RGAT-ABSA - GitLite

KO | EN

gitlite — search

#python #hacktoberfest #react #typescript #llm #golang #rust #deep-learning #java #windows #awesome #cli #pytorch #ios

RGAT-ABSA

(★ 218)

No description available.

파일 탐색기

최종 버전 다운로드 (.zip)

- - eval_results.txt
- - Laptop_Train_v2.xml
  - Laptop_Train_v2_biaffine_depparsed.json
  - Laptop_Train_v2_depparsed.json
  - Laptop_Train_v2_text.txt
  - Laptops_Test_Gold.xml
  - Laptops_Test_Gold_biaffine_depparsed.json
  - Laptops_Test_Gold_depparsed.json
  - Laptops_Test_Gold_text.txt
  - Restaurants_Test_Gold.xml
  - Restaurants_Test_Gold_biaffine_depparsed.json
  - Restaurants_Test_Gold_biaffine_depparsed_with_energy.json
  - Restaurants_Test_Gold_depparsed.json
  - Restaurants_Test_Gold_text.txt
  - Restaurants_Train_v2.xml
  - Restaurants_Train_v2_biaffine_depparsed.json
  - Restaurants_Train_v2_biaffine_depparsed_with_energy.json
  - Restaurants_Train_v2_depparsed.json
  - Restaurants_Train_v2_text.txt
- - acl-14-short-data.zip
  - readme.txt
  - test.raw
  - test.txt
  - test.txt.out
  - test_biaffine.json
  - test_depparsed.json
  - test_New_Depparsed.json
  - train.raw
  - train.txt
  - train.txt.out
  - train_biaffine.json
  - train_depparsed.json
  - train_New_Depparsed.json
data_preprocess_semeval.py
data_preprocess_twitter.py
datasets.py
LICENSE
model.py
model_gcn.py
model_utils.py
README.md
run.py
run.sh
trainer.py
tree.py
tree_samples.json

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Relational-Graph-Attention-Network-for-Aspect-based-Sentiment-Analysis
This repo contains the PyTorch implementaion for the paper [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://arxiv.org/abs/2004.12362).

For any questions about the implementation, plaese email shenwzh3@mail2.sysu.edu.cn.

## Requirements
* Python 3.6.8
* PyTorch 1.2.0
* Transformers https://github.com/huggingface/transformers
* CUDA 9.0

## Perparation
### For Glove Embedding
First, download and unzip GloVe vectors(`glove.840B.300d.zip`) from https://nlp.stanford.edu/projects/glove/. Then change the value of parameter `--glove_dir` to the directory of the word vector file.

### For BERT Embedding
Download the pytorch version pre-trained `bert-base-uncased` model and vocabulary from the link provided by huggingface. Then change the value of parameter `--bert_model_dir` to the directory of the bert model.

## Preprocess
The preprocess codes are in `data_preprocess_semeval.py` and `data_preprocess_twitter.py`. However we already provided the preprocessed datasets with dependency parcing results in `./data/`, so you can skip preprocess.

## Training
Run:
`./run.sh`