There are several Question & Answer OpenSource Language Comprehension models that can be applied to unstructured text. Even without tuning to a domain, they are capable of producing some quite remarkable answers buried in large amounts of text for simple factual questions. The image above is a simple example related to Carbon Capture, Utilisation and Storage... Continue Reading →

Sentence based sentiment analysis was conducted for monthly hydrological summary reports for the UK, covering groundwater, river flows and rainfall over the past 9 years. The hypothesis was whether seasonal changes would be picked out using text based sentiment. Averaging smoothes out the 'edge cases' but nevertheless some consistent patterns may emerge. Further work ongoing.... Continue Reading →

Looking to extract evidence for petroleum systems, metals & minerals, heat flow, fluid flow or aquifers & seals in reports or semi-structured databases? Or chronostratigraphy, lithostratigraphy, tectonics, depositional environment and lithology? The patented algorithms from Infoscience Technologies may give your organisation a fast start.. contact@infosciencetechnologies.com

Using machine learning to detect mentions of drilling and operational problems in text. Over 5,000 public domain sentences have been labelled to train a predictive machine learning model to detect wellbore drilling and operational ‘problems’ (including reservoir and production) in documents, reports and logs. This can support alerts & monitoring, health & safety, search &... Continue Reading →

Excited to start the Curtin University course 'Digital Transformation in Mining' today in my spare time. https://news.curtin.edu.au/media-releases/curtin-and-uq-collaborate-with-industry-on-new-online-mining-course/ https://www.edx.org/course/digital-transformation-of-mining

Discover new insights in geoscience documents, using patterns in unstructured text to detect petroleum, mineral, hydro, geothermal and hydrogen exploration opportunities. First-of-a-kind OpportunityFinderⓇ and GeoClassifierⓇ algorithms are now integrated. Teaching machines about geoscience.  Apply to deep archives, documents on your shared drive, or in Microsoft Sharepoint or Document Management Systems. Apply to external geoscience subscription reports and... Continue Reading →

Enjoyed giving the lecture on search & text analytics to over 40 MSc Business Analytics students at RGU today. Great questions and a knowledgeable and enthusiastic audience. Thanks to Dr Ebuka Ibeke for a warm welcome as usual! More on the MSc course here: https://www.rgu.ac.uk/study/courses/1177-pgcert-pgdip-msc-business-analytics

Honoured to be reviewing for the British Computer Society Search Industry Awards next month.  https://www.bcs.org/membership/member-communities/information-retrieval-specialist-group/

Delighted to guest author an article on Natural Language Processing (NLP) in the Geosciences for Halliburton’s September Issue of Subsurface Insights. This month's issue is a minerals special. To access the article you can sign up free to Halliburton's magazine: https://geoweb.neftex.com/account/accessrequest Infoscience Technologies website is: http://www.infosciencetechnologies.com

When deploying a search engine in an organisation, it can be useful to think deeply about the underlying assumptions being made. These can help inform strategies. Arguably, some organisations may deploy reductionist technology focused strategies without perhaps thinking about all the assumptions they are making. CLEVERLEY, P.H. and BURNETT, S. 2019. Enterprise search and discovery... Continue Reading →