M. A. Linda Andersson

 

Ph.D. student, Computational Intelligence


 

Bild på Linda

Institute of Software Technology and Interactive Systems Information and Software Engineering Group, Vienna University of Technology

Contact

Institute of Software Technology and Interactive Systems
Favoritenstrasse 9-11/188,
1040 Vienna


Email: andersson [at] ifs.tuwien.ac.at





 

Biography

 



For the last 15 years, Linda has worked with different aspects associated with scientific literature text mining. Parallel with her academic studies Linda has been working in the industry, designing different domain specific text mining solutions. In 2009 Linda presented here Master Thesis A Vector Space analysis of Swedish patent claims, does decompounding help? which was based on a collaboration with Swedish Patent and Registration Office. The thesis has since 2009 been part of the collection INNOVA - the Bibliography of Intellectual Property Rights at the National Library of Sweden.

For the PhD Thesis The Essence of Patent Text Mining Linda continued working close with the text mining industry. Linda's research focus has been on developing real-world text mining applications using Natural Language Processing techniques. Among others, Linda has worked together with Uppdragshuset Sverige AB for several years in charge of the R&D group. The outcome of her work at the TU Wien and the collaboration with Uppdragshuset Sverige AB was a EuroStars project in 2015-2017 (Self-Optimizer). In the line of Linda's research work in different scientific projects KConnect and Self-Optimizer, Linda has developed a process flow for establishing a generic method for Natural Language Annotation Design for domain specific text mining solutions.

In 2017, Linda was awarded the most promising PhD research results, and in 2018 she launched the product idea 'Artificial Researcher in Science' and received the Commercial Viability Award by the Austrian Angel Investors Association. During autumn 2018, Linda and her team are participating in the TUW i²ncubator Incubation Program for TU Wien spin-offs/spin-outs.

Linda is now the CEO of the start-up Artificial Researcher-IT GmbH. The start-up received a three-year research grant for the project Artificial Research in Science: Efficient Scientific Publication Mining, a collaboration with the Technische Universität Wien IFS and Technische Universität Wien Bibliothek (supported by Vienna Business Agency). In 2019, the start-up received pre-seed grant for the product Artificial Researcher in Open Access with a focus to provide patent data and open access scholarly literature to industry as well as universities (supported by Austria Wirtschaft Service). In 2020, they joined the text mining community effort to enhance text data extracted from open available resources on COVID-19, and was granted a research project AR-ONTO-COVID - Support Material by the European Open Science Cloud (EOSC) to access the knowledgebase resource and the open-source code. We also received a second co-creation grant from EOSC, together with Research Studio Austria the iFAIR - Identifying datasets by mining research papers to make more data FAIR to access collection, test and training data as well as the open-source software.



 

Research interests

 

Linda is interested in several research fields connected to text mining, domain specific Information Retrieval and Information Extraction (law, medicine, patent), Generative lexicon, Distributional Semantic, Corpus profiling to more traditional Information Retrieval.



 

Education

 

Education Logos

 


Application Demos

 


Ontology used in an Information Retrieval setting Graph Search Demo

 


Document and Paragraph (Passage) Retrieval Search Passage Retrieval

 

Invited Talks & Teaching

 


2021 July

 


The next generation AI-based Prior Art Search tools can be sustainable and transparent
PatentSemTech21 (Demo Talk).

 


Linda Anderson - Artificial Researcher: On the History and Challenges of Domain Specific Text Mining
Austrian AI Podcast (Interview).

 


2021 (Apr) Open Data: An Important Source for Intellectual Property Awareness
Building Consistency for Open Science in Europe: Rhetoric and Practice. For video select Item 10: Lightning Talks (2:57).

 


2021 (Mar) Artificial Researcher - The Next Generation Search Technology
Female Founders Events (Pitch)

 


2020 December

 


Domain Knowledge makes Artificial Intelligence Smart
AI & Patent Data Workshop - JURIX 2020

 


Artificial Researcher - Your scientific knowledge provider
Online forum Erfolgreiche Unternehmensgründung St Pölten University of Applied Sciences

 


2019 (Nov) From idea to the first clients: Building a deep-tech start-up - how to spot early monetization opportunities
WeAreDevelopers Congress Vienna (Workshop)

 


2019 September

 


Combining full-text search and Statistics: To narrow the scope of the search to a specific technical domain, geographic region and down to companies and inventors.

From A-Z, towards a patent text mining application - Cross Genre Paragraph Retrieval
European Patent Office Summer School, Vienna (Presentations)

 


Tutorial 2 - From A-Z, towards a patent text mining application
The 1st Workshop on Patent Text Mining and Semantic Technologies
(PatentSemTech) in conjunction with SEMANTiCS Karlsruhe

 


Domain Ontology - Human Aided Computer Assessment tool for exhaustive search
Text mining in the Patent domain
Linguistic knowledge does it really matter
Guest Lectures in the iDSDL project

 


2019 (Jun) Rethinking Scholarly Communication with AI: Keywords Are Not the Answer to Improve Your Search Result
at The CERN-UNIGE Workshop on Innovations in Scholarly Communication will be held at University of Geneva (Presentation)

 


2019 (Jan) Text Mining & Domain Adaptation: Learning from the Best - bringing research to a start up and a novel and innovative platform at the Research Studios Austria Forschungsgesellschaft mbH Jahresklausur, Salzburg, Austria (Presentation)

 


2019 (Jan) Text mining in the Patent domain - what can the near future bring?, European Patent Office, Vienna, Austria (Presentation)

 


2018 The Essence of Patent Text Mining, FIZ Karlsruhe Germany (Presentation)

 


2018 The Essence of Patent Text Mining, LegalTech Track, SEMANTiCS Vienna, Austria (Presentation)

 


2018 The Essence of Domain-specific Text Mining, IBM Zürich, Switzerland (Presentation)

 


2017 The Essence of Patent Text Mining, Seminar in Computational Linguistic, Uppsala University, Sweden

 


2017 Domain specific text mining almost from scratch with Deep Learning ,
One pager for Open session at Deep Learning Summer Schoolin Bilbao, Spain

 


2011 Advanced search for Information specialists, Patent experts at GE India (Training sessions)

 


2010 Building a Patent Retrieval system for Swedish, Swedish Patent and Registration Office (Presentation)

 


2001 Trubbiga sökverktyg, Mälardalens Univeristy College (Lectures)


 

Scientific Projects

 


KConnect EU Innovation Action - Search technologies for medical information, Vienna University of Technology(2016-2017)

 

Self-Optimizer -support tool for companies Innovation process, EuroStars (2015-2017)

 

ADmIRE - Abstracting Domain-Specific Information Retrieval and Evaluation, Austrian Science Fund (FWF) (2013-2016

 

Khresmoi - Medical Information Analysis and Retrieval, EU Integrated Project Science Fund (2011-2014)

 

Q&A system for Quantities in patent Innovation Check for a text mining company MaxRecall, Forschungsförderungsgesellschaft Errichtungsgesetz (FFG) (2012)



 

Programme committee or Reviewer

 


Conference on Information and Knowledge Management (2014-2016)

 


European Conference on Information Retrieval (Organization member in 2015, since 2016 Reviewer)
Acknowledged with the Recognized Reviewer Award at 41st European Conference on Information Retrieval, ECIR2019 Cologne



 

Professional Career

 


Research Assistant, Secure Business Austria Research, (Jan-Aug 2018)

 


Research Assistant, Information and Software Engineering Group (IFS), Vienna University of Technology (TUWIEN), (2009-2017)

 


R&D Project manager, Uppdragshuset Sverige AB, Sweden (2014-2015)

 


Assistance Archivist, University of Växjö (2007-2008)

 


Assistance admission administrator, The teaching Education Office at Stockholm University (2007)

 


E-learning developer, Mälardalens University/College (1999-2000)

 


Student researcher Assistance, Mälardalens University/College and National Semiconductor (1999)


 

Publication

 


Ralf Krestel, Hidir Aras, Linda Andersson, Florina Piroi, Allan Hanbury, Dean Alderucci (2021) 2nd Workshop on Patent Text Mining and Semantic Technologies (PatentSemTech2021) In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '21). Association for Computing Machinery, New York, NY, USA, 2693-2696.

 


Alaa El-Ebshihy, Annisa Maulida Ningtyas, Linda Andersson, Florina Piroi, Andreas Rauber (2020) ARTU / TU Wien and Artificial Researcher@ LongSumm 20. SDP@EMNLP 2020: 310-317 Proceedings of the First Workshop on Scholarly Document, Association for Computational Linguistics

 


Annisa Maulida Ningtyas, Alaa El-Ebshihy, Florina Piroi, Allan Hanbury, Linda Andersson (2020) TUW-IFS at TREC NEWS 2020 : Wikification Task TREC 2020

 


Markus Zlabinger, Linda Andersson, Allan Hanbury, Michael Andersson, Vanessa Quasnik, Jon Brassey (2018) Medical Entity Corpus with PICO Elements and Sentiment Analysis Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan

 


László Grad-Gyenge and Linda Andersson (2018) The MediaBubble DatasetThe 3rd CCURL Workshop, in conjunction with LREC 2018, Miyazaki, Japan

 


Markus Zlabinger, Linda Andersson, Jon Brassey, Allan Hanbury (2018) Extracting the Population, Intervention, Comparison and Sentiment from Randomized Controlled TrialsBuilding Continents of Knowledge in Oceans of Data: The Future of Co-Created eHealth - Proceedings of {MIE}, Medical Informatics Europe, Göteborg, Sweden, April

 


Linda Andersson, Navid Rekabsaz, Allan Hanbury (2017) Automatic query expansion for patent passage retrieval using paradigmatic and syntagmatic information The first WiNLP Workshop co-located with with the Annual Meeting of the Association for Computational Linguistics (ACL 2017), Vancouver

 


Navid Rekabsaz, Mihai Lupu, Artem Baklanov, Allan Hanbury, Alexander Duer, Linda Anderson Volatility Prediction using Financial Disclosures Sentiments with Word Embedding-based IR Models Proceedings of the Annual Meeting of the Association for Computational Linguistics ACL 2017

 


Linda Andersson, Allan Hanbury, Andreas Rauber (2017) The Portability of three type of Text Mining Techniques into the patent text genre. In M. Lupu, K. Mayer, J. Tait, and A. J. Trippe, Second edition, Current Challenges in Patent Information Retrieval

 

Linda Andersson, Mihai Lupu, João R. M. Palotti, Allan Hanbury, Andreas Rauber (2016) When is the time Ripe for Natural Language Processing for Patent Passage Retrieval? In Proceedings of the 25th ACM International Conference on Conference on Information and Knowledge Management (CIKM 2016)

 

Navid Rekabsaz, Serwah Sabetghadam, Mihai Lupu, Linda Andersson, Allan Hanbury (2016) Standard Test Collection for English-Persian Cross-Lingual Word Sense Disambiguation In Proceedings of the Language Resources and Evaluation Conference (LREC 2016)

 

Linda Andersson, Helena Rastas, Andreas Rauber (2014) Post OCR Correction of Swedish Patent Text - The Difference between Reading Tongue 'Lästunga' and Security Tab 'Låstunga' In Proceedings of Multidisciplinary Information Retrieval,Eds. David Lamas, Paul Buitelaar,Lecture Notes in Computer Science, Springer Berlin Heidelberg, (1-9)

 

Aldo Lipani, Florina Piroi, Linda Andersson, Allan Hanbury (2014) Extracting Nanopublications from IR Papers In Proceedings of Multidisciplinary Information Retrieval, Eds. David Lamas, Paul Buitelaar, Lecture Notes in Computer Science, Springer Berlin Heidelberg, (53-62)

 

Linda Andersson, Mihai Lupu, João Palotti, Florina Piroi, Allan Hanbury, Andreas Rauber (2014) Insight to Hyponymy Lexical Relation Extraction in the Patent Genre Versus Other Text Genres In Proceedings of the First International Workshop on Patent Mining and Its Applications (IPaMin 2014) co-located with Konvens Hildesheim Germany, October 6-7 2014

 

Aldo Lipani, Florina Piroi, Linda Andersson, Allan Hanbury (2014) An Information Retrieval Ontology for Information Retrieval Nanopublications In Proceeding of the of the Conference and Labs of the Evaluation Forum (CLEF2014)

 

João Palotti, Navid Rekabsaz, Linda Andersson, Allan Hanbury (2014) TUW@TREC clinical decision support track In Proceedings of the Twenty-Third Text REtrieval Conference (TREC 2014)

 

Linda Andersson, Mihai Lupu, Allan Hanbury (2013) Domain Adaptation of General Natural Language Processing Tools for a Patent Claim Visualization System In Proceedings of Multidisciplinary Information Retrieval, Eds. Mihai Lupu, Evangelos Kanoulas, Fernando Loizides, Lecture Notes in Computer Science, Springer Berlin Heidelberg, (70-82)

 

Linda Andersson, Parvaz Mahdabi, Allan Hanbury, Andreas Rauber (2013) Exploring patent passage retrieval using nouns phrases In Proceeding of the 35th European conference on Advances in Information Retrieval (ECIR'13), Eds. Pavel Serdyukov, Pavel Braslavski, Sergei O. Kuznetsov, Jaap Kamps, and Stefan Rüger, Springer-Verlag, Berlin, Heidelberg, (676-679)

 

Parvaz Mahdabi, Linda Andersson, Mostafa Keikha, Fabio Crestani (2012) Automatic refinement of patent queries using concept importance predictors In ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2012),(505-514)

 

Linda Andersson, Parvaz Mahdabi, Allan Hanbury, Andreas Rauber (2012) Report on the CLEF-IP 2012 Experiments: Exploring Passage Retrieval with the PIPExtractor In Proceeding of the of the Conference and Labs of the Evaluation Forum (CLEF2012)

 

Parvaz Mahdabi, Linda Andersson, Allan Hanbury, Fabio Crestani (2011) Report on the CLEF-IP 2011 Experiments: Exploring Patent Summarisation In Proceeding of the of the Conference and Labs of the Evaluation Forum (CLEF2011)

 

Linda Andersson (2010) A Vector Space analysis of Swedish patent claims with different linguistic indices In Proceeding of the 3rd International Workshop on Patent Information Retrieval (PaIR), 2010


 

Thesis

 

Linda Andersson (2009) A Vector Space analysis of Swedish patent claims, does decompounding help?
Master thesis, Department of Linguistic, Stockholm University PDF

 

Linda Andersson (2003) Hantering av sammansatta ord vid indexering med två statistiska indexeringsmetoder.
Bachelors thesis, Department of Linguistic, Stockholm University English summary: Performance of Two Statistical Indexing Methods, with and without Compound-word Analysis