Cải thiện Elasticsearch trong bài toán semantic search sử dụng phương pháp Sentence Embeddings

Last update: Nov 25, 2022

Related tags

Overview

Cải thiện Elasticsearch trong bài toán semantic search sử dụng phương pháp Sentence Embeddings

Trong bài viết này mình sẽ sử dụng pretrain model SimCSE_Vietnamese để cải thiện elastic search trong bài toán semantic search.

Mọi người có thể xem bài viết hướng dẫn đầy đủ tại đây.

Cài đặt:

git clone https://github.com/vovanphuc/elastic_simCSE.git
cd elastic_simCSE
pip install -r requirements.txt

Đánh index cho toàn bộ data

python3 index_elastic.py

Search keyword và so sánh giữa BM25 (elasticsearch thường) và simCSE:

streamlit run main.py

Kết quả tìm kiếm:

Kết quả khi sử dụng elasticsearch bình thường.

Kết quả khi sử dụng SimCSE_VietNamese.

Contact:

Email: [email protected]

Facebook: facebook.com/vovanphucc

Linkedin: linkedin.com/in/vovanphuc

Owner

Vo Van Phuc

KEEP IT SIMPLE STUPID!

GitHub Repository

🕹 An esoteric language designed so that the program looks like the transcript of a Pokémon battle

PokéBattle is an esoteric language designed so that the program looks like the transcript of a Pokémon battle. Original inspiration and specification

9 Jan 11, 2022

Utilities for preprocessing text for deep learning with Keras

Note: This utility is really old and is no longer maintained. You should use keras.layers.TextVectorization instead of this. Utilities for pre-process

180 Dec 09, 2022

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

English | 中文 Features 🌍 Chinese supported mandarin and tested with multiple datasets: aidatatang_200zh, magicdata, aishell3, data_aishell, and etc. ?

25.6k Dec 31, 2022

T‘rex Park is a Youzan sponsored project. Offering Chinese NLP and image models pretrained from E-commerce datasets

T‘rex Park is a Youzan sponsored project. Offering Chinese NLP and image models pretrained from E-commerce datasets (product titles, images, comments, etc.).

55 Nov 22, 2022

GPT-Code-Clippy (GPT-CC) is an open source version of GitHub Copilot, a language model

GPT-Code-Clippy (GPT-CC) is an open source version of GitHub Copilot, a language model -- based on GPT-3, called GPT-Codex -- that is fine-tuned on publicly available code from GitHub.

2.3k Jan 01, 2023

A high-level yet extensible library for fast language model tuning via automatic prompt search

ruPrompts ruPrompts is a high-level yet extensible library for fast language model tuning via automatic prompt search, featuring integration with Hugg

37 Dec 07, 2022

NLP made easy

GluonNLP: Your Choice of Deep Learning for NLP GluonNLP is a toolkit that helps you solve NLP problems. It provides easy-to-use tools that helps you l

2.5k Jan 04, 2023

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

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis Jungil Kong, Jaehyeon Kim, Jaekyoung Bae In our paper, we p

1.1k Jan 02, 2023

PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models

Deepvoice3_pytorch PyTorch implementation of convolutional networks-based text-to-speech synthesis models: arXiv:1710.07654: Deep Voice 3: Scaling Tex

1.8k Dec 30, 2022

Snips Python library to extract meaning from text

Snips NLU Snips NLU (Natural Language Understanding) is a Python library that allows to extract structured information from sentences written in natur

3.7k Dec 30, 2022

Telegram AI chat bot written in Python using Pyrogram

Aurora_Al Just another Telegram AI chat bot written in Python using Pyrogram. A public running instance can be found on telegram as @AuroraAl. Require

1 Oct 31, 2021

Google and Stanford University released a new pre-trained model called ELECTRA

Google and Stanford University released a new pre-trained model called ELECTRA, which has a much compact model size and relatively competitive performance compared to BERT and its variants. For furth

1.2k Dec 30, 2022

Concept Modeling: Topic Modeling on Images and Text

Concept is a technique that leverages CLIP and BERTopic-based techniques to perform Concept Modeling on images.

120 Dec 27, 2022

Natural Language Processing

NLP Natural Language Processing apps Multilingual_NLP.py start #This script is demonstartion of Mul

1 Oct 31, 2021

Deduplication is the task to combine different representations of the same real world entity.

Deduplication is the task to combine different representations of the same real world entity. This package implements deduplication using active learning. Active learning allows for rapid training wi

63 Nov 17, 2022

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

NLP-based analysis of poor Chinese movie reviews on Douban

douban_embedding 豆瓣中文影评差评分析 1. NLP NLP（Natural Language Processing）是指自然语言处理，他的目的是让计算机可以听懂人话。下面是我将2万条豆瓣影评训练之后，随意输入一段新影评交给神经网络，最终AI推断出的结果。 "很好，演技不错

3 Apr 15, 2022

RuCLIP-SB (Russian Contrastive Language–Image Pretraining SWIN-BERT) is a multimodal model for obtaining images and text similarities and rearranging captions and pictures. Unlike other versions of the model we use BERT for text encoder and SWIN transformer for image encoder.

ruCLIP-SB RuCLIP-SB (Russian Contrastive Language–Image Pretraining SWIN-BERT) is a multimodal model for obtaining images and text similarities and re

5 Apr 13, 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