Convolution over Hierarchical Syntactic and Lexical Graphs for Aspect Level Sentiment Analysis
- Code and preprocessed dataset for EMNLP 2020 paper titled "Convolution over Hierarchical Syntactic and Lexical Graphs for Aspect Level Sentiment Analysis"
- Python 3.7
- PyTorch 1.1.0
- SpaCy 2.0.18
- numpy 1.16.2
- Download pretrained GloVe embeddings with this link and extract
glove.840B.300d.txtintoglove/. - Train with command, optional arguments could be found in train.py
python train.py --dataset rest16 --vocab_dir datasets/semeval16/rest16_ --save TrueIf you use the code in your paper, please kindly star this repo and cite our paper
@inproceedings{DBLP:conf/emnlp/ZhangQ20,
author = {Mi Zhang and
Tieyun Qian},
title = {Convolution over Hierarchical Syntactic and Lexical Graphs for Aspect
Level Sentiment Analysis},
booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural
Language Processing, {EMNLP} 2020, Online, November 16-20, 2020},
pages = {3540--3549},
year = {2020},
crossref = {DBLP:conf/emnlp/2020-1},
url = {https://www.aclweb.org/anthology/2020.emnlp-main.286/},
timestamp = {Thu, 19 Nov 2020 16:13:16 +0100},
biburl = {https://dblp.org/rec/conf/emnlp/ZhangQ20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
- Code of this repo heavily relies on ABSA-PyTorch and ASGCN
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent