The IDP vendor’s Natural Language Processing (NLP) research team succeeded in identifying problem entities from the problem set with its innovative approach, “a system for Named Entity Recognition using data augmentation transformer-based sequence labeling model, and EnsembleCRF.”
Infrrd, an Intelligent Document Processing (IDP) provider, announced December 8 that its Research Lab has won the Natural Language for Optimization (NL4Opt) 2022 competition. The solution methodology presented by Infrrd’s research team outperformed all other methodologies presented in the Named Entity Recognition subtask.
This annual workshop was organized by non-profit corporation Neural Information Processing Systems to foster the exchange of research advances in AI and machine learning. In this year’s workshop, Natural Language Processing (NLP) research teams from around the world were tasked with investigating the best methods to automate the conversion of text descriptions into proper formulations for optimization solvers.
The problem was divided into two parts. First, to find an intelligent solution to detect problem entities from the text, and second, to generate a precise meaning representation. Infrrd’s research lab solved both subtasks and outperformed all other methodologies presented in the Named Entity Recognition subtask with its innovative approach.
Pratyusha Rasamsetty, Head of Infrrd’s Research Lab, commented: “Our research team is striving to perfect named entity recognition which is a key element of building intelligence into document processing. We’re honored to receive this recognition, which is a validation of how Infrrd’s NLP research is blazing the trails in the IDP space.”
Infrrd has already recently been recognized by the Association for Computational Linguistics at its annual workshop for an innovative problem-solving approach in Natural Language Processing.
San Jose, California-based Infrrd provides proprietary and patented Intelligent Document Processing (IDP) solutions that leverage artificial intelligence and machine learning to enable organizations to extract and manage data from semi-structured and unstructured documents in large volumes.
Get industry news distilled, every week: