilks Stopping, as well as code for the paper "Statistically Signifigant Stopping of Neural Network Training"

This codebase is being actively maintained, please create and issue if you have issues using it Basics All data files are included under losses and ea

32 Nov 9, 2021

Comments

Save and Load model

Hi, thank you so much for this repository and congratulations for your work!

Could you please update the code so that we can save and load the trained models? I trained a model based on your typed entity marker method and now I would like to load it and apply it to predict relations on new texts. I would appreciate if you can explain to me how to do it or give some examples.

Thank you!

opened by fillipefbr 1
Tiny bug with padding

Hey @wzhouad,

This is probably a harmless bug in the current code base but just wanted to point this out FYI.

The padding token is hard-coded to 0 in this line. However, for many models padding token id is non-zero (for roberta based models it's 1 and 0 actually corresponds to BOS token). As long as one sends the right attention mask (as you do), this should be harmless. Otherwise, this is a silent bug that might go unnoticed.

Cheers, Komal

opened by kkteru 0

Code for technical report "An Improved Baseline for Sentence-level Relation Extraction".

Related tags

Overview

RE_improved_baseline

Requirements

Dataset

Training and Evaluation

You might also like...

Empirical Study of Transformers for Source Code & A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code

Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pretrained models.

Code for the prototype tool in our paper "CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning".

Low-code/No-code approach for deep learning inference on devices

Code for all the Advent of Code'21 challenges mostly written in python

Code to use Augmented Shapiro Wilks Stopping, as well as code for the paper "Statistically Signifigant Stopping of Neural Network Training"

Opinionated code formatter, just like Python's black code formatter but for Beancount

a delightful machine learning tool that allows you to train, test and use models without writing code

Pytorch Lightning code guideline for conferences

Comments

Save and Load model

Tiny bug with padding

Owner

Wenxuan Zhou

🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"

Technical experimentations to beat the stock market using deep learning :chart_with_upwards_trend:

Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT

Resco: A simple python package that report the effect of deep residual learning

This is the official source code for SLATE. We provide the code for the model, the training code, and a dataset loader for the 3D Shapes dataset. This code is implemented in Pytorch.

TensorFlow code for the neural network presented in the paper: "Structural Language Models of Code" (ICML'2020)

Inference code for "StylePeople: A Generative Model of Fullbody Human Avatars" paper. This code is for the part of the paper describing video-based avatars.

A code generator from ONNX to PyTorch code

This is the code for our KILT leaderboard submission to the T-REx and zsRE tasks. It includes code for training a DPR model then continuing training with RAG.

Convert Python 3 code to CUDA code.