Downloaded 51 times
Uploaded bySemantic Web Company
Deep Text Analytics - How to extract hidden information and aboutness from text
The document discusses the Semantic Web Company and its co-founder, Andreas Blumauer, highlighting its software solutions like PoolParty for knowledge graphs and text analytics. It covers topics such as private equity, particularly Bain Capital, wine production in Languedoc-Roussillon, and various applications of a recommender system connecting content and users. Additionally, it addresses challenges in text mining and semantic analysis, offering insights into deep text analytics and machine learning techniques.
More Related Content
Similar to Deep Text Analytics - How to extract hidden information and aboutness from text
![Governance, Deployment & Methodologies for Agentic Automation [2/3]](https://cdn.slidesharecdn.com/ss_thumbnails/agenticcommunityseries-day2-251112135038-a386476d-thumbnail.jpg?width=640&height=640&fit=bounds)
Deep Text Analytics - How to extract hidden information and aboutness from text
- 1. Andreas Blumauer Co-founder andCEO Semantic Web Company
- 2. © Semantic WebCompany 2019 Semantic Web Company Founder & CEO of Andreas Blumauer active at developer & vendor of based on part of standard for standard for graduates PoolParty Software Ltd Director of parent company of London located 2004 founded headquartered >200 serves customers Vienna CMS/DMS/DA M/.. 7.0version Graph database integrates with awarded by Gartner KMWorld Search engine manages Taxonomies Ontologies Text Mining used for Knowledge Graphs part of based on
- 3. © Semantic WebCompany 2019 KNOWLEDGE GRAPHS How to create actionable and meaningful content?
- 4. © Semantic WebCompany 2019 Is this text about ▸ Architecture? ▸ Wine tasting? ▸ Mediterranean Sea? Languedoc-Roussillon Languedoc is a significant producer of wine, and a major contributor to the surplus known as the "wine lake". Today it produces more than a third of the grapes in France, and is a focus for outside investors. The region contains the historic cities of Carcassonne, Toulouse, Montpellier, countless Roman monuments, medieval abbeys, Romanesque churches, and old castles.
- 5. © Semantic WebCompany 2019 Recommender System Connecting ▸ content to content ▸ people to content ▸ people to people Demo: Event Advisor Architecture Mediterranean Sea Wine Tasting Languedoc-Roussillon Languedoc is a significant producer of wine, and a major contributor to the surplus known as the "wine lake". Today it produces more than a third of the grapes in France, and is a focus for outside investors. The region contains the historic cities of Carcassonne, Toulouse, Montpellier, countless Roman monuments, medieval abbeys, Romanesque churches, and old castles. I am interested in ... ?
- 6. © Semantic WebCompany 2019 Recommender System Connecting ▸ content to content ▸ people to content ▸ people to people Architecture Mediterranean Sea Wine Tasting Languedoc-Roussillon Languedoc is a significant producer of wine, and a major contributor to the surplus known as the "wine lake". Today it produces more than a third of the grapes in France, and is a focus for outside investors. The region contains the historic cities of Carcassonne, Toulouse, Montpellier, countless Roman monuments, medieval abbeys, Romanesque churches, and old castles. Occitanie, vineyard, sea, church, village I am interested in ... Demo: Event Advisor
- 7. © Semantic WebCompany 2019 Classification of text Private equity typically refers to investment funds, generally organized as limited partnerships, that buy and restructure companies that are not publicly traded. Bain Capital is a venture capital company based in Boston, MA. Since inception it has invested in hundreds of companies. In 2018, Bain had $75b AUM. Mitt Romney is an American politician and businessman serving as the junior United States senator from Utah since January 2019. Give me all paragraphs in documents about “US based Private Equity firms with AUM higher than $20B”
- 8. © Semantic WebCompany 2019 ▸ Corpus statistics / Word embeddings → Keyphrase extraction ▸ Graph-based annotation → Entity/Concept linking ▸ Corpus Statistics embedded in graphs → Shadow Concepts ▸ Machine-learning-based annotation → Named entity recognition (NER) ▸ Machine-learning based classification → Document Classification ▸ Annotation based on regex → Regular expressions Bain Capital is a venture capital company based in Boston, MA. Since inception it has invested in hundreds of companies. In 2018, Bain had $75b AUM. Graph-based Entity Linking Regular Expressions-based Annotation Semantic Rules Engine Give me all paragraphs in documents about “US based Private Equity firms with AUM higher than $20B” ML-based Entity Extraction
- 9. © Semantic WebCompany 2019 ▸ Deep Text Analytics is an application of Semantic AI ▸ Fusing methods and algorithms taken from language modeling, corpus linguistics, machine learning, knowledge representation and the semantic web result into Deep Text Analytics methods ▸ Main areas of use cases for DTA are Information retrieval, NLU, Question answering, and Recommender Systems
- 10. © Semantic WebCompany 2019 WHAT’S THE PROBLEM? Many Challenges in Text Mining
- 11. © Semantic WebCompany 2019
- 12. © Semantic WebCompany 2019 Perth Australia Perth is one of the most isolated major cities in the world, with a population of 2,022,044 living in Greater Perth. Australia is a member of the OECD, United Nations, G20, ANZUS, and the World Trade Organisation. Country City is a is a is located in distance between Commonwealth of Nations International Organisation is a Avoid illogical answers: is part of Support complex Q&A: Which cities located in the Commonwealth of Nations have a population of more than 2 mio. people?
- 13. © Semantic WebCompany 2019 doc doc doc Jaguar Elephant Wolf Rabbit doc Jaguar Elephant Wolf Rabbit doc Show me all documents about Carnivores Traditional approach Graph-based approach doc doc doc
- 14. © Semantic WebCompany 2019 Show me all documents about Carnivores Traditional approach Graph-based approach doc doc doc Jaguar Carnivore Elephant Wolf Carnivore Rabbit doc Jaguar Elephant Wolf Rabbit doc Carnivores doc doc doc
- 15. © Semantic WebCompany 2019 Show me all documents about Carnivores Traditional approach Graph-based approach doc doc doc Jaguar Cat Carnivore Elephant Wolf Carnivore Rabbit doc Jaguar Elephant Wolf Rabbit doc Carnivores doc doc Cat Show me all documents about Cats doc
- 16. 16 doc doc doc Jaguar Cat Felidae CarnivoreElephant Wolf Carnivore Rabbit doc Jaguar Elephant Wolf Rabbit doc Carnivore Traditional approach Graph-based approach Show me all documents about Felidae doc doc doc Show me all documents about Carnivores Cat = Felidae
- 17. 17 doc doc doc Jaguar Cat Felidae Carnivore Keystone Species Elephant Keystone Species Wolf CarnivoreRabbit doc Jaguar Elephant Wolf Rabbit doc Carnivore Traditional approach Graph-based approach Show me all documents about Felidae doc doc doc Show me all documents about Carnivores Cat = Felidae Keystone Species? Keystone Species
- 18. 18 doc doc doc Jaguar Cat Felidae Carnivore Keystone SpeciesElephant Wolf Carnivore Rabbit doc Jaguar Elephant Wolf Rabbit doc Carnivore Traditional approach Graph-based approach Show me all documents about Felidae doc doc doc Show me all documents about Carnivores Cat = Felidae Keystone Species? Keystone Species Metadata per document 1. No or little network effects 2. No reuse of metadata 3. Metadata resides in silos 4. Data quality hard to measure 5. Not machine-readable Knowledge about metadata 1. Explicit knowledge models 2. Reusable and measurable 3. Metadata is machine-processable 4. Standards-based metadata 5. Linkable metadata opens silos
- 19. © Semantic WebCompany 2019 Unsupervised sense representation (Word sense induction) Knowledge-based sense representation The main problem: From Word to Sense Embeddings: A Survey on Vector Representations of Meaning
- 20. © Semantic WebCompany 2019 Mechanism How does it work? Entity extraction based on concepts instead of simple term-based extraction Make use of synonyms in a glossary / taxonomy; disambiguation based on taxonomies / corpus statistics Extraction of super-classes and broader concepts Make use of hierarchical structures in a taxonomy or knowledge graph Extraction of related terms and concepts KGs, co-occurrence models and word embeddings Extraction of ‘Shadow Concepts’ Combining co-occurrence models and knowledge graphs Semantic Classifier Enrichment of training documents with data from a knowledge graph Deep Text Analytics Derivation of new metadata and classifications based on mechanisms as described above combined by rules Complexity
- 21. © Semantic WebCompany 2019 Austria’s capital, lies in the country’s east on the Danube River. Its artistic and intellectual legacy was shaped by residents including Mozart, Beethoven and Sigmund Freud. The city is also known for its Imperial palaces, including Schönbrunn, the Habsburgs’ summer residence. In the MuseumsQuartier district, historic and contemporary buildings display works by Egon Schiele, Gustav Klimt and other artists. Schaut man vom Kahlenberg auf die Donau hinunter, kann man Wien mit allen Sinnen spüren. Weinberge sind da zu sehen, dahinter glänzt das bauliche Erbe der mitteleuropäischen Metropole. Ein halbes Jahrtausend wurde hier Weltgeschichte geschrieben. Kunstgeschichte sowieso.
- 22. © Semantic WebCompany 2019
- 23. © Semantic WebCompany 2019 http://www.my.com/ taxonomy/62346723 prefLabel Retina image http://www.my.com/ images/90546089 http://www.my.com/ taxonomy/ 97345854 prefLabel Funduscope altLabel Ophthalmoscope http://www.mycom.com /taxonomy/4543567 prefLabel Diagnostic Equipment has broader Extraction of super-classes and broader concepts
- 24. © Semantic WebCompany 2019 Document Corpus ▸ Websites ▸ PDF, Word, … ▸ Abstracts from DBpedia ▸ RSS Feeds Term 8 Term 3 Term 7 Term 8 Term 6 Term 9 Term 5 Term 10 ▸ Relevant terms and phrases ▸ Relevancy of terms ▸ co-occurrence between terms and terms Term 1 Term 4 Term 2
- 25. © Semantic WebCompany 2019 How do we learn from a lot of text? Bla bla bla bla. Bla bla bla bla The stove is on. The stove is hot! Ontological model → reasoning Taxonomical model → is-a abstractions Bla stove bla bla. Bla bla bla hot Switched on devices are dangerous devices. Switched on devices are dangerous, only if the operating temperature is above 100 degrees and the automatic shutdown mechanism is broken. The stove is on. The stove is hot! Statistical model/cooccurences → is related The stove is on. The stove is hot! Bla bla bla bla Bla bla bla bla.
- 26. © Semantic WebCompany 2019 Use co-occurrences between concepts and terms to extract ‘shadow concepts’ 26 This site is a 15th-century Inca site located 2,430 metres above sea level. It is located in Cusco, Peru. It is situated on a mountain ridge above the Sacred Valley through which the Urubamba River flows. Most archaeologists believe that it was built as an estate for the Inca emperor Pachacuti. Often mistakenly referred to as the "Lost City of the Incas", it is the most familiar icon of Inca civilization. The Incas built the estate around 1450, but abandoned it a century later at the time of the Spanish Conquest. Inca site Machu Picchu CuscoInca empire Inca emperor Peru Spanish Conquest Sacred Valley Chankas Lost City Pachacuti In addition to explicitly used concepts and terms, Machu Picchu is extracted from the article as a Shadow Concept. As a prerequisite, one has to provide and analyze a representative text corpus first.
- 27. © Semantic WebCompany 2019 ▸ Corpus statistics / Word embeddings → Keyphrase extraction ▸ Graph-based annotation → Entity/Concept linking ▸ Corpus Statistics embedded in graphs → Shadow Concepts ▸ Machine-learning-based annotation → Named entity recognition (NER) ▸ Machine-learning based classification → Document Classification ▸ Annotation based on regex → Regular expressions Bain Capital is a venture capital company based in Boston, MA. Since inception it has invested in hundreds of companies. In 2018, Bain had $75b AUM. Graph-based Entity Linking Regular Expressions-based Annotation Semantic Rules Engine Give me all paragraphs in documents about “US based Private Equity firms with AUM higher than $20B” ML-based Entity Extraction
- 28. © Semantic WebCompany 2019 PoolParty Semantic Classifier combines machine learning algorithms (SVM, Deep Learning, Naive Bayes, etc.) with Semantic Knowledge Graphs.
- 29. © Semantic WebCompany 2019 USE CASES See how it can be used in your environment!
- 30. © Semantic WebCompany 2019
- 31. © Semantic WebCompany 2019 Some domains use text that doesn’t always call a spade a spade. With ‘shadow concept extraction’ those ‘masked’ concepts still can be surfaced. Since these technologies would have become conventional technologies that are made into products and introduced into market at the time of their introduction, it would be difficult to differentiate them as innovative environmental and energy technologies from other global warming prevention technologies that have already been put to practical use in the industrial, commercial, residential, and energy conversion sectors. - The Innovative Global Warming Prevention Technology Working Group under the Research and Development Subcommittee - Council assessed that innovative global warming prevention technologies would bring about a reduction effect of 7.49 million t-CO2 case of average emissions factor for all power sources of carbon dioxide in 2010. In view of the difficulty in putting innovative carbon dioxide sequestration technology into practical use by 2010, the Working Group reassigned it as an issue of global warming prevention technology to be tackled by 2030. The Central Environment Council, however, has not had the opportunity to examine the contents of these technologies in detail. (Promotion of climate change prevention activities by every social actor) - The Programme encourages every social actor to take actions to prevent global warming. The actions include measures undertaken by the public sector. Climate Change Since these technologies would have become conventional technologies that are made into products and introduced into market at the time of their introduction, it would be difficult to differentiate them as innovative environmental and energy technologies from other global warming prevention technologies that have already been put to practical use in the industrial, commercial, residential, and energy conversion sectors. - The Innovative Global Warming Prevention Technology Working Group under the Research and Development Subcommittee - Council assessed that innovative global warming prevention technologies would bring about a reduction effect of 7.49 million t-CO2 case of average emissions factor for all power sources of carbon dioxide in 2010. In view of the difficulty in putting innovative carbon dioxide sequestration technology into practical use by 2010, the Working Group reassigned it as an issue of global warming prevention technology to be tackled by 2030. The Central Environment Council, however, has not had the opportunity to examine the contents of these technologies in detail. (Promotion of climate change prevention activities by every social actor) - The Programme encourages every social actor to take actions to prevent global warming. The actions include measures undertaken by the public sector. Climate Change
- 32. © Semantic WebCompany 2019 Mini Countryman And it’s probably more of a crossover than ever, with the design to match, Being a Mini, the Countryman is clearly meant to be the driver’s car among small crossovers. The suspension is sophisticated, and there are lots of chassis options (a stiffer sports setup, variable damping, the electronically controlled ALL4 all-wheel-drive). But it’s also the crossover for people who’ve bags of cash to blow on personalisation and luxury. There’s been a lot of effort on ramping up the cabin quality, but then the outgoing Countryman was a sad let-down in that department. On the outside, plastic wheel-arch extensions, with eyebrow creases in the metalwork above, as well as roof bars and sill protectors all add to the visual crossover-ness. This remains the only Mini with angular rather than oval headlamps, and there’s a load of visual posturing going on in the lower face. There are eight versions at launch, and they’re exactly what you’d expect. It’s Cooper or Cooper S, each fuelled by petrol or diesel, each of them with front drive or ALL4. Oh and an eight-speed auto, too, if you count that as a separate choice. The Cooper petrol is a three-cylinder, the rest fours. You get extra kit as standard versus the old car, including navigation, Bluetooth, emergency call and park sensors. Upgrades include a bigger touch-screen nav with high-definition traffic, various posher seats, a HUD, and driver aids. Oh and a cushion thingy that folds out from the boot so you can sit on the rear bumper without getting your clothes mucky. In June 2017 a Cooper E will launch, which has the Cooper three-cylinder petrol driving the front wheels, and an electric motor for the rears, with a capacity to do a claimed 25 miles of gentle all-electric running. So it has the performance of a Cooper S ALL4 with the tax-busting advantages of a plug-in hybrid. And you wouldn’t use any fuel if you commuted a short distance. The platform is BMW’s contemporary transverse-engined hardware, in the bigger of its two sizes. That means it shares a lot with the BMW X1. The 4WD system is more sophisticated than the previous Countryman’s. The proportion of drive to the rear is computed by a controller that takes into account parameters including grip, steering angle and throttle position, as well as whether you’ve got the sports mode and sports traction systems selected.
- 33. © Semantic WebCompany 2019 TheCompany 12 Termination by TheCompany for Semantic analysis and pre-selection of relevant clauses in contracts
- 34. Integrating Semantics intoDialog Workflows My uncle lives in the same household. Darf ich seine Betreuungskosten absetzen? Ange- hörige same household haushalts- zugehöriger Angehöriger uncle teyze ortak ev Can I deduct my aunt’s care expenses?
- 35. © Semantic WebCompany 2019 Use KGs and DTA to generate test data for your ML (which are GDPR compliant)
- 36. The Knowledge Engineer’sperspective Bain Capital is a venture capital company based in Boston, MA. Since inception it has invested in hundreds of companies including AMC Entertainment, Brookstone, and Burger King. The company was co-founded by Mitt Romney. UnifiedViews PoolParty GraphSearch Identify new candidate concepts to be included in a controlled vocabulary RDF Graph Database Factsheet Schema mapping based on ontologies Entity linking based on Knowledge Graph Unstructured Data Semi-structured Data Structured Data Controlled vocabularies as a basis for highly precise knowledge extraction and text classification
- 37. © Semantic WebCompany 2019 Learn more about it!
- 38. © Semantic WebCompany 2019 Andreas Blumauer CEO, Semantic Web Company ▸ Mail [email protected] ▸ Company https://www.semantic-web.com ▸ LinkedIn https://www.linkedin.com/in/andreasblumauer ▸ Twitter https://twitter.com/semwebcompany ▸ Medium https://medium.com/semantic-tech-hotspot