VPP – State Research Program
Header

On July 8, 3 pm Institute of Mathematics and Computer Science will host a seminar in auditorium 210 , titled: „Development of ontology-based knowledge engineering technologies suitable for web environment” as part of the “Cyber-physical systems, ontologies and biophotonics for safe&smart city and society” (SOPHIS), a program funded by the National Research Program.
Agenda:

1. Ontology-based modelling technologies and tools for knowledge analysis suitable for web environment(IMCS) – J.Bārzdiņš, A.Šostaks, E.Rencis, M.Grasmanis, A.Sproģis
2. Ontology-based methods for mining semantics of natural language. (IMCS) – G.Bārzdiņš, D.Goško, P.Paikens.
3. Semantic web technologies for knowledge formalization, reuse and sharing. (FCSIT) – J.Grundspeņķis, V.Graudiņa, M.Kirikova, A.Novickis
4. Novel data query and visualization methods and related challenges for web environment. (FC) – J.Bičevskis, G.Arnicāns, Ģ.Karnītis

Knowledge formalization is one of the main tasks in research of systems complexity. It is usually based on the development and analysis of different kind of models. Structural modeling (SM) is proposed as a succesfull approach which manages this task. The main idea of SM is building and analysis of mutually transformable models. Therefore an appropriate software for development and analysis of models has been launched by RTU FCSIT .

Software architecture

Software architecture

Software architecture

(more…)

With semantic parsing technologies developed within Project Nr.2 of the National Research Programme SOPHIS we have achieved sufficient international recognition to be able to participate in a high-quality consortium in the area of BigData. Together with BBC, Deutche Welle, Univerity of Edinburgh, University Colledge of London, IDIAP from Switzerland, and Priberam from Portugal we have prepared an H2020 ICT-16 proposal on BigData media-monitoring.

UL IMCS participated in International Workshop on Semantic Evaluation (SemEval-2015) and specifically in Task 18 on Broad-Coverage Semantic Dependency Parsing (SDP 2015). Broad-coverage semantic dependency parsing is the task of recovering sentence-internal predicate–argument relationships for all content words, i.e. the semantic structure constituting the relational core of sentence meaning. SDP 2015 competition provided training data and evaluated SDP parsers for English, Czech, and Chinese languages.

The FrameNet based semantic parsing technology for Latvian developed within the National Research Programme is already exploited industrially through partnership projects with Latvian News Agency (LETA) and is described in several scientific papers ublished in international conferences. Meanwhile none of this provided an independent verification for the quality of our semantic parsing technology compared to the best parsing systems in the world. To clarify this and to rise the international recognition for UL IMCS achievements, we took part in the above-mentioned SemEval-2015, Task 18 international competition, where research teams from whole world compete to achieve the best parsing results for shared semantic parsing tasks.

Results of Sem Eval 2015

Results of Sem Eval 2015

We (Riga-team) are proud to finish this competition among the three best teams with results largely on par with Peking and Lisbon research teams. In this and last year SDP competitions took part more than 10 reasearch teams, including Cornegie Mellon University (CMU) from US, which was considered the leader in FrameNet semantic parsing. Results are available at http://svn.emmtee.net/sdp/public/2015/scores.ods . It is interesting to note that although we (Riga-team) were third on the official LF metric „F1-score for labeled graphs”, in other parameters we were first. For example, for the proportion of completely correctly parsed sentences in Chinese (LM metric: labeled exact match) we were first with slightly better result than Peking team.

A paper describing our system has been accepted for publication in NAACL’2015 conference

Some initial results of SOPHIS Project No.2 „Ontology-based knowledge engineering technologies suitable for web environment” have been presented at:

Arturs Bartusevics, Andrejs Lesovskis, Leonids Novickis. Model-Driven Software Configuration Management and Semantic Web in Applied Software Development. 10th International Conference on EDUCATIONAL TECHNOLOGIES (EDUTE ’14)Istanbul, Turkey, December 15-17, 2014.

Within SOPHIS Project No.2 „Ontology-based knowledge engineering technologies suitable for web environment” Institute of Mathematics and Computer Science (IMCS) has developed the CCUH data ontology which describes the episodes of inpatient and outpatient treatment in the hospital. Ontology will be used in the implementation of ad hoc query language designed for the needs of physicians of CCUH.

the CCUH data ontology which describes the episodes of inpatient and outpatient treatment in the hospital.

The CCUH data ontology which describes the episodes of inpatient and outpatient treatment in the hospital.

February 20, 2015 the results of SOPHIS Project No.2 „Ontology-based knowledge engineering technologies suitable for web environment” have been presented in the computer science and information technology section of 73rd Scientific Conference of University of Latvia.

  • I. Odītis, J. BičevskisRuntime Verification
  • R. Bundulis, G. ArnicānsUse of virtualization in development of high resolution display wall

February 13, 2015 the results of SOPHIS Project No.2 „Ontology-based knowledge engineering technologies suitable for web environment” have been presented in the computer science and information technology section of 73rd Scientific Conference of University of Latvia.

  • Jānis Bārzdiņš, M. Grasmanis, M. Opmanis, E. Rencis, A. Šostaks, Juris Bārzdiņš – Ontology-based ad hoc query language and its implementation: hospital’s case
  • K. Čerāns, G. Bārzdiņš, G. Būmans, J. Ovčiņņikova, A. Romāne, M. Zviedris – Semantic databeses: opportunities and challanges.

February 12, 2015 the results of SOPHIS Project No.2 „Ontology-based knowledge engineering technologies suitable for web environment” have been presented in the computer linguistics section of 73rd Scientific Conference of University of Latvia.

  • P. Paikens Possibilities of usage of computerized lexical resources
  • D. Goško, G. Bārzdiņš Application of rule-based classification in the language processing

Within SOPHIS Project No.2 „Ontology-based knowledge engineering technologies suitable for web environment” Institute of Mathematics and Computer Science (IMCS) has used the prototype of the developed ad hoc query language and tool in the Children’s Clinical University Hospital’s (CCUH) Anesthesiology and Intensive Care Clinic for the data analysis and report preparation. The first results showed that professionals with no more experience in data processing technologies than using spreadsheet tables themselves could formulate appropriate queries. At the same time the experiments showed the existing problems in the query language implementations.

December 12, 2014 the Institute of Mathematics and Computer Science (IMCS) leading researcher Dr.sc.comp. Agris Šostaks met with Nora Kaufmane – head of Department of Medical Statistics and E-health in Children’s Clinical University Hospital (CCUH) in order to discuss the possibilities of approbation of ontology-based ad hoc query language which is being developed within SOPHIS Project No.2 „Ontology-based knowledge engineering technologies suitable for web environment”.

Results of the meeting are agreement on the CCUH data ontology development and approbation of query language together with physicians on the real data of CCUH.