使用pytorch+transformers复现了SimCSE论文中的有监督训练和无监督训练方法

Related tags

Text Data & NLPSimCSE
Overview

SimCSE复现

项目描述

SimCSE是一种简单但是很巧妙的NLP对比学习方法,创新性地引入Dropout的方式,对样本添加噪声,从而达到对正样本增强的目的。 该框架的训练目的为:对于batch中的每个样本,拉近其与正样本之间的距离,拉远其与负样本之间的距离,使得模型能够在大规模无监督语料(也可以使用有监督的语料)中学习到文本相似关系。 详见论文:Simple Contrastive Learning of Sentence EmbeddingsSimCSE官方代码仓库

本项目使用pytorch+transformers复现了SimCSE论文中的有监督训练和无监督训练方法,并且在STS-B数据集上进行消融实验,评价指标为Spearman相关系数,预训练模型为Bert-base-uncased, 验证了SimCSE的有效性。在STS-B数据集上,有监督训练和无监督训练的复现效果如下表。

在无监督训练中,dropout=0.1时,复现效果比原文略差,但也比较接近。当dropout=0.2时,复现效果比原文略高。 ** 但在有监督训练中,不知是否由于batch size过小(原论文使用512),复现效果与论文的效果相差较远,后续会进行排查。 **

训练方法 learning rate batch size dropout Spearman’s correlation
原论文 无监督 3e-5 64 0.1 0.763
复现 无监督 3e-5 64 0.2 0.771
复现 无监督 3e-5 64 0.1 0.748
原论文 有监督 5e-5 512 0.1 0.816
复现 有监督 5e-5 64 0.1 0.764

运行环境

python==3.6、transformers==3.1.0、torch==1.6.0

项目结构

  • data:存放训练数据
    • stsbenchmark:STS-B数据集
      • sts-dev.csv:STS-B验证集
      • sts-test.csv:STS-B验测试集
    • nli_for_simcse.csv:数量275601为的NLI数据集
    • wiki1m_for_simcse.txt:维基百科上获取的100w的文本
  • output:输出目录
  • pretrain_model:预训练模型存放位置
  • script:脚本存放位置。
  • dataset.py
  • model.py:模型代码,包含有监督和无监督损失函数的计算方式
  • train.py:训练代码

使用方法

Quick Start

下载训练数据:

bash script/download_nli.sh
bash script/download_wiki.sh

无监督训练,运行脚本

bash script/run_unsup_train.sh

有监督训练,运行脚本

bash script/run_sup_train.sh

实验

无监督训练

从前四条实验数据中可以看到,较大的batch size在一定程度上可以增加模型的泛化性。

dropout为0.2的时候,训练效果比0.1与0.3更好,有可能dropout=0.1加入的噪声过小,而dropout=0.3加入的噪声过大,增强得到的样本与原始样本差异较大。

learning rate batch size dropout 在哪一步得到best checkpoint 验证集上的得分 测试集上的得分
3e-5 256 0.1 6000 0.800 0.761
3e-5 128 0.1 4200 0.799 0.747
3e-5 64 0.1 10900 0.803 0.748
3e-5 32 0.1 21300 0.787 0.714
3e-5 64 0.2 11200 0.811 0.771
3e-5 64 0.3 6300 0.781 0.745
1e-5 64 0.1 16400 0.798 0.751

有监督训练

有监督实验的复现结果未达到预期,超参数相同时,在验证集上的得分略高于无监督,但是在测试集上,得分基本没有差异。增大有监督训练的学习率,有监督的训练的得分略高于无监督训练, 但还是与论文声称的0.816相差较远,原论文使用512的batch size, 不知是否由于batch size的设置有关,后续会对有监督的训练代码进一步排查。

不过从训练曲线可以看到,有监督训练的收敛速度明显快于无监督训练,这也符合我们的认知。

训练方法 learning rate batch size dropout 在哪一步得到best checkpoint 验证集上的得分 测试集上的得分
无监督 3e-5 64 0.1 10900 0.803 0.748
有监督 3e-5 64 0.1 200 0.810 0.748
有监督 5e-5 64 0.1 2300 0.809 0.764
有监督 3e-5 32 0.1 200 0.808 0.743
有监督 5e-5 32 0.1 200 0.806 0.746

无监督训练过程中,验证集得分的变化曲线: avatar

有监督训练过程中,验证集得分的变化曲线: avatar

REFERENCE

TODO

  • 排查有监督学习的效果不符合预期的原因
Fidibo.com comments Sentiment Analyser

Fidibo.com comments Sentiment Analyser Introduction This project first asynchronously grab Fidibo.com books comment data using grabber.py and then sav

Iman Kermani 3 Apr 15, 2022
Write Python in Urdu - اردو میں کوڈ لکھیں

UrduPython Write simple Python in Urdu. How to Use Write Urdu code in سامپل۔پے The mappings are as following: "۔": ".", "،":

Saad A. Bazaz 26 Nov 27, 2022
GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training Code and model from our AAAI 2021 paper

Amazon Web Services - Labs 83 Jan 09, 2023
Shirt Bot is a discord bot which uses GPT-3 to generate text

SHIRT BOT · Shirt Bot is a discord bot which uses GPT-3 to generate text. Made by Cyclcrclicly#3420 (474183744685604865) on Discord. Support Server EX

31 Oct 31, 2022
A list of NLP(Natural Language Processing) tutorials built on Tensorflow 2.0.

A list of NLP(Natural Language Processing) tutorials built on Tensorflow 2.0.

Won Joon Yoo 335 Jan 04, 2023
CoSENT 比Sentence-BERT更有效的句向量方案

CoSENT 比Sentence-BERT更有效的句向量方案

苏剑林(Jianlin Su) 201 Dec 12, 2022
A demo of chinese asr

chinese_asr_demo 一个端到端的中文语音识别模型训练、测试框架 具备数据预处理、模型训练、解码、计算wer等等功能 训练数据 训练数据采用thchs_30,

4 Dec 09, 2021
**NSFW** A chatbot based on GPT2-chitchat

DangBot -- 好怪哦,再来一句 卡群怪话bot,powered by GPT2 for Chinese chitchat Training Example: python train.py --lr 5e-2 --epochs 30 --max_len 300 --batch_size 8

Tommy Yang 11 Jul 21, 2022
Contains analysis of trends from Fitbit Dataset (source: Kaggle) to see how the trends can be applied to Bellabeat customers and Bellabeat products

Contains analysis of trends from Fitbit Dataset (source: Kaggle) to see how the trends can be applied to Bellabeat customers and Bellabeat products.

Leah Pathan Khan 2 Jan 12, 2022
ACL22 paper: Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost

Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost LOVE is accpeted by ACL22 main conference as a long pape

Lihu Chen 32 Jan 03, 2023
Mlcode - Continuous ML API Integrations

mlcode Basic APIs for ML applications. Django REST Application Contains REST API

Sujith S 1 Jan 01, 2022
Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

Phil Wang 5k Jan 02, 2023
Random-Word-Generator - Generates meaningful words from dictionary with given no. of letters and words.

Random Word Generator Generates meaningful words from dictionary with given no. of letters and words. This might be useful for generating short links

Mohammed Rabil 1 Jan 01, 2022
Free and Open Source Machine Translation API. 100% self-hosted, offline capable and easy to setup.

LibreTranslate Try it online! | API Docs | Community Forum Free and Open Source Machine Translation API, entirely self-hosted. Unlike other APIs, it d

3.4k Dec 27, 2022
One Stop Anomaly Shop: Anomaly detection using two-phase approach: (a) pre-labeling using statistics, Natural Language Processing and static rules; (b) anomaly scoring using supervised and unsupervised machine learning.

One Stop Anomaly Shop (OSAS) Quick start guide Step 1: Get/build the docker image Option 1: Use precompiled image (might not reflect latest changes):

Adobe, Inc. 148 Dec 26, 2022
Baseline code for Korean open domain question answering(ODQA)

Open-Domain Question Answering(ODQA)는 다양한 주제에 대한 문서 집합으로부터 자연어 질의에 대한 답변을 찾아오는 task입니다. 이때 사용자 질의에 답변하기 위해 주어지는 지문이 따로 존재하지 않습니다. 따라서 사전에 구축되어있는 Knowl

VUMBLEB 69 Nov 04, 2022
Open-source offline translation library written in Python. Uses OpenNMT for translations

Open source neural machine translation in Python. Designed to be used either as a Python library or desktop application. Uses OpenNMT for translations and PyQt for GUI.

Argos Open Tech 1.6k Jan 01, 2023
Paradigm Shift in NLP - "Paradigm Shift in Natural Language Processing".

Paradigm Shift in NLP Welcome to the webpage for "Paradigm Shift in Natural Language Processing". Some resources of the paper are constantly maintaine

Tianxiang Sun 41 Dec 30, 2022
NLTK Source

Natural Language Toolkit (NLTK) NLTK -- the Natural Language Toolkit -- is a suite of open source Python modules, data sets, and tutorials supporting

Natural Language Toolkit 11.4k Jan 04, 2023
The NewSHead dataset is a multi-doc headline dataset used in NHNet for training a headline summarization model.

This repository contains the raw dataset used in NHNet [1] for the task of News Story Headline Generation. The code of data processing and training is available under Tensorflow Models - NHNet.

Google Research Datasets 31 Jul 15, 2022