loading
pic 1

Lum accelerates solution discovery


Our natural language processing (NLP) technology augments R&D investments by distilling libraries of unstructured text and revealing mechanisms that matter: drivers, detractors and how that insight may impact your model, so that you can discover, explain, and innovate confidently.



Latest news

alteae template image news

Lum contributes to the Knowledge Integration effort of the Healthy Birth, Growth, and Development (HBGD) program

The Healthy Birth, Growth, and Development (HBGD) program was launched in 2013 by the Bill & Melinda Gates Foundation. The HBGD Knowledge Integration (HBGDki) initiative aims to aggregate resources to facilitate collaboration between researchers, quantitative experts, and policy makers in fields related to HBGD.

Lum contributed its Influence Search to the HBGD program. Influence Search is a semantic search engine that retrieves, assembles, and interprets knowledge fragments extracted from over a hundred thousand publications relevant to children's health. The company is currently working on a knowledge integration platform that integrates Influence Search with other knowledge sources such as citation graph and funding information.

read more
alteae template image news

Digging Deeper into Soil Health Research

The Soil Health Institute, The American Society of Agronomy, Crop Science Society of America, Soil Science Society of America and Lum are partnering on a project that uses natural language processing (NLP) and machine learning (ML) to accelerate the retrieval and use of soil health research.

read more

About us

  • pic 1
  • pic 1

Who we are

Our machine reading technology was developed at the University of Arizona and was funded by DARPA through the Big Mechanism program. The technology includes a mix of natural language processing and machine learning, including a novel framework for the rapid development of semantic grammars for machine reading. In a 2015 DARPA evaluation, our system performed at the accuracy of human experts and at a much higher throughput. By exploring a sea of literature, our solution has uncovered novel genetic pathways for seven types of cancer.

Meet our team

We are a team of researchers with experience and expertise in developing language understanding systems for sources as diverse as social media and scientific publications. These systems incorporate both state-of-the-art approaches in artificial intelligence, as well as rule-based components that encode detailed domain knowledge. Our hybridized approach produces practical systems that are both powerful and versatile.


team altea

Kevin McLaughlin

Chief Executive Officer

Co-founder

About

Kevin advised the team at the University of Arizona prior to co-founding Lum in 2017. He brings over 30 years of experience in technology commercialization, and executive leadership working for companies like Motorola, Cray Research, SGI, Cisco Systems and Avid technology. Kevin works with Tech Launch Arizona as Mentor in Residence for UA startups.


team altea

Mihai Surdeanu

Chief Scientist

Co-founder

About

Associate professor in the Computer Science department at University of Arizona, co-authored over 90 peer-reviewed publications and has over 15 years of experience in building systems driven by NLP and machine learning.
His experience spans both academia (Stanford University, University of Arizona) and industry (Yahoo! Research and two other NLP-centric startups).


team altea

Marco Valenzuela

Co-founder

About

Holds a PhD in Computer Science. He has previous experience with multiple startups and is an expert on machine reading technology.


team altea

Gus Hahn-Powell

Co-founder

About

Holds graduate degrees in Computational Linguistics and Information Science, and focuses on implementing linguistic theory in machine reading systems.


team altea

Dane Bell

Co-Founder

About

Holds an MA in Linguistics. He specializes in complex linguistic phenomena and domain adaptation for machine reading.

Contact us

Questions? You can reach us at [email protected]

Copyright © 2017 Lum / All rights reserved.