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

Almost State-of-the-art Text Generation library

Ps: we are adding transformer model soon Text Gen 🐐 Almost State-of-the-art Text Generation library Text gen is a python library that allow you build

63 Jun 24, 2022

Neural network sequence labeling model

Sequence labeler This is a neural network sequence labeling system. Given a sequence of tokens, it will learn to assign labels to each token. Can be u

250 Nov 03, 2022

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

Samantha, A covid-19 information bot which will provide basic information about this pandemic in form of conversation.

Covid-19-BOT Samantha, A covid-19 information bot which will provide basic information about this pandemic in form of conversation. This bot uses torc

2 Nov 05, 2021

Basic yet complete Machine Learning pipeline for NLP tasks

Basic yet complete Machine Learning pipeline for NLP tasks This repository accompanies the article on building basic yet complete ML pipelines for sol

20 Aug 22, 2022

The official implementation of VAENAR-TTS, a VAE based non-autoregressive TTS model.

VAENAR-TTS This repo contains code accompanying the paper "VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis". Sa

138 Oct 28, 2022

Wikipedia-Utils: Preprocessing Wikipedia Texts for NLP

Wikipedia-Utils: Preprocessing Wikipedia Texts for NLP This repository maintains some utility scripts for retrieving and preprocessing Wikipedia text

44 Oct 19, 2022

Local cross-platform machine translation GUI, based on CTranslate2

DesktopTranslator Local cross-platform machine translation GUI, based on CTranslate2 Download Windows Installer You can either download a ready-made W

29 Jan 05, 2023

Code for text augmentation method leveraging large-scale language models

HyperMix Code for our paper GPT3Mix and conducting classification experiments using GPT-3 prompt-based data augmentation. Getting Started Installing P

47 Dec 20, 2022

TPlinker for NER 中文/英文命名实体识别

本项目是参考 TPLinker 中HandshakingTagging思想，将TPLinker由原来的关系抽取(RE)模型修改为命名实体识别(NER)模型。

113 Dec 28, 2022

Predicting the usefulness of reviews given the review text and metadata surrounding the reviews.

Predicting Yelp Review Quality Table of Contents Introduction Motivation Goal and Central Questions The Data Data Storage and ETL EDA Data Pipeline Da

3 Nov 27, 2022

Gpt2-WebAPI - The objective of this API is to provide the 3 best possible responses to sentences that the user would input via http GET request as a parameter

This repository is a modification of: https://github.com/openai/gpt-2 for our sp

1 Jan 06, 2022

Automatically search Stack Overflow for the command you want to run

stackshell Automatically search Stack Overflow (and other Stack Exchange sites) for the command you want to ru Use the up and down arrows to change be

22 Oct 27, 2021

BPEmb is a collection of pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) and trained on Wikipedia.

BPEmb is a collection of pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) and trained on Wikipedia. Its intended use is as input for neural models in natural languag

1.1k Jan 03, 2023