Natural Language 

 

Get understanding from unstructured data with advanced natural language processing tooling to recognise named entities, relationships, keywords and part of speech.

Gwendra AI uses advanced tools to enable the detailed analysis of vast volumes of unstructured text. NLP forms a core part of many of our models and applications. Tools to process textual information, drawing out facts, meaning and sentiment give us the ability to access the vast wealth of data outside of traditional databases of structured data.

We use state of the art neural network based NLP tools, coupled with proprietary deep learning capabilities on a high performance computing platform to create bespoke NLP processing pipelines tailored and tuned to the client’s individual data, use cases and requirements.


This is an example of how the Gwendra AI NLP pipeline identifies entities in text. These neural network based tools have significant advantages over lexicon based approaches, with improved accuracy and the ability to further refine the cognitive abilities of the technology by training the algorithms to recognise your entities in context of your specific business domain and application.

Extracted from 'Brexit in peril' as PM May faces heavy defeat’, reuters.com 10th March 2019:

ParliamentORG rejected TheresaORG’s deal by 230CARDINAL votes on Jan. 15DATE, prompting her to return to BrusselsGPE in search of changes to address the so-called IrishNORP backstop - an insurance policy designed to prevent the return of a hard border between IrelandGPE and Northern IrelandGPE.PERSONMany BritishNORP lawmakers object to the policy on the grounds that it could leave BritainGPE subject to EUORG rules indefinitely and cleave Northern IrelandGPE away from the rest of the country.

We also use part of speech tagging and sentence detection to pull out SVO (Subject-Verb-Object) semantics to identify the key subject of a sentence and extraction of keywords from broader English language texts.

These tools, along with custom keyword extraction can quickly process huge volumes of historic texts, opening up information for use in analysing legacy documents or for processing real time data, for example news or social media feeds.