unikcc / DiaASQ

ACL 2023 (Findings) : DiaASQ: A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis

Home Page:https://diaasq-page.pages.dev/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

DiaASQ

pytorch 1.8.1 pytorch 1.8.1 Build Status

This repository contains data and code for the ACL23 (findings) paper: DiaASQ: A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis

See the project page for more details.


To clone the repository, please run the following command:

git clone https://github.com/unikcc/DiaASQ

News 🎉

📢 2023-05-10: Released code and dataset.
2022-12-10: Created repository.

Quick Links

Overview

In this work, we propose a new task named DiaASQ, which aims to extract Target-Aspect-Opinion-Sentiment quadruples from the given dialogue. More details about the task can be found in our paper.

DiaASQ Data

The dataset can be found at:

data/dataset
  - jsons_en
  - jsons_zh

Requirements

The model is implemented using PyTorch. The versions of the main packages:

  • python>=3.7
  • torch>=1.8.1

Install the other required packages:

pip install -r requirements.txt

Code Usage

  • Train && Evaluate on the Chinese dataset

    bash scripts/train_zh.sh
  • Train && Evaluate on the English dataset

    bash scripts/train_en.sh
  • GPU memory requirements

    Dataset Batch size GPU Memory
    Chinese 2 8GB.
    English 2 16GB.
  • Customized hyperparameters:
    You can set hyperparameters in main.py or src/config.yaml, and the former has a higher priority.

Citation

If you use our dataset, please cite the following paper:

@inproceedings{li-2023-diaasq,
    title = "{D}ia{ASQ}: A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis",
    author = "Li, Bobo  and Fei, Hao and Li, Fei and Wu, Yuhan and Zhang, Jinsong and Wu, Shengqiong and Li, Jingye and
      Liu, Yijiang and Liao, Lizi and Chua, Tat-Seng and Ji, Donghong",
    booktitle = "Findings of ACL",
    year = "2023",
    pages = "13449--13467",
}

About

ACL 2023 (Findings) : DiaASQ: A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis

https://diaasq-page.pages.dev/

License:MIT License


Languages

Language:Python 99.7%Language:Shell 0.3%