“英特尔创新大师杯”深度学习挑战赛 赛道3:CCKS2021中文NLP地址相关性任务

Overview

ccks2021-track3

CCKS2021中文NLP地址相关性任务-赛道三-冠军方案

团队:我的加菲鱼- wodejiafeiyu

初赛第二/复赛第一/决赛第一

前言

19年开始,陆陆续续参加了一些比赛,拿到过一些top,比较懒一直都没分享过,这次比较幸运又拿了top1,打算分享下

分类的任务用这个框架基本都能top10,之前个人参加的《全球人工智能大赛-赛道一》和这个也差不多,只是有些具体任务的trick不同

比赛主页

https://tianchi.aliyun.com/competition/entrance/531901/introduction

环境

  • torch==1.6.0
  • transformers=3.0.2

预训练模型

- nezha-base 
- nezha-wwm
- macbert
  • 下载预训练模型,放到文件夹user_data/model_param/pretrain_model_param/下,文件夹和模型名字一一对应

全流程脚本

sh run.sh

核心思路

  • 预训练mlm中的mask策略使用ngram-mask,相比原始的动态mask,提升了预训练难度
  • 标签也包含语义信息,预训练部分融入标签信息,提升预训练效果
  • 混合精度预训练,损失一部分精度,提升整体的训练速度,实际测试结果精度损失不大,速度提升明显
  • 对抗训练,已经是一个比较常用的trick了
  • 后12层加上embedding的cls动态加权平均
  • multi-sample dropout
  • 推理的时候,阈值搜索
  • 三折交叉验证,每折使用不同的随机数种子使用dynamic pad
  • 加权平均,模型融合

总结

模块 提分点分析 提升
ngram-mask 相比于单个字的遮蔽,ngram-mask加大了预训练任务的难度,从而提升效果 2.6个千分点
融入标签信息预训练 标签也含有语义信息,模型学习的更多 1个千分点
后12层加上embedding的cls动态加权平均+multi-sample dropout 加权平均能增强向量的语义表征能力从而提升效果。multi-sample dropout能加速训练,增强泛化能力 3.3个千分点
对抗训练fgm 生成对抗样本,对抗样本的训练,增加模型泛化能力 2.2个千分点
多分类阈值搜索 缩放系数使得f1最优 0.7个千分点
模型融合 提升模型的鲁棒性和泛化能力 1.5个千分点
动态pad和预训练混合精度训练和每折使用不同的随机数种子 提升模型训练速度,不同的随机数种子加大了模型的差异,提升融合的效果
Owner
shaochenjie
shaochenjie
Provided is code that demonstrates the training and evaluation of the work presented in the paper: "On the Detection of Digital Face Manipulation" published in CVPR 2020.

FFD Source Code Provided is code that demonstrates the training and evaluation of the work presented in the paper: "On the Detection of Digital Face M

88 Nov 22, 2022
BRepNet: A topological message passing system for solid models

BRepNet: A topological message passing system for solid models This repository contains the an implementation of BRepNet: A topological message passin

Autodesk AI Lab 42 Dec 30, 2022
PyTorch META-DATASET (Few-shot classification benchmark)

PyTorch META-DATASET (Few-shot classification benchmark) This repo contains a PyTorch implementation of meta-dataset and a unified implementation of s

Malik Boudiaf 39 Oct 31, 2022
SHIFT15M: multiobjective large-scale fashion dataset with distributional shifts

[arXiv] The main motivation of the SHIFT15M project is to provide a dataset that contains natural dataset shifts collected from a web service IQON, wh

ZOZO, Inc. 138 Nov 24, 2022
The aim of the game, as in the original one, is to find a specific image from a group of different images of a person's face

GUESS WHO Main Links: [Github] [App] Related Links: [CLIP] [Celeba] The aim of the game, as in the original one, is to find a specific image from a gr

Arnau - DIMAI 3 Jan 04, 2022
A font family with a great monospaced variant for programmers.

Fantasque Sans Mono A programming font, designed with functionality in mind, and with some wibbly-wobbly handwriting-like fuzziness that makes it unas

Jany Belluz 6.3k Jan 08, 2023
Trains an agent with stochastic policy gradient ascent to solve the Lunar Lander challenge from OpenAI

Introduction This script trains an agent with stochastic policy gradient ascent to solve the Lunar Lander challenge from OpenAI. In order to run this

Momin Haider 0 Jan 02, 2022
🥇Samsung AI Challenge 2021 1등 솔루션입니다🥇

MoT - Molecular Transformer Large-scale Pretraining for Molecular Property Prediction Samsung AI Challenge for Scientific Discovery This repository is

Jungwoo Park 44 Dec 03, 2022
Codes for Causal Semantic Generative model (CSG), the model proposed in "Learning Causal Semantic Representation for Out-of-Distribution Prediction" (NeurIPS-21)

Learning Causal Semantic Representation for Out-of-Distribution Prediction This repository is the official implementation of "Learning Causal Semantic

Chang Liu 54 Dec 01, 2022
This demo showcase the use of onnxruntime-rs with a GPU on CUDA 11 to run Bert in a data pipeline with Rust.

Demo BERT ONNX pipeline written in rust This demo showcase the use of onnxruntime-rs with a GPU on CUDA 11 to run Bert in a data pipeline with Rust. R

Xavier Tao 14 Dec 17, 2022
A nutritional label for food for thought.

Lexiscore As a first effort in tackling the theme of information overload in content consumption, I've been working on the lexiscore: a nutritional la

Paul Bricman 34 Nov 08, 2022
Simple converter for deploying Stable-Baselines3 model to TFLite and/or Coral

Running SB3 developed agents on TFLite or Coral Introduction I've been using Stable-Baselines3 to train agents against some custom Gyms, some of which

Gary Briggs 16 Oct 11, 2022
Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR

Official implementation for paper "Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR"

Ziyue Feng 72 Dec 09, 2022
Perfect implement. Model shared. x0.5 (Top1:60.646) and 1.0x (Top1:69.402).

Shufflenet-v2-Pytorch Introduction This is a Pytorch implementation of faceplusplus's ShuffleNet-v2. For details, please read the following papers:

423 Dec 07, 2022
Repository for "Space-Time Correspondence as a Contrastive Random Walk" (NeurIPS 2020)

Space-Time Correspondence as a Contrastive Random Walk This is the repository for Space-Time Correspondence as a Contrastive Random Walk, published at

A. Jabri 239 Dec 27, 2022
Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift (ICCV 2021)

Π-NAS This repository provides the evaluation code of our submitted paper: Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training

Jiqi Zhang 18 Aug 18, 2022
[ICML 2021] Break-It-Fix-It: Learning to Repair Programs from Unlabeled Data

Break-It-Fix-It: Learning to Repair Programs from Unlabeled Data This repo provides the source code & data of our paper: Break-It-Fix-It: Unsupervised

Michihiro Yasunaga 86 Nov 30, 2022
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services

Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning

MaCan 4.2k Dec 29, 2022
Dynamic vae - Dynamic VAE algorithm is used for anomaly detection of battery data

Dynamic VAE frame Automatic feature extraction can be achieved by probability di

10 Oct 07, 2022
A TikTok-like recommender system for GitHub repositories based on Gorse

GitRec GitRec is the missing recommender system for GitHub repositories based on Gorse. Architecture The trending crawler crawls trending repositories

337 Jan 04, 2023