p-tuning_NLU

Overview

这个小项目是受乐于分享的苏剑林大佬这篇p-tuning 文章启发，也实现了个使用P-tuning进行NLU分类的任务，思路是一样的，prompt实现方式有不同，这里是将[unused*]的embeddings参数抽取出用于初始化prompt_embed后，再接一个lstm和mlp用于关联各prompt，与最初p-tuning提出《GPT Understands, Too》的实现一样，结果显示在few-shot上p-tuning非常接近finetune效果。

Dataset

数据是情感分类，下载地址百度网盘提取码：osja

Evaluation

1. finetune

python few_shot_finetune.py

测试集效果：

epoch: 0 - acc: 0.897679 - best_test_acc: 0.8976788252013264
epoch: 1 - acc: 0.876362 - best_test_acc: 0.8976788252013264
epoch: 2 - acc: 0.884889 - best_test_acc: 0.8976788252013264
epoch: 3 - acc: 0.884415 - best_test_acc: 0.8976788252013264
epoch: 4 - acc: 0.884415 - best_test_acc: 0.8976788252013264

全量参数对小样本进行finetune，仅1个epoch就收敛了

2. p-tuning

python few_shot_ptuning.py

测试集效果：

epoch: 0 - acc: 0.546660 - best_test_acc: 0.5466603505447655
epoch: 1 - acc: 0.687826 - best_test_acc: 0.6878256750355282
epoch: 2 - acc: 0.737091 - best_test_acc: 0.7370914258645191
epoch: 3 - acc: 0.722406 - best_test_acc: 0.7370914258645191
epoch: 4 - acc: 0.776883 - best_test_acc: 0.7768829938417812
epoch: 5 - acc: 0.805306 - best_test_acc: 0.8053055423969683
epoch: 6 - acc: 0.833254 - best_test_acc: 0.8332543818095689
epoch: 7 - acc: 0.837991 - best_test_acc: 0.8379914732354334
epoch: 8 - acc: 0.854571 - best_test_acc: 0.8545712932259593
epoch: 9 - acc: 0.858361 - best_test_acc: 0.8583609663666508
epoch: 10 - acc: 0.856466 - best_test_acc: 0.8583609663666508
epoch: 11 - acc: 0.853150 - best_test_acc: 0.8583609663666508
epoch: 12 - acc: 0.868783 - best_test_acc: 0.8687825675035529
epoch: 13 - acc: 0.877309 - best_test_acc: 0.877309332070109
epoch: 14 - acc: 0.873993 - best_test_acc: 0.877309332070109
epoch: 15 - acc: 0.877783 - best_test_acc: 0.8777830412126955
epoch: 16 - acc: 0.882994 - best_test_acc: 0.8829938417811464
epoch: 17 - acc: 0.881573 - best_test_acc: 0.8829938417811464
epoch: 18 - acc: 0.889626 - best_test_acc: 0.8896257697773567
epoch: 19 - acc: 0.877783 - best_test_acc: 0.8896257697773567

仅prompt_embed和lstm及mlp去做p-tuning，20个epoch后接近收敛，acc=0.8896，略小于finetun的acc 0.8977

附上苏神结果对比：

p-tuning for few-shot NLU task

Related tags

Overview

p-tuning_NLU

Overview

Dataset

Evaluation

Owner

多语言降噪预训练模型MBart的中文生成任务

Semantic search for quotes.

Meta learning algorithms to train cross-lingual NLI (multi-task) models

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

:P Some basic stuff I'm gonna use for my upcoming Agile Software Development and Devops

DeepPavlov Tutorials

API for the GPT-J language model 🦜. Including a FastAPI backend and a streamlit frontend

Repo for Enhanced Seq2Seq Autoencoder via Contrastive Learning for Abstractive Text Summarization

Web mining module for Python, with tools for scraping, natural language processing, machine learning, network analysis and visualization.

Korean extractive summarization. 2021 AI 텍스트 요약 온라인 해커톤 화성갈끄니까팀 코드

RoNER is a Named Entity Recognition model based on a pre-trained BERT transformer model trained on RONECv2

ByT5: Towards a token-free future with pre-trained byte-to-byte models

Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration

NLTK Source

Programme de chiffrement et de déchiffrement inverse d'un message en python3.

🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

Pre-Training with Whole Word Masking for Chinese BERT

List of GSoC organisations with number of times they have been selected.

This repository structures data in title, summary, tags, sentiment given a fragment of a conversation

Implementation for paper BLEU: a Method for Automatic Evaluation of Machine Translation