SimCSE在中文任务上的简单实验

Related tags

MiscellaneousSimCSE
Overview

SimCSE 中文测试

SimCSE在常见中文数据集上的测试,包含ATECBQLCQMCPAWSXSTS-B共5个任务。

介绍

文件

- utils.py  工具函数
- eval.py  评测主文件

评测

命令格式:

python eval.py [model_type] [pooling] [task_name] [dropout_rate]

使用例子:

python eval.py BERT cls ATEC 0.3

其中四个参数必须传入,含义分别如下:

- model_type: 模型,必须是['BERT', 'RoBERTa', 'WoBERT', 'RoFormer', 'BERT-large', 'RoBERTa-large', 'SimBERT', 'SimBERT-tiny', 'SimBERT-small']之一;
- pooling: 池化方式,必须是['first-last-avg', 'last-avg', 'cls', 'pooler']之一;
- task_name: 评测数据集,必须是['ATEC', 'BQ', 'LCQMC', 'PAWSX', 'STS-B']之一;
- dropout_rate: 浮点数,dropout的比例,如果为0则不dropout;

环境

测试环境:tensorflow 1.14 + keras 2.3.1 + bert4keras 0.10.5,如果在其他环境组合下报错,请根据错误信息自行调整代码。

下载

Google官方的两个BERT模型:

关于语义相似度数据集,可以从数据集对应的链接自行下载,也可以从作者提供的百度云链接下载。

其中senteval_cn目录是评测数据集汇总,senteval_cn.zip是senteval目录的打包,两者下其一就好。

相关

交流

QQ交流群:808623966,微信群请加机器人微信号spaces_ac_cn

Owner
苏剑林(Jianlin Su)
科学爱好者
苏剑林(Jianlin Su)
Python Project For Beginner

Basic-Vitrual-AI-Assistant Python Project For Beginner Hey There, I had manipulated Selenium WebDriver to make this assistant. I hope, It will be help

Maruf Billah 13 Dec 12, 2022
Reverse the infix string. Note that while reversing the string you must interchange left and right parentheses

Reverse the infix string. Note that while reversing the string you must interchange left and right parentheses. Obtain the postfix expression of the infix expression Step 1.Reverse the postfix expres

Sazzad Hossen 1 Jan 04, 2022
Retrying is an Apache 2.0 licensed general-purpose retrying library, written in Python, to simplify the task of adding retry behavior to just about anything.

Retrying Retrying is an Apache 2.0 licensed general-purpose retrying library, written in Python, to simplify the task of adding retry behavior to just

Ray Holder 1.9k Dec 29, 2022
Mommas-cookbook - A Repository About Mom's Recipes

Mommas Cookbook A Repository for Mom's Recipes Contents bacalhau à Gomes de Sá Beef-Rendang bacalhau à Gomes de Sá, recommended by @s0undt3ch One of t

1 Jan 08, 2022
Strawberry Benchmark With Python

Strawberry benchmarks these benchmarks have been made to compare the performance of dataloaders and joined database queries. How to use You can run th

Doctor 4 Feb 23, 2022
py2dis - A disassembly engine & library for Python

py2dis - A disassembly engine & library for Python. py2dis is a disassembly library for Python that does not use any modules/libraries other than colo

3 Feb 04, 2022
Apache Airflow - A platform to programmatically author, schedule, and monitor workflows

Apache Airflow Apache Airflow (or simply Airflow) is a platform to programmatically author, schedule, and monitor workflows. When workflows are define

The Apache Software Foundation 28.6k Dec 28, 2022
Mannaggia is a python application to praise or more likely to curse the saints

Mannaggia-py 👼 Remember Mannaggia? This is a Python remake of it, with new features. mannaggia is a python application to praise or more likely to cu

Christian Visintin 9 Aug 12, 2022
Port of the OpenCascade library to JavaScript / WebAssembly using Emscripten

OpenCascade.js A port of the OpenCascade CAD library to JavaScript and WebAssembly via Emscripten. Explore the docs » Examples · Issues · Discuss Proj

Sebastian Alff 347 Jan 08, 2023
A python script to run any executable and pass test cases to it's stdin and compare stdout with correct output.

quera_testcase_checker A python script to run any executable and pass test cases to it's stdin and compare stdout with correct output. proper way to u

k3y1 1 Nov 15, 2021
Customizable-menu-python - User customizable menu in Python

Menu personalizável pelo usuário em Python A minha ideia com esse projeto pessoa

Renan Barbosa 4 Oct 28, 2022
A conda-smithy repository for boost-histogram.

The official Boost.Histogram Python bindings. Provides fast, efficient histogramming with a variety of different storages combined with dozens of composable axes. Part of the Scikit-HEP family.

conda-forge 0 Dec 17, 2021
A Brainfuck interpreter written in Python.

A Brainfuck interpreter written in Python.

Ethan Evans 1 Dec 05, 2021
With Christmas and New Year ahead, it is time for some festive coding. Here is a Christmas Card for you all!

Christmas Card With Christmas and New Year ahead, it is time for some festive coding! Here is a Christmas Card for you all! NOTE: I have not made this

CodeMaster7000 1 Dec 25, 2021
PhD document for navlab

PhD_document_for_navlab The project contains the relative software documents which I developped or used during my PhD period. It includes: FLVIS. A st

ZOU YAJING 9 Feb 21, 2022
A simple bot that will help you in your learning and make it more fun.

hyperskill-SimpleChattyBot-python A simple bot that will help you in your learning and make it more fun. Syntax bot.py Stages Stage #1: Zuhura Bot we

1 Nov 09, 2021
C++ Environment InitiatorVisual Studio Code C / C++ Environment Initiator

Visual Studio Code C / C++ Environment Initiator Latest Version : v 1.0.1(2021/11/08) .exe link here About : Visual Studio Code에서 C/C++환경을 MinGW GCC/G

Junho Yoon 2 Dec 19, 2021
Show my read on kindle this year

Show my kindle status on GitHub

yihong 26 Jun 20, 2022
Bitflip Fault Simulation Platform by Daniele Rizzieri (2021)

BFSP [v1.05] Bitflip Fault Simulation Platform by Daniele Rizzieri (2021) The platform injects a random bitflip in each of N copies of a binary file.

Daniele Rizzieri 2 Nov 05, 2022
Job Guy Backend

جاب‌گای چیست؟ اونجا وضعیت چطوریه؟ یه سوال به همین کلیت و ابهام معمولا وقتی برای یه شرکت رزومه می‌فرستیم این سوال کلی و بزرگ برای همه پیش میاد.اونجا وض

Jobguy.work 217 Dec 25, 2022