OUR EXCLUSIVE NLP TECHNOLOGY

Rasp

RASP (robust accurate statistical parsing) system, designed for syntactic annotation of free text.

iLexIR own the sole commercial rights to RASP and licenses can be purchased for commercial applications.

Search

We are actively developing our generic search technology that allows users to search in an intuitive manner to produce complex linguistic searches easily. iLexIR own the sole commercial rights to this search technology.

This search technology is available for commercial use only.

Data Anonymisation

We have developed an anonymisation tool capable of supporting more rapid and accurate anonymisation of sensitive data such as patient medical records. iLexIR own the sole commercial rights to this technology.

This technology is available for commercial use only.

TAP

TAP classifier is a highly scalable linear classifier which has been shown to outperform SVMs and Bayesian logistic regression (BLR) on topic and other text classification tasks. Further, the TAP classifier can be trained in near linear time.

The TAP classifier is patented and available for commercial use only.

To date, we have worked with clients to develop sentiment classification systems, mobile phone based question-answering services, and text mining tools for use in ESOL examination design and biomedical information extraction.

Our Clients & Partnerships

We shared our technology with SwiftKey who used it to help develop the next generation of text prediction software for smartphones.

We worked with Cisco to improve terminology recognition in Cisco Pulse.

We have developed automated english as a second language (ESOL) text grading and error feedback systems.

We have worked with Cambridge English Language Assessment to deploy the technology in Write & Improve.

We are working with Cambridge Assessment and Cambridge University Press to develop the next generation of EFL teaching and testing materials.

We helped Texperts (now kgb) to develop techniques for efficient processing of SMS Text Questions.

We helped Corpora (later Infonic, now iOra) build their sentiment classifier.

We worked with CPRD (a part of the NHS) to anonymise sensitive patient medical records using our anonymisation tools.

We are collaborating with Speechmatics to develop speech analytics tools
that leverage their world-class speech transcription cloud-based
services.

We are advising Cytora on the development of textual information extraction systems to support their risk management products.

We are advising ThoughtRiver on the development of textual information extraction tools to support their contract intelligence software.

We are advising All Street on the development of textual information extraction systems to support creation of low-cost accessible company reports for investors.