• Stars
    star
    110
  • Rank 316,770 (Top 7 %)
  • Language
    Python
  • Created over 4 years ago
  • Updated about 4 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Semantic search using Transformers and others

Semantic Search using sentence embeddings from Transformers models and others

Simple application using sentece embedding to project the documents in a high dimensional space and find most similarities using cosine similarity.

The purpose is to demo and compare the models. To deploy in scale, it is necessary to compute and save the document embeddings to quickly search and compute similarities.

The first load take a long time since the application will download all the models. Beside 6 models running, inference time is acceptable even in CPU.

Application

The demo text has 4 sentences about each topic: Apple, Operating Systems, Java and Python.

It is possible to see the semantic search works well filtering out only documents about the specific query, even tought the query doesn't have the exaclty words in documents.

The Raw BERT performs poorly (as expected)

Searching for Apple

Query about apple

Searching for OS

Query about OS

Searching for Java

Query about Java

Searching for Python

Query about Python

Running

It is necessary to download the Infersent model 1 and glove.840B.300d.txt.

Download and put the files in the infersent_files in each respective folders.

python app.py

Open your browser http://localhost:8000

More Repositories

1

next_word_prediction

Using transformers to predict next word and predict <mask> word
Python
725
star
2

Question-Answering-Albert-Electra

Question Answering using Albert and Electra
Python
205
star
3

Bart_T5-summarization

Summarization Task using Bart and T5 models.
HTML
168
star
4

bg-remove-augment

Python
156
star
5

Multiple-Choice-Question-Generation-T5-and-Text2Text

Question Generation using Google T5 and Text2Text
Python
153
star
6

T5-paraphrase-generation

HTML
67
star
7

BERT-cpp-inference

Makefile
52
star
8

GAN-image-inpainting

Deep Learning technics to image inptaining
Python
30
star
9

Deploying-YOLOv5-fastapi-celery-redis-rabbitmq

Python
29
star
10

Switch-Transformers-in-Seq2Seq

Python
22
star
11

go-hexagonal-shortener

Go
12
star
12

Deploying-Deep-Learning-Models-in-C-A-comparison-with-Python-server

Makefile
9
star
13

autograde-deeplearning

This projects aims to implement a auto-grade assistant capable to give a score of "correctness" between a provided answer and a target answer.
HTML
7
star
14

electra-squad-8GB

Fine tuning Electra large model using RTX2080 8 GB on Squad 2 dataset
Python
7
star
15

webapp-StyleGAN2-ADA-PyTorch

Python
6
star
16

deep-reinforcement-learning

Python
6
star
17

sync_async_await_multiprocess_multithread

Python
4
star
18

django_auth_face_recognition

Django web app using face recognition to auth user.
JavaScript
4
star
19

flickr-downloader

Python
3
star
20

bert-nq-python3

Bert-NQ - Google Bert for Natural Question adjusted for Python 3
Python
3
star
21

object_segmentation

Object segmentation using SOTA models
Python
3
star
22

bert_sentiment_flask

Using flask API to predict the sentiment using BERT model
Python
2
star
23

Patches-are-all-you-need-ViT-and-ConvMixer

Python
2
star
24

go-node-python

Go
2
star
25

qa-electra-predict

Predicting with electra model fine tuned in squad 2.0
Python
1
star
26

machine_learning

Exemplos para a disciplina
Python
1
star
27

criptografia

Exemplo de criptografia
HTML
1
star
28

RL-Soft-Actor-Critic_Pytorch

Python
1
star
29

Types-of-Convolution-PyTorch

Python
1
star
30

siamese-neural-net-pytorch

Jupyter Notebook
1
star
31

golang-whatsapp-broker

Whatsapp Broker written in Go
Go
1
star