NeuML - Applying machine learning to solve everyday problems

NeuML develops groundbreaking data analytics and machine learning software to solve everyday problems. Applications include txtai, an AI-powered search engine and paperai, an award-winning AI-powered literature discovery and review engine.

About Us

NeuML has years of relevant experience in building data strategies for both small and large organizations. With the right data, valuable insights can be gained by capitalizing on modern advances in machine learning.

NeuML has a robust suite of open-source applications that can be leveraged to jump start you towards gaining a competitive edge.

Capabilities

Advisory and Strategy Support Build out your data and AI strategy, leveraging our deep expertise
Data-driven Analysis Run an exploratory data analysis and gain insights from large existing datasets
Training Group training covering AI, Machine Learning and NLP using our open-source stack

AI-driven Literature Review Automate reviews of large-scale unstructured literature datasets
Market Research Gather statistics on specific market trends and competitive analysis
Social Media Analytics Sentiment analysis, event discovery, trend detection and summarization

Applications

txtai

txtai executes machine-learning workflows to transform data and build AI-powered text indices to perform similarity search. txtai supports indexing text snippets, documents, audio and images. Pipelines and workflows enable transforming data with machine-learning models. NeuML uses txtai and/or the concepts behind it to power all of our Natural Language Processing (NLP) applications.

List of applications powered by txtai:

paperai - AI-powered literature discovery and review engine for medical/scientific papers
tldrstory - AI-powered understanding of headlines and story text
neuspo - Fact-driven, real-time sports event and news site
codequestion - Ask coding questions directly from the terminal

paperai

paperai is an AI-powered literature discovery and review engine for medical/scientific papers. paperai helps automate tedious literature reviews allowing researchers to focus on their core work. Queries are run to filter papers with specified criteria. Reports powered by extractive question-answering are run to identify answers to key questions within sets of medical/scientific papers.

paperai was used to analyze the COVID-19 Open Research Dataset (CORD-19), winning multiple awards in the CORD-19 Kaggle challenge.

paperai and/or NeuML has been recognized in the following articles:

tldrstory

tldrstory is a framework for AI-powered understanding of headlines and text content related to stories. tldrstory applies zero-shot labeling over text, which allows dynamically categorizing content. A customizable Streamlit application and FastAPI backend service allows users to review and analyze the data processed.

neuspo

neuspo is laser-focused on identifying fact-driven, real-time event data from sports social media and news data. The platform looks to set an example of media providing tailored experiences to distinct topics of interest, with clarity into how content is recommended.

Articles

txtai: AI-powered search engine

Search is the base of many applications. Once data starts to pile up, users want to be able to find it. It’s the foundation of the internet and an ever-growing challenge that is never solved or done. This article discusses how txtai can be used to build AI-powered similarity search systems.

Combating COVID-19 with Data Science

COVID-19 Open Research Dataset (CORD-19) was released “to apply recent advances in natural language processing to generate new insights in support of the fight against this infectious disease”. Read about how NeuML applied machine learning and data science to help researchers find answers in the large incoming stream of COVID-19 literature.

Building a sentence embedding index with fastText and BM25

An overview of how fastText + BM25 can be used to build an effective and high performing embeddings index. This article explores various methods and goes through an evaluation process for building a text search system.

neuspo

Sports is a topic with many voices, opinions and commentary. Information is plentiful but objective, descriptive, real-time information is hard to find in an opinionated world. With social media in particular, it’s hard to separate fact from opinion and follow what is actually happening. Read about how neuspo sets out to change that.

Leadership

David Mezzetti - Founder/CEO

David Mezzetti founded NeuML in 2020 to apply machine learning to solve everyday problems. Dave is leading the way in helping to build innovative products backed by machine learning.

Dave previously co-founded and built Data Works from the ground up into a 50+ person well-respected software services company. In August 2019, Data Works was acquired by E3/Sentinel.

Dave is also an active Medium contributor, his articles have been published with Towards Data Science and Better Programming.