Jyrki Nummenmaa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jyrki Nummenmaa has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Jaakko Peltonen
Tampere University, Tampere, Finland
4 shared publications - Kostas Stefanidis
Tampere University
4 shared publications - Timo Nummenmaa
Gamification Group, Research Centre of Gameful Realities, Tampere University, Tampere, Finland
4 shared publications Elizaveta Zimina
Tampere University
2 shared publications- Jani Marjanen
University of Helsinki
2 shared publications - Jussi Kurunmäki
Centre for Nordic Studies, University of Helsinki, Helsinki, Finland
2 shared publications
Latest Publications
- 29 September 2026
- Published by Springer Nature
- p. 60-71
Calibrated Multi-agent Consensus for Knowledge Graph Validation Using Open-Source LLM
- 29 September 2026
- Published by Springer Nature
- p. 60-71
Calibrated Multi-agent Consensus for Knowledge Graph Validation Using Open-Source LLM
- Open Access
- 14 January 2026
- Published by Universidad Tecnica de Ambato - Carrera de Medicina in Journal of Emerging & Sustainable Smart Engineering
- Vol. 2 (1)
Editor's letter
- 14 January 2026
- Published by Universidad Tecnica de Ambato - Carrera de Medicina in Journal of Emerging & Sustainable Smart Engineering
- Vol. 2 (1)
Open AccessEditor's letter
- Open Access
- 27 November 2024
- Published by Springer Nature
- p. 171-196
Toward Designing Ethically Acceptable AI Security Systems Through Agent Modeling
AI systems are often complex and they have ethical consequences. We propose careful modeling of the related agents and their ethical concerns for the design of acceptable AI systems. We have worked on an example case of shopping mall security, and we will exemplify our ideas with our case study. Our modeling is based on BDI (belief-desire-intention) theory, philosophical theories of social action, and cognitive research on individual minds and ethics. For our empirical part, we have met and interviewed personnel in a real shopping mall. We aim to give a theoretical basis for considering ethical aspects for the use and design of AI in security.
- 27 November 2024
- Published by Springer Nature
- p. 171-196
Open AccessToward Designing Ethically Acceptable AI Security Systems Through Agent Modeling
AI systems are often complex and they have ethical consequences. We propose careful modeling of the related agents and their ethical concerns for the design of acceptable AI systems. We have worked on an example case of shopping mall security, and we will exemplify our ideas with our case study. Our modeling is based on BDI (belief-desire-intention) theory, philosophical theories of social action, and cognitive research on individual minds and ethics. For our empirical part, we have met and interviewed personnel in a real shopping mall. We aim to give a theoretical basis for considering ethical aspects for the use and design of AI in security.
- 16 June 2024
- Published by Springer Nature
- p. 19-33
TraQuLA: Transparent Question Answering Over RDF Through Linguistic Analysis
- 16 June 2024
- Published by Springer Nature
- p. 19-33
TraQuLA: Transparent Question Answering Over RDF Through Linguistic Analysis
- 16 January 2024
- Published by John Benjamins Publishing Company in Narrative Inquiry
- Vol. 34 (2) , 335-363
Computational recognition of narratives
Computational recognition of narratives, if successful, would find innumerable applications with large digitized datasets. Systematic identification of narratives in the text flow could significantly contribute to such pivotal questions as where, when, and how narratives are employed. This paper discusses an approach to extract narratives from two datasets, Finnish parliamentary records (1980–2021) and oral history interviews with former Finnish MPs (1988–2018). Our study was based on an iterative approach, proceeding from original expert readings to a rule-based, computational approach that was elaborated with the help of annotated samples and annotation scheme. Annotated samples and computationally found extracts were compared, and a good correspondence was found. In this paper, we exhibit and compare the results from annotation and rule-based approach, and discuss examples of correctly and incorrectly found narrative sections. We consider that all attempts at recognizing and extracting narratives are definition dependent, and feed back to narrative theory.
- 16 January 2024
- Published by John Benjamins Publishing Company in Narrative Inquiry
- Vol. 34 (2) , 335-363
Computational recognition of narratives
Computational recognition of narratives, if successful, would find innumerable applications with large digitized datasets. Systematic identification of narratives in the text flow could significantly contribute to such pivotal questions as where, when, and how narratives are employed. This paper discusses an approach to extract narratives from two datasets, Finnish parliamentary records (1980–2021) and oral history interviews with former Finnish MPs (1988–2018). Our study was based on an iterative approach, proceeding from original expert readings to a rule-based, computational approach that was elaborated with the help of annotated samples and annotation scheme. Annotated samples and computationally found extracts were compared, and a good correspondence was found. In this paper, we exhibit and compare the results from annotation and rule-based approach, and discuss examples of correctly and incorrectly found narrative sections. We consider that all attempts at recognizing and extracting narratives are definition dependent, and feed back to narrative theory.
- Open Access
- 1 January 2024
- Published by American Institute of Mathematical Sciences (AIMS) in Applied Computing and Intelligence
- Vol. 4 (1) , 1-18
Linguistic summarisation of multiple entities in RDF graphs
Methods for producing summaries from structured data have gained interest due to the huge volume of available data in the Web. Simultaneously, there have been advances in natural language generation from Resource Description Framework (RDF) data. However, no efforts have been made to generate natural language summaries for groups of multiple RDF entities. This paper describes the first algorithm for summarising the information of a set of RDF entities in the form of human-readable text. The paper also proposes an experimental design for the evaluation of the summaries in a human task context. Experiments were carried out comparing machine-made summaries and summaries written by humans, with and without the help of machine-made summaries. We develop criteria for evaluating the content and text quality of summaries of both types, as well as a function measuring the agreement between machine-made and human-written summaries. The experiments indicated that machine-made natural language summaries can substantially help humans in writing their own textual descriptions of entity sets within a limited time.
- 1 January 2024
- Published by American Institute of Mathematical Sciences (AIMS) in Applied Computing and Intelligence
- Vol. 4 (1) , 1-18
Open AccessLinguistic summarisation of multiple entities in RDF graphs
Methods for producing summaries from structured data have gained interest due to the huge volume of available data in the Web. Simultaneously, there have been advances in natural language generation from Resource Description Framework (RDF) data. However, no efforts have been made to generate natural language summaries for groups of multiple RDF entities. This paper describes the first algorithm for summarising the information of a set of RDF entities in the form of human-readable text. The paper also proposes an experimental design for the evaluation of the summaries in a human task context. Experiments were carried out comparing machine-made summaries and summaries written by humans, with and without the help of machine-made summaries. We develop criteria for evaluating the content and text quality of summaries of both types, as well as a function measuring the agreement between machine-made and human-written summaries. The experiments indicated that machine-made natural language summaries can substantially help humans in writing their own textual descriptions of entity sets within a limited time.
- Open Access
- 27 March 2023
- Published by Qeios Ltd
Review of: "OpenAI ChatGPT Generated Content and Similarity Index: A study of selected terms from the Library & Information Science (LIS)"
The topic is timely as it seems that the question of whether the text generated by Chat GPT will be detected as copying or potential plagiarism by Turnitin. The study is very straightforward - just creating samples of text with Chat GPT and then fee...
- 27 March 2023
- Published by Qeios Ltd
Open AccessReview of: "OpenAI ChatGPT Generated Content and Similarity Index: A study of selected terms from the Library & Information Science (LIS)"
The topic is timely as it seems that the question of whether the text generated by Chat GPT will be detected as copying or potential plagiarism by Turnitin. The study is very straightforward - just creating samples of text with Chat GPT and then fee...
- Open Access
- 5 December 2022
- Published by MDPI AG in Information
- Vol. 13 (12) , 568
Incremental Entity Blocking over Heterogeneous Streaming Data
Web systems have become a valuable source of semi-structured and streaming data. In this sense, Entity Resolution (ER) has become a key solution for integrating multiple data sources or identifying similarities between data items, namely entities. To avoid the quadratic costs of the ER task and improve efficiency, blocking techniques are usually applied. Beyond the traditional challenges faced by ER and, consequently, by the blocking techniques, there are also challenges related to streaming data, incremental processing, and noisy data. To address them, we propose a schema-agnostic blocking technique capable of handling noisy and streaming data incrementally through a distributed computational infrastructure. To the best of our knowledge, there is a lack of blocking techniques that address these challenges simultaneously. This work proposes two strategies (attribute selection and top-n neighborhood entities) to minimize resource consumption and improve blocking efficiency. Moreover, this work presents a noise-tolerant algorithm, which minimizes the impact of noisy data (e.g., typos and misspellings) on blocking effectiveness. In our experimental evaluation, we use real-world pairs of data sources, including a case study that involves data from Twitter and Google News. The proposed technique achieves better results regarding effectiveness and efficiency compared to the state-of-the-art technique (metablocking). More precisely, the application of the two strategies over the proposed technique alone improves efficiency by 56%, on average.
- 5 December 2022
- Published by MDPI AG in Information
- Vol. 13 (12) , 568
Open AccessIncremental Entity Blocking over Heterogeneous Streaming Data
Web systems have become a valuable source of semi-structured and streaming data. In this sense, Entity Resolution (ER) has become a key solution for integrating multiple data sources or identifying similarities between data items, namely entities. To avoid the quadratic costs of the ER task and improve efficiency, blocking techniques are usually applied. Beyond the traditional challenges faced by ER and, consequently, by the blocking techniques, there are also challenges related to streaming data, incremental processing, and noisy data. To address them, we propose a schema-agnostic blocking technique capable of handling noisy and streaming data incrementally through a distributed computational infrastructure. To the best of our knowledge, there is a lack of blocking techniques that address these challenges simultaneously. This work proposes two strategies (attribute selection and top-n neighborhood entities) to minimize resource consumption and improve blocking efficiency. Moreover, this work presents a noise-tolerant algorithm, which minimizes the impact of noisy data (e.g., typos and misspellings) on blocking effectiveness. In our experimental evaluation, we use real-world pairs of data sources, including a case study that involves data from Twitter and Google News. The proposed technique achieves better results regarding effectiveness and efficiency compared to the state-of-the-art technique (metablocking). More precisely, the application of the two strategies over the proposed technique alone improves efficiency by 56%, on average.
- Open Access
- 6 October 2022
- Published by University of Oslo Library in Digital Humanities in the Nordic and Baltic Countries Publications
- Vol. 4 (1) , 406-414
Analyzing Temporalities in Parliamentary Speech about Ideologies Using Dependency Parsed Data
The temporal aspects of politics have been discussed extensively by political theorists, but have not been explored using grammatically parsed textual datasets. This paper explores the ways in which future, present and past are projected and referred to in speeches in the Finnish parliament that talk about ideologies. Ideologies are crucial categories of thinking about the political past and future and therefore serve as a case in which temporality is expressed in a variety of ways. We use a dataset drawn from Finnish parliamentary records from 1980 to 2021 and operationalize morpho-syntactic information on clause structures and grammatical tense system to explore the different temporal profiles of ideologies. We show how some isms, like communism and fascism, are much more likely to appear in the context of the past, whereas others, like capitalism and racism, tend to appear in the present tense. We further develop a framework for analyzing temporality based on clause structures and grammatical tense and relate that to how the study of politics has approached time in parliamentary speaking.
- 6 October 2022
- Published by University of Oslo Library in Digital Humanities in the Nordic and Baltic Countries Publications
- Vol. 4 (1) , 406-414
Open AccessAnalyzing Temporalities in Parliamentary Speech about Ideologies Using Dependency Parsed Data
The temporal aspects of politics have been discussed extensively by political theorists, but have not been explored using grammatically parsed textual datasets. This paper explores the ways in which future, present and past are projected and referred to in speeches in the Finnish parliament that talk about ideologies. Ideologies are crucial categories of thinking about the political past and future and therefore serve as a case in which temporality is expressed in a variety of ways. We use a dataset drawn from Finnish parliamentary records from 1980 to 2021 and operationalize morpho-syntactic information on clause structures and grammatical tense system to explore the different temporal profiles of ideologies. We show how some isms, like communism and fascism, are much more likely to appear in the context of the past, whereas others, like capitalism and racism, tend to appear in the present tense. We further develop a framework for analyzing temporality based on clause structures and grammatical tense and relate that to how the study of politics has approached time in parliamentary speaking.