San Jose, Calif. …September 14, 2022 … Infrrd, a leading provider of Intelligent Document Processing (IDP) solutions, announced today research conducted by Infrrd’s Innovation Lab was recognized as an innovative NLP problem-solving approach by the Association for Computational Linguistics (ACL), an international scientific and professional society for people working on problems involving natural language and computation.
During the ACL’s 16th International Workshop on Semantic Evaluation (SemEval 2022), Infrrd ranked on the top end of the leaderboards in the Task 2: Multilingual Complex Named Entity Recognition competition), demonstrating its Innovation Lab’s ability to recognize and capture data accurately.
SemEval is an annual international vocabulary and semantic competition spanning a series of tests which measure computer understanding of human language.
This year, the SemEval task II consisted of a natural language processing (NLP) task that pushed the limits of named entity recognition for a given set of multilingual data. The organizers defined a task (i.e., NER) that required researchers to build and train named entity recognition models for each language track. The task was divided across several languages. Infrrd worked on nine tracks across several languages including English, Spanish, Dutch, Korean, German, Chinese, Hindi, Bangla, and multi-language.
A dedicated team of machine learning researchers from the Infrrd Innovation Lab solved the task with their innovative approach, entitled, “A System for Named Entity Recognition Using Data Augmentation Transformer-Based Sequence Labeling Model, and EnsembleCRF."
As part of the recognition earned by the Innovation Lab, the team was asked to present their approach at the North American Chapter of the Association for Computational Linguistics (NAACL) conference in Seattle on July 15, 2022. JiangLong He from the Infrrd Innovation Lab represented Infrrd’s research done by him and his team of engineers including Akshay Uppal, Mamatha N, Shiv Vignesh, Deepak Kumar, and Aditya Kumar Sarda.
“Participating in workshops like SemEval validates our technology and also puts our knowledge leaps and bounds ahead of the ongoing research in NLP. Our researchers get to witness how other academic researchers are approaching similar challenges, which helps us identify areas within the knowledge gap and grow from these insights. Additionally, these workshops help us build upon state-of-the-art technology for our own Infrrd Intelligent Document Processing Platform. Our team’s approach and achievements were among the leading solutions at the competition and turned the heads of many participants at the workshop,” said Pratyusha Rasamsetty, head of Infrrd’s Innovation Lab.
To learn more about Infrrd’s approach to solving the task for which it was recognized at SemEval, click here. SemEval Workshop information can be found here.
ABOUT INFRRD
San Jose, Calif.-based Infrrd is a leading provider of proprietary and patented Intelligent Document Processing (IDP) solutions, which leverage artificial intelligence (AI) and machine learning (ML) to enable enterprises to extract and manage data from semi-structured and unstructured documents in large volumes. Infrrd offers pre-built, highly configurable solutions for managing complex documents with reliable accuracy, such as invoices, claims, and bank statements, while also allowing organizations to create and train new models. Enterprises across the globe use Infrrd’s solutions to enhance employee productivity, improve operations, accelerate business scalability, reap cost efficiencies, and deliver exceptional customer experiences.
For more information, visit www.infrrd.ai or connect with Infrrd on LinkedIn, Facebook, and Twitter.
