CoSENT 比Sentence-BERT更有效的句向量方案

Last update: Dec 12, 2022

Related tags

Text Data & NLP CoSENT

Overview

CoSENT

比Sentence-BERT更有效的句向量方案

介绍

博客：https://kexue.fm/archives/8847
数据：https://github.com/bojone/BERT-whitening/tree/main/chn

效果

train训练、test测试：

	ATEC	BQ	LCQMC	PAWSX	STS-B	Avg
BERT+CoSENT	49.74	72.38	78.69	60.00	80.14	68.19
Sentence-BERT	46.36	70.36	78.72	46.86	66.41	61.74
RoBERTa+CoSENT	50.81	71.45	79.31	61.56	81.13	68.85
Sentence-RoBERTa	48.29	69.99	79.22	44.10	72.42	62.80

NLI训练、test测试：

	ATEC	BQ	LCQMC	PAWSX	STS-B	Avg
BERT+CoSENT	28.93	41.84	66.07	20.49	73.91	46.25
Sentence-BERT	28.19	42.73	64.98	15.38	**74.88	45.23
RoBERTa+CoSENT	31.84	46.65	68.43	20.89	74.37	48.43
Sentence-RoBERTa	31.87	45.60	67.89	15.64	73.93	46.99

环境

需要bert4keras >= 0.10.8。个人实验环境是tensorflow 1.15 + keras 2.3.1 + bert4keras 0.10.8。

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

GitHub Repository

Implementation of Multistream Transformers in Pytorch

Multistream Transformers Implementation of Multistream Transformers in Pytorch. This repository deviates slightly from the paper, where instead of usi

47 Jul 26, 2022

Python code for ICLR 2022 spotlight paper EViT: Expediting Vision Transformers via Token Reorganizations

Expediting Vision Transformers via Token Reorganizations This repository contain

101 Dec 26, 2022

Let Xiao Ai speakers control third-party devices

A stupid way to extend miot/xiaoai. Demo for Panasonic Bath Bully FV-RB20VL1 逆向 Panasonic Smart China，获得控制浴霸的请求信息（HTTP 请求），详见 apps/panasonic.py； 2. 通过

14 Jul 07, 2022

Jupyter Notebook tutorials on solving real-world problems with Machine Learning & Deep Learning using PyTorch

Jupyter Notebook tutorials on solving real-world problems with Machine Learning & Deep Learning using PyTorch. Topics: Face detection with Detectron 2, Time Series anomaly detection with LSTM Autoenc

1.8k Dec 31, 2022

Ceaser-Cipher - The Caesar Cipher technique is one of the earliest and simplest method of encryption technique

Ceaser-Cipher The Caesar Cipher technique is one of the earliest and simplest me

2 May 12, 2022

skweak: A software toolkit for weak supervision applied to NLP tasks

Labelled data remains a scarce resource in many practical NLP scenarios. This is especially the case when working with resource-poor languages (or text domains), or when using task-specific labels wi

850 Dec 28, 2022

Data preprocessing rosetta parser for python

datapreprocessing_rosetta_parser I've never done any NLP or text data processing before, so I wanted to use this hackathon as a learning opportunity,

2 Nov 28, 2021

Code release for "COTR: Correspondence Transformer for Matching Across Images"

COTR: Correspondence Transformer for Matching Across Images This repository contains the inference code for COTR. We plan to release the training code

358 Dec 24, 2022

KoBERT - Korean BERT pre-trained cased (KoBERT)

KoBERT KoBERT Korean BERT pre-trained cased (KoBERT) Why'?' Training Environment Requirements How to install How to use Using with PyTorch Using with

1k Jan 02, 2023

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

Understand-conversation-AI This repository structures data in title, summary, tags, sentiment given a fragment of a conversation How to install: pip i

1 Jan 11, 2022

customer care chatbot made with Rasa Open Source.

Customer Care Bot Customer care bot for ecomm company which can solve faq and chitchat with users, can contact directly to team. 🛠 Features Basic E-c

23 Oct 27, 2022

A simple recipe for training and inferencing Transformer architecture for Multi-Task Learning on custom datasets. You can find two approaches for achieving this in this repo.

multitask-learning-transformers A simple recipe for training and inferencing Transformer architecture for Multi-Task Learning on custom datasets. You

48 Jan 02, 2023

CoSENT 比Sentence-BERT更有效的句向量方案

Related tags

Overview

CoSENT

介绍

效果

环境

交流

Owner

苏剑林(Jianlin Su)

Implementation of Multistream Transformers in Pytorch

Python code for ICLR 2022 spotlight paper EViT: Expediting Vision Transformers via Token Reorganizations

Let Xiao Ai speakers control third-party devices

Jupyter Notebook tutorials on solving real-world problems with Machine Learning & Deep Learning using PyTorch

Ceaser-Cipher - The Caesar Cipher technique is one of the earliest and simplest method of encryption technique

skweak: A software toolkit for weak supervision applied to NLP tasks

Data preprocessing rosetta parser for python

Code release for "COTR: Correspondence Transformer for Matching Across Images"

KoBERT - Korean BERT pre-trained cased (KoBERT)

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

customer care chatbot made with Rasa Open Source.

A simple recipe for training and inferencing Transformer architecture for Multi-Task Learning on custom datasets. You can find two approaches for achieving this in this repo.

Extract Keywords from sentence or Replace keywords in sentences.

The training code for the 4th place model at MDX 2021 leaderboard A.

Rank-One Model Editing for Locating and Editing Factual Knowledge in GPT

Rootski - Full codebase for rootski.io (without the data)

jel - Japanese Entity Linker - is Bi-encoder based entity linker for japanese.

Multiple implementations for abstractive text summurization , using google colab

nlp基础任务

Learning Spatio-Temporal Transformer for Visual Tracking