Umeå University's logo

umu.sePublications
Change search
Link to record
Permanent link

Direct link
Alternative names
Publications (10 of 68) Show all publications
Häglund, E. & Björklund, J. (2024). AI-driven contextual advertising: toward relevant messaging without personal data. Journal of Current Issues and Research in Advertising
Open this publication in new window or tab >>AI-driven contextual advertising: toward relevant messaging without personal data
2024 (English)In: Journal of Current Issues and Research in Advertising, ISSN 1064-1734Article in journal (Refereed) Epub ahead of print
Abstract [en]

In programmatic advertising, bids are increasingly based on knowledge of the surrounding media context. This shift toward contextual advertising is in part a counter-reaction to the current dependency on personal data, which is problematic from legal and ethical standpoints. The transition is accelerated by developments in artificial intelligence (AI), which allow for a deeper semantic analysis of the context and, by extension, more effective ad placement. We survey existing literature on the influence of context on the reception of an advertisement, focusing on three context factors: the applicability of the content and the ad, the affective tone of the content, and the involvement of the consumer. We then discuss how AI can leverage these priming effects to optimize ad placement through techniques such as reinforcement learning, data clustering, and sentiment analysis. This helps close the gap between the state of the art in advertising technology and the AI-driven targeting methodologies described in prior academic research.

Place, publisher, year, edition, pages
Routledge, 2024
National Category
Computer Sciences
Identifiers
urn:nbn:se:umu:diva-224265 (URN)10.1080/10641734.2024.2334939 (DOI)001209522500001 ()2-s2.0-85192195055 (Scopus ID)
Available from: 2024-05-14 Created: 2024-05-14 Last updated: 2024-05-14
Berglund, M., Björklund, H. & Björklund, J. (2024). Parsing unranked tree languages, folded once. Algorithms, 17(6), Article ID 268.
Open this publication in new window or tab >>Parsing unranked tree languages, folded once
2024 (English)In: Algorithms, E-ISSN 1999-4893, Vol. 17, no 6, article id 268Article in journal (Refereed) Published
Abstract [en]

A regular unranked tree folding consists of a regular unranked tree language and a folding operation that merges (i.e., folds) selected nodes of a tree to form a graph; the combination is a formal device for representing graph languages. If, in the process of folding, the order among edges is discarded so that the result is an unordered graph, then two applications of a fold operation are enough to make the associated parsing problem NP-complete. However, if the order is kept, then the problem is solvable in non-uniform polynomial time. In this paper, we address the remaining case, where only one fold operation is applied, but the order among the edges is discarded. We show that, under these conditions, the problem is solvable in non-uniform polynomial time.

Place, publisher, year, edition, pages
MDPI, 2024
Keywords
graphs, transducers, trees, vector addition systems
National Category
Computer Sciences
Identifiers
urn:nbn:se:umu:diva-227569 (URN)10.3390/a17060268 (DOI)2-s2.0-85196886791 (Scopus ID)
Funder
Swedish Research Council, 2020-03852Wallenberg AI, Autonomous Systems and Software Program (WASP)Knut and Alice Wallenberg Foundation
Note

This paper is an extended version of a paper published in International Symposium on Fundamentals of Computation Theory, Trier, Germany, 18–21 September.

Available from: 2024-07-02 Created: 2024-07-02 Last updated: 2024-07-02Bibliographically approved
Ryazanov, I. & Björklund, J. (2024). Thesis Proposal: Detecting Agency Attribution. In: Neele Falk; Sara Papi; Mike Zhang (Ed.), Proceedings of the 18th conference of the European chapter of the association for computational linguistics: student research workshop. Paper presented at 18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024, St. Julian’s, Malta, March 17-22, 2024 (pp. 208-214). Association for Computational Linguistics (ACL)
Open this publication in new window or tab >>Thesis Proposal: Detecting Agency Attribution
2024 (English)In: Proceedings of the 18th conference of the European chapter of the association for computational linguistics: student research workshop / [ed] Neele Falk; Sara Papi; Mike Zhang, Association for Computational Linguistics (ACL) , 2024, p. 208-214Conference paper, Published paper (Refereed)
Abstract [en]

We explore computational methods for perceived agency attribution in natural language data. We consider ‘agency’ as the freedom and capacity to act, and the corresponding Natural Language Processing (NLP) task involves automatically detecting attributions of agency to entities in text. Our theoretical framework draws on semantic frame analysis, role labelling and related techniques. In initial experiments, we focus on the perceived agency of AI systems. To achieve this, we analyse a dataset of English-language news coverage of AI-related topics, published within one year surrounding the release of the Large Language Model-based service ChatGPT, a milestone in the general public’s awareness of AI. Building on this, we propose a schema to annotate a dataset for agency attribution and formulate additional research questions to answer by applying NLP models.

Place, publisher, year, edition, pages
Association for Computational Linguistics (ACL), 2024
National Category
Language Technology (Computational Linguistics) Computer Sciences
Identifiers
urn:nbn:se:umu:diva-222874 (URN)2-s2.0-85188728107 (Scopus ID)9798891760905 (ISBN)
Conference
18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024, St. Julian’s, Malta, March 17-22, 2024
Funder
Marianne and Marcus Wallenberg FoundationWallenberg AI, Autonomous Systems and Software Program (WASP)
Available from: 2024-04-16 Created: 2024-04-16 Last updated: 2024-04-16Bibliographically approved
Björklund, H., Björklund, J. & Ericson, P. (2024). Tree-based generation of restricted graph languages. International Journal of Foundations of Computer Science, 35(1 & 2), 215-243
Open this publication in new window or tab >>Tree-based generation of restricted graph languages
2024 (English)In: International Journal of Foundations of Computer Science, ISSN 0129-0541, Vol. 35, no 1 & 2, p. 215-243Article in journal (Refereed) Published
Abstract [en]

Order-preserving DAG grammars (OPDGs) is a formalism for representing languages of structurally restricted graphs. As demonstrated in [17], they are sufficiently expressive to model abstract meaning representations in natural language processing, a graph-based form of semantic representation in which nodes encode objects and edges relations. At the same time, they can be parsed in O (n2 + nm) , where m and n are the sizes of the grammar and the input graph, respectively. In this work, we provide an initial algebra semantic for OPDGs, which allows us to view them as regular tree grammars under an equivalence theory. This makes it possible to transfer results from the field of formal tree languages to the domain of OPDGs, both in the unweighted and the weighted case. In particular, we show that deterministic OPDGs can be minimised efficiently, and that they are learnable under the \minimal adequeate teacher" paradigm, that is, by querying an oracle for equivalence between languages, and membership of individual graphs. To conclude, we demonstrate that the languages generated by OPDGs are definable in monadic second-order logic.

Place, publisher, year, edition, pages
World Scientific, 2024
Keywords
Graph languages, logic characterisation, MAT learning, minimization
National Category
Computer Sciences
Identifiers
urn:nbn:se:umu:diva-217981 (URN)10.1142/S0129054123480106 (DOI)001109806500001 ()2-s2.0-85178101785 (Scopus ID)
Funder
Swedish Research Council, 2020-03852Wallenberg AI, Autonomous Systems and Software Program (WASP), Nest project Sting
Available from: 2023-12-15 Created: 2023-12-15 Last updated: 2024-05-14Bibliographically approved
Andersson, E., Björklund, J., Drewes, F. & Jonsson, A. (2023). Generating semantic graph corpora with graph expansion grammar. In: Nagy B., Freund R. (Ed.), 13th International Workshop on Non-Classical Models of Automata and Applications (NCMA 2023): . Paper presented at 13th International Workshop on Non-Classical Models of Automata and Applications, NCMA 2023, 18-19 September, 2023, Famagusta, Cyprus (pp. 3-15). Open Publishing Association, 388
Open this publication in new window or tab >>Generating semantic graph corpora with graph expansion grammar
2023 (English)In: 13th International Workshop on Non-Classical Models of Automata and Applications (NCMA 2023) / [ed] Nagy B., Freund R., Open Publishing Association , 2023, Vol. 388, p. 3-15Conference paper, Published paper (Refereed)
Abstract [en]

We introduce LOVELACE, a tool for creating corpora of semantic graphs.The system uses graph expansion grammar as  a representational language, thus allowing users to craft a grammar that describes a corpus with desired properties. When given such grammar as input, the system generates a set of output graphs that are well-formed according to the grammar, i.e., a graph bank.The generation process can be controlled via a number of configurable parameters that allow the user to, for example, specify a range of desired output graph sizes.Central use cases are the creation of synthetic data to augment existing corpora, and as a pedagogical tool for teaching formal language theory. 

Place, publisher, year, edition, pages
Open Publishing Association, 2023
Series
Electronic Proceedings in Theoretical Computer Science, ISSN 2075-2180
Keywords
semantic representation, graph corpora, graph grammar
National Category
Language Technology (Computational Linguistics)
Research subject
Computer Science
Identifiers
urn:nbn:se:umu:diva-212143 (URN)10.4204/EPTCS.388.3 (DOI)2-s2.0-85173059788 (Scopus ID)
Conference
13th International Workshop on Non-Classical Models of Automata and Applications, NCMA 2023, 18-19 September, 2023, Famagusta, Cyprus
Funder
Swedish Research Council, 2020-03852
Available from: 2023-07-18 Created: 2023-07-18 Last updated: 2023-10-18Bibliographically approved
Björklund, J., Drewes, F. & Jonsson, A. (2023). Generation and polynomial parsing of graph languages with non-structural reentrancies. Computational linguistics - Association for Computational Linguistics (Print), 49(4), 841-882
Open this publication in new window or tab >>Generation and polynomial parsing of graph languages with non-structural reentrancies
2023 (English)In: Computational linguistics - Association for Computational Linguistics (Print), ISSN 0891-2017, E-ISSN 1530-9312, Vol. 49, no 4, p. 841-882Article in journal (Refereed) Published
Abstract [en]

Graph-based semantic representations are popular in natural language processing (NLP), where it is often convenient to model linguistic concepts as nodes and relations as edges between them. Several attempts have been made to find a generative device that is sufficiently powerful to describe languages of semantic graphs, while at the same allowing efficient parsing. We contribute to this line of work by introducing graph extension grammar, a variant of the contextual hyperedge replacement grammars proposed by Hoffmann et al. Contextual hyperedge replacement can generate graphs with non-structural reentrancies, a type of node-sharing that is very common in formalisms such as abstract meaning representation, but which context-free types of graph grammars cannot model. To provide our formalism with a way to place reentrancies in a linguistically meaningful way, we endow rules with logical formulas in counting monadic second-order logic. We then present a parsing algorithm and show as our main result that this algorithm runs in polynomial time on graph languages generated by a subclass of our grammars, the so-called local graph extension grammars.

Place, publisher, year, edition, pages
Association for Computational Linguistics, 2023
Keywords
Graph grammar, semantic graph, meaning representation, graph parsing
National Category
Language Technology (Computational Linguistics)
Research subject
Computer Science; computational linguistics
Identifiers
urn:nbn:se:umu:diva-209515 (URN)10.1162/coli_a_00488 (DOI)001152974700005 ()2-s2.0-85173016925 (Scopus ID)
Projects
STING – Synthesis and analysis with Transducers and Invertible Neural Generators
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)Swedish Research Council, 2020-03852
Available from: 2023-06-10 Created: 2023-06-10 Last updated: 2024-02-19Bibliographically approved
Ryazanov, I. & Björklund, J. (2023). How does the language of 'threat' vary across news domains?: a semi-supervised pipeline for understanding narrative components in news contexts. In: Håkan Grahn; Anton Borg; Martin Boldt (Ed.), SAIS 2023: 35th Annual Workshop of the Swedish Artificial Intelligence Society. Paper presented at SAIS 2023, 35th Annual Workshop of the Swedish Artificial Intelligence Society, Karlskrona, Sweden, June 12-13, 2023 (pp. 94-99). Swedish Artificial Intelligence Society
Open this publication in new window or tab >>How does the language of 'threat' vary across news domains?: a semi-supervised pipeline for understanding narrative components in news contexts
2023 (English)In: SAIS 2023: 35th Annual Workshop of the Swedish Artificial Intelligence Society / [ed] Håkan Grahn; Anton Borg; Martin Boldt, Swedish Artificial Intelligence Society , 2023, p. 94-99Conference paper, Published paper (Refereed)
Abstract [en]

By identifying and characterising the narratives told in news media we can better understand political and societal processes. The problem is challenging from the perspective of natural language processing because it requires a combination of quantitative and qualitative methods. This paper reports on work in progress, which aims to build a human-in-the-loop pipeline for analysing how the variation of narrative themes across different domains, based on topic modelling and word embeddings. As an illustration, we study the language associated with the threat narrative in British news media.

Place, publisher, year, edition, pages
Swedish Artificial Intelligence Society, 2023
Series
Linköping Electronic Conference Proceedings, ISSN 1650-3686, E-ISSN 1650-3740
Keywords
topic modelling, natural language processing, narrative analysis, text embeddings
National Category
Computer Sciences Language Technology (Computational Linguistics)
Research subject
computational linguistics; Computer Science
Identifiers
urn:nbn:se:umu:diva-213801 (URN)10.3384/ecp199010 (DOI)978-91-8075-274-9 (ISBN)
Conference
SAIS 2023, 35th Annual Workshop of the Swedish Artificial Intelligence Society, Karlskrona, Sweden, June 12-13, 2023
Available from: 2023-08-29 Created: 2023-08-29 Last updated: 2023-08-29Bibliographically approved
Berglund, M., Björklund, H. & Björklund, J. (2023). Parsing unranked tree languages, folded once. In: Henning Fernau; Klaus Jansen (Ed.), Fundamentals of computation theory: 24th International Symposium, FCT 2023, Trier, Germany, September 18–21, 2023, Proceedings. Paper presented at 24th International Symposium on Fundamentals of Computation Theory, FCT 2023, Trier, Germany, September 18–21, 2023 (pp. 60-73). Springer Nature
Open this publication in new window or tab >>Parsing unranked tree languages, folded once
2023 (English)In: Fundamentals of computation theory: 24th International Symposium, FCT 2023, Trier, Germany, September 18–21, 2023, Proceedings / [ed] Henning Fernau; Klaus Jansen, Springer Nature, 2023, p. 60-73Conference paper, Published paper (Refereed)
Abstract [en]

A regular unranked tree folding consists of a regular unranked tree language and a folding operation that merges, i.e., folds, selected nodes of a tree to form a graph; the combination is a formal device for representing graph languages. If, in the process of folding, the order among edges is discarded so that the result is an unordered graph, then two applications of a fold operation is enough to make the associated parsing problem NP-complete. However, if the order is kept, then the problem is solvable in non-uniform polynomial time. In this paper we address the remaining case where only one fold operation is applied, but the order among edges is discarded. We show that under these conditions, the problem is solvable in non-uniform polynomial time.

Place, publisher, year, edition, pages
Springer Nature, 2023
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 14292
National Category
Computer Sciences
Identifiers
urn:nbn:se:umu:diva-215936 (URN)10.1007/978-3-031-43587-4_5 (DOI)2-s2.0-85174590997 (Scopus ID)9783031435867 (ISBN)
Conference
24th International Symposium on Fundamentals of Computation Theory, FCT 2023, Trier, Germany, September 18–21, 2023
Available from: 2023-11-02 Created: 2023-11-02 Last updated: 2023-11-02Bibliographically approved
Kristan, M., Matas, J., Danelljan, M., Felsberg, M., Chang, H. J., Zajc, L. Č., . . . Zuo, K. (2023). The first visual object tracking segmentation VOTS2023 challenge results. In: 2023 IEEE/CVF International conference on computer vision workshops (ICCVW): . Paper presented at International Conference on Computer Vision, Paris, France, October 2-6, 2023 (pp. 1788-1810). Institute of Electrical and Electronics Engineers Inc.
Open this publication in new window or tab >>The first visual object tracking segmentation VOTS2023 challenge results
Show others...
2023 (English)In: 2023 IEEE/CVF International conference on computer vision workshops (ICCVW), Institute of Electrical and Electronics Engineers Inc. , 2023, p. 1788-1810Conference paper, Published paper (Refereed)
Abstract [en]

The Visual Object Tracking Segmentation VOTS2023 challenge is the eleventh annual tracker benchmarking activity of the VOT initiative. This challenge is the first to merge short-term and long-term as well as single-target and multiple-target tracking with segmentation masks as the only target location specification. A new dataset was created; the ground truth has been withheld to prevent overfitting. New performance measures and evaluation protocols have been created along with a new toolkit and an evaluation server. Results of the presented 47 trackers indicate that modern tracking frameworks are well-suited to deal with convergence of short-term and long-term tracking and that multiple and single target tracking can be considered a single problem. A leaderboard, with participating trackers details, the source code, the datasets, and the evaluation kit are publicly available at the challenge website1

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2023
Series
International Conference on Computer Vision Workshops (ICCV Workshops)
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:umu:diva-220443 (URN)10.1109/ICCVW60793.2023.00195 (DOI)2-s2.0-85175967599 (Scopus ID)9798350307443 (ISBN)
Conference
International Conference on Computer Vision, Paris, France, October 2-6, 2023
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)
Available from: 2024-02-13 Created: 2024-02-13 Last updated: 2024-02-13Bibliographically approved
Björklund, J. (2023). The impact of state merging on predictive accuracy in probabilistic tree automata: Dietze’s conjecture revisited. In: Henning Fernau; Klaus Jansen (Ed.), Fundamentals of computation theory: 24th International Symposium, FCT 2023, Trier, Germany, September 18–21, 2023, Proceedings. Paper presented at 24th International Symposium on Fundamentals of Computation Theory, FCT 2023, Trier, Germany, September 18–21, 2023 (pp. 74-87). Springer Nature
Open this publication in new window or tab >>The impact of state merging on predictive accuracy in probabilistic tree automata: Dietze’s conjecture revisited
2023 (English)In: Fundamentals of computation theory: 24th International Symposium, FCT 2023, Trier, Germany, September 18–21, 2023, Proceedings / [ed] Henning Fernau; Klaus Jansen, Springer Nature, 2023, p. 74-87Conference paper, Published paper (Refereed)
Abstract [en]

Dietze’s conjecture concerns the problem of equipping a tree automaton M with weights to make it probabilistic, in such a way that the resulting automaton N predicts a given corpus C as accurately as possible. The conjecture states that the accuracy cannot increase if the states in M are merged with respect to an equivalence relation ∼ so that the result is a smaller automaton M∼. Put differently, merging states can never improve predictions. This is under the assumption that both M and M∼ are bottom-up deterministic and accept every tree in C. We prove that the conjecture holds, using a construction that turns any probabilistic version N∼ of M∼ into a probabilistic version N of M, such that N assigns at least as great a weight to each tree in C as N∼ does.

Place, publisher, year, edition, pages
Springer Nature, 2023
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 14292
Keywords
Probability distributions, Statistical ML, Tree automata
National Category
Computer Sciences Discrete Mathematics
Identifiers
urn:nbn:se:umu:diva-215917 (URN)10.1007/978-3-031-43587-4_6 (DOI)2-s2.0-85174586168 (Scopus ID)978-3-031-43586-7 (ISBN)978-3-031-43587-4 (ISBN)
Conference
24th International Symposium on Fundamentals of Computation Theory, FCT 2023, Trier, Germany, September 18–21, 2023
Available from: 2023-11-02 Created: 2023-11-02 Last updated: 2023-11-02Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-8503-0118

Search in DiVA

Show all publications