Healthsea is a spaCy pipeline for analyzing user reviews of supplementary products for their effects on health.

Overview

Welcome to Healthsea

Create better access to health with spaCy.

Healthsea is a pipeline for analyzing user reviews to supplement products by extracting their effects on health.

Learn more about Healthsea in our blog post!

💉 Creating better access to health

Healthsea aims to analyze user-written reviews of supplements in relation to their effects on health. Based on this analysis, we try to provide product recommendations. For many people, supplements are an addition to maintaining health and achieving personal goals. Due to their rising popularity, consumers have increasing access to a variety of products.

However, it's likely that most of the products on the market are redundant or produced in a "quantity over quality" fashion to maximize profit. The resulting white noise of products makes it hard to find the right supplements.

Healthsea automizes the analysis and provides information in a more digestible way.


🟢 Requirements

To run this project you need:

spacy>=3.2.0
benepar>=0.2.0
torch>=1.6.0
spacy-transformers>=1.1.2

You can install them in the project folder via spacy project run install

📖 Documentation

Documentation
🧭 Usage How to use the pipeline
⚙️ Pipeline Learn more about the architecture of the pipeline
🪐 spaCy project Introduction to the spaCy project
Demos Introduction to the Healthsea demos

🧭 Usage

The pipeline processes reviews to supplements and returns health effects for every found health aspect.

You can either train the pipeline yourself with the provided datasets in the spaCy project or directly download the trained Healthsea pipeline from Huggingface via pip install https://huggingface.co/explosion/en_healthsea/resolve/main/en_healthsea-any-py3-none-any.whl

import spacy

nlp = spacy.load("en_healthsea")
doc = nlp("This is great for joint pain.")

# Clause Segmentation & Blinding
print(doc._.clauses)

>    {"split_indices": [0, 7],
>    "has_ent": true,
>    "ent_indices": [4, 6],
>    "blinder": "_CONDITION_",
>    "ent_name": "joint pain",
>    "cats": {
>        "POSITIVE": 0.9824668169021606,
>        "NEUTRAL": 0.017364952713251114,
>        "NEGATIVE": 0.00002889777533710003,
>        "ANAMNESIS": 0.0001394189748680219
>    },
>    "prediction_text": ["This", "is", "great", "for", "_CONDITION_", "!"]}

# Aggregated results
print(doc._.health_effects)

>    {"joint_pain": {
>        "effects": ["POSITIVE"],
>        "effect": "POSITIVE",
>        "label": "CONDITION",
>        "text": "joint pain"
>    }}


⚙️ Pipeline

The pipeline consists of the following components:

pipeline = [sentencizer, tok2vec, ner, benepar, segmentation, clausecat, aggregation]

It uses Named Entity Recognition to detect two types of entities Condition and Benefit.

Condition entities are defined as health aspects that are improved by decreasing them. They include diseases, symptoms and general health problems (e.g. pain in back). Benefit entities on the other hand, are desired states of health (muscle recovery, glowing skin) that improve by increasing them.

The pipeline uses a modified model that performs Clause Segmentation based on the benepar parser, Entity Blinding and Text Classification. It predicts four exclusive effects: Positive, Negative, Neutral, and Anamnesis.


🪐 spaCy project

The project folder contains a spaCy project with all the training data and workflows.

Use spacy project run inside the project folder to get an overview of all commands and assets. For more detailed documentation, visit the project folders readme.

Use spacy project run install to install dependencies needed for the pipeline.

Demo

Healthsea Demo

A demo for exploring the results of Healthsea on real data can be found at Hugging Face Spaces.

Healthsea Pipeline

A demo for exploring the Healthsea pipeline with its individual processing steps can be found at Hugging Face Spaces.

Owner
Explosion
A software company specializing in developer tools for Artificial Intelligence and Natural Language Processing
Explosion
Stanford CoreNLP provides a set of natural language analysis tools written in Java

Stanford CoreNLP Stanford CoreNLP provides a set of natural language analysis tools written in Java. It can take raw human language text input and giv

Stanford NLP 8.8k Jan 07, 2023
A PyTorch-based model pruning toolkit for pre-trained language models

English | 中文说明 TextPruner是一个为预训练语言模型设计的模型裁剪工具包,通过轻量、快速的裁剪方法对模型进行结构化剪枝,从而实现压缩模型体积、提升模型速度。 其他相关资源: 知识蒸馏工具TextBrewer:https://github.com/airaria/TextBrewe

Ziqing Yang 231 Jan 08, 2023
CPC-big and k-means clustering for zero-resource speech processing

The CPC-big model and k-means checkpoints used in Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing.

Benjamin van Niekerk 5 Nov 23, 2022
An A-SOUL Text Generator Based on CPM-Distill.

ASOUL-Generator-Backend 本项目为 https://asoul.infedg.xyz/ 的后端。 模型为基于 CPM-Distill 的 transformers 转化版本 CPM-Generate-distill 训练而成。

infinityedge 46 Dec 11, 2022
Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System Authors: Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai

Amazon Web Services - Labs 124 Jan 03, 2023
sangha, pronounced "suhng-guh", is a social networking, booking platform where students and teachers can share their practice.

Flask React Project This is the backend for the Flask React project. Getting started Clone this repository (only this branch) git clone https://github

Courtney Newcomer 17 Sep 29, 2021
Some embedding layer implementation using ivy library

ivy-manual-embeddings Some embedding layer implementation using ivy library. Just for fun. It is based on NYCTaxiFare dataset from kaggle (cut down to

Ishtiaq Hussain 2 Feb 10, 2022
Turkish Stop Words Türkçe Dolgu Sözcükleri

trstop Turkish Stop Words Türkçe Dolgu Sözcükleri In this repository I put Turkish stop words that is contained in the first 10 thousand words with th

Ahmet Aksoy 103 Nov 12, 2022
VMD Audio/Text control with natural language

This repository is a proof of principle for performing Molecular Dynamics analysis, in this case with the program VMD, via natural language commands.

Andrew White 13 Jun 09, 2022
Production First and Production Ready End-to-End Keyword Spotting Toolkit

Production First and Production Ready End-to-End Keyword Spotting Toolkit

223 Jan 02, 2023
A toolkit for document-level event extraction, containing some SOTA model implementations

Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker Source code for ACL-IJCNLP 2021 Long paper: Document-le

84 Dec 15, 2022
A simple Flask site that allows users to create, update, and delete posts in a database, as well as perform basic NLP tasks on the posts.

A simple Flask site that allows users to create, update, and delete posts in a database, as well as perform basic NLP tasks on the posts.

Ian 1 Jan 15, 2022
This is the main repository of open-sourced speech technology by Huawei Noah's Ark Lab.

Speech-Backbones This is the main repository of open-sourced speech technology by Huawei Noah's Ark Lab. Grad-TTS Official implementation of the Grad-

HUAWEI Noah's Ark Lab 295 Jan 07, 2023
Repository for Project Insight: NLP as a Service

Project Insight NLP as a Service Contents Introduction Features Installation Setup and Documentation Project Details Demonstration Directory Details H

Abhishek Kumar Mishra 286 Dec 06, 2022
Write Alphabet, Words and Sentences with your eyes.

The-Next-Gen-AI-Eye-Writer The Eye tracking Technique has become one of the most popular techniques within the human and computer interaction era, thi

Rohan Kasabe 2 Apr 05, 2022
NL. The natural language programming language.

NL A Natural-Language programming language. Built using Codex. A few examples are inside the nl_projects directory. How it works Write any code in pur

2 Jan 17, 2022
A fast hierarchical dimensionality reduction algorithm.

h-NNE: Hierarchical Nearest Neighbor Embedding A fast hierarchical dimensionality reduction algorithm. h-NNE is a general purpose dimensionality reduc

Marios Koulakis 35 Dec 12, 2022
An ActivityWatch watcher to pose questions to the user and record her answers.

aw-watcher-ask An ActivityWatch watcher to pose questions to the user and record her answers. This watcher uses Zenity to present dialog boxes to the

Bernardo Chrispim Baron 33 Dec 03, 2022
CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation

CPT This repository contains code and checkpoints for CPT. CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Gener

fastNLP 342 Jan 05, 2023