There are 5 repositories under universal-sentence-encoder topic.
a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)
Document similarity algorithms experiment - Jaccard, TF-IDF, Doc2vec, USE, and BERT.
Open Source Text Embedding Models with OpenAI Compatible API
REST API for sentence tokenization and embedding using Multilingual Universal Sentence Encoder.
Document Search Engine project with TF-IDF abd Google universal sentence encoder model
All about Neural Networks!
Summarizer in python with Spacy and Universal Sentence Encoder build on Flask framework
Code for replicating results of team 'hateminers' at EVALITA-2018 for AMI task
Persian word embedding ( نشاننده واژه ها فارسی | تعبیه سازی کلمات فارسی )
Creating an automatic answer checker web application for students and teachers, for grading of the answers submitted by students against an ideal solution uploaded by the teacher.
Language independent sentiment analysis
Combined semantic similarity search based visual search engine.
Fine-grained Propaganda Detection at NLP4IF 2019
Full example of semantic search system
Next Word Prediction using Google's Universal Sentence Encoder from Tensorflow hub. lol
It is well-known that stock price movements are highly sensitive to different types of news, including global events such as outbreaks of epidemics or military conflicts, as well as what people post about specific companies on their social networks. Previous research has studied methods to predict stock price movements based on sentiment analysis of business news and social media posts of a particular company alongside its historical stock price data. In contrast, this project will also implement a new state of the art algorithm recently developed by the Google Research team called Universal Sentence Encoder, which is able to encode input text, implementing sentence level embeddings, into high dimensional vectors that will be used as predictors of future stock price movements. According to that, both the Sentient Analysis and the Universal Sentence Encoder will be performed and the outputs will be used as an exogenous variable in machine learning models which will be then compared with each other to find the best model with the aim of achieving a higher model accuracy, better performance and a more robust model than only using either the historical stock price data ad endogenous variable or implementing other natural language processing methodologies based on word embeddings.
Wagtail Django Website with PostreSQL Database Focused on Providing a Central Hub of Educational Resources to the MJC Student Body
Determining similarity between two sentences in terms of semantic using pre trained Universal Sentence Encoder from TensorFlow.js
Use-cases of Google's Universal Sentence Encoder (e.g. sentence similarity, unsupervised extractive summarization).
Semantic Textual Similarity between two document
Using Random Forest , Bi Direction LSTM and Tensorflow Transfer Learning to do a text classification project. Compare model differences between tokenization and word embedding.
Predicting product recommendation score using the data available on the website of the client
Evaluates a client-side model built on top of the Universal Sentence Encoder to detect hateful content selected for the analysis
A Natural Language Processing (NLP) model with TensorFlow to segment text lines of abstracts from medical research papers in order to improve readability.
Shack Labs Assignments: 1. House Price Prediction 2. Product Matching
Using Neural Representations for Generating Intent-based Query Phrases
This repository contains a simple code to compare two sentences based on their semantic similarity scores using a Universal sentence encoder.
Implementing Text Similarity for US Patents using modern day Word2Vec and USE(Universal Sentence Encoding) and some classical algos. like Jaro Winkler and Jaccard
comment analysis experiment
This code provides an implementation of clustering text data using the Universal Sentence Encoder (USE) and the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. You can provide a list of queries (sentences or words) and it will cluster them for your SEO needs (or other use cases).
Experiments in the field of Semantic Search using BM-25 Algorithm, Mean of Word Vectors, along with state of the art Transformer based models namely USE and SBERT.