Infrrd Recognized for its Innovative Natural Language Processing Research

By
Infrrd
September 14, 2022

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.

Frequently asked questions

What does your pricing model look like?

We price based on the annual volume of pages and complexity of document type.  We can get you preliminary pricing once we outlined a solution.  Let's do this.

To know more, book a 15-min session with an IDP expert

How can I try Infrrd before I commit to a full deployment?

Sure.  The first step is to schedule a guided demo where you get to jump into the thick of it.  After you explore our solution you can try a proof of concept. When you're ready, you can deploy the system to one use case.  Then more use cases.  Then across your enterprise.

To know more, book a 15-min session with an IDP expert

How does your system integrate with others in my enterprise?

We play nice.  Our solutions are API-based.  Your documents are feed into the solution using APIs. And extracted data is sent out through APIs.  We use REST APIs.

To know more, book a 15-min session with an IDP expert

Does your solution run in the cloud or on premise?

Our solution is cloud-native but is also design for premise deployments.  Your choice on how you want to deploy it.

To know more, book a 15-min session with an IDP expert

Does Infrrd run on mobile or desktop device?

Glad you asked.  Our data extraction process runs on servers.  We have found performance and accuracy decline when running on a desktop or mobile device. (Remember Infrrd is running a powerful AI stack).

To know more, book a 15-min session with an IDP expert

Does your system work out of the box or does it require training?

Common documents and use cases work out of the box.  The cool thing is your solution will improve as the system learns from your documents upfront and over time.

To know more, book a 15-min session with an IDP expert

How does your solution handle corrections?

Did you know no system is 100% accurate all the time?  When extraction errors occur you want to correct them.  We provide a simple UI that your business analyst will use to make corrections.

To know more, book a 15-min session with an IDP expert

Does your solution work with handwriting?

Our solution excels at data extraction from handwriting.  We've got proprietary methods and techniques that do the trick.  It's pretty cool.  See for yourself.

To know more, book a 15-min session with an IDP expert