Umeå University's logo

umu.sePublications
Change search
Refine search result
1 - 7 of 7
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Aler Tubella, Andrea
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Coelho Mollo, Dimitri
    Umeå University, Faculty of Arts, Department of historical, philosophical and religious studies.
    Dahlgren, Adam
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Devinney, Hannah
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Dignum, Virginia
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Ericson, Petter
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Jonsson, Anna
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Kampik, Timotheus
    Umeå University, Faculty of Science and Technology, Department of Computing Science. SAP Signavio, Germany.
    Lenaerts, Tom
    Université Libre de Bruxelles, Belgium; University of California, Berkeley, USA.
    Mendez, Julian Alfredo
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Nieves, Juan Carlos
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    ACROCPoLis: a descriptive framework for making sense of fairness2023In: FAccT '23: Proceedings of the 2023 ACM conference on fairness, accountability, and transparency, ACM Digital Library, 2023, p. 1014-1025Conference paper (Refereed)
    Abstract [en]

    Fairness is central to the ethical and responsible development and use of AI systems, with a large number of frameworks and formal notions of algorithmic fairness being available. However, many of the fairness solutions proposed revolve around technical considerations and not the needs of and consequences for the most impacted communities. We therefore want to take the focus away from definitions and allow for the inclusion of societal and relational aspects to represent how the effects of AI systems impact and are experienced by individuals and social groups. In this paper, we do this by means of proposing the ACROCPoLis framework to represent allocation processes with a modeling emphasis on fairness aspects. The framework provides a shared vocabulary in which the factors relevant to fairness assessments for different situations and procedures are made explicit, as well as their interrelationships. This enables us to compare analogous situations, to highlight the differences in dissimilar situations, and to capture differing interpretations of the same situation by different stakeholders.

    Download full text (pdf)
    fulltext
  • 2.
    Björklund, Henrik
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Björklund, Johanna
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Dahlgren, Adam
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Demeke, Yonas
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Implementing a speech-to-text pipeline on the MICO platform2016Report (Other academic)
    Abstract [en]

    MICO is an open-source platform for cross-media analysis, querying, and recommendation. It is the major outcome of the European research project Media in Context, and has been contributed to by academic and industrial partners from Germany, Austria, Sweden, Italy, and the UK. A central idea is to group sets of related media objects into multimodal content items, and to process and store these as logical units. The platform is designed to be easy to extend and adapt, and this makes it a useful building block for a diverse set of multimedia applications. To promote the platform and demonstrate its potential, we describe our work on a Kaldi-based speech-recognition pipeline.

    Download full text (pdf)
    fulltext
  • 3.
    Björklund, Johanna
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Dahlgren Lindström, Adam
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Drewes, Frank
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Bridging Perception, Memory, and Inference through Semantic Relations2021In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics (ACL) , 2021, p. 9136-9142Conference paper (Refereed)
    Abstract [en]

    There is a growing consensus that surface form alone does not enable models to learn meaning and gain language understanding. This warrants an interest in hybrid systems that combine the strengths of neural and symbolic methods. We favour triadic systems consisting of neural networks, knowledge bases, and inference engines. The network provides perception, that is, the interface between the system and its environment. The knowledge base provides explicit memory and thus immediate access to established facts. Finally, inference capabilities are provided by the inference engine which reflects on the perception, supported by memory, to reason and discover new facts. In this work, we probe six popular language models for semantic relations and outline a future line of research to study how the constituent subsystems can be jointly realised and integrated.

  • 4.
    Dahlgren Lindström, Adam
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Learning, reasoning, and compositional generalisation in multimodal language models2024Doctoral thesis, monograph (Other academic)
    Abstract [en]

    We humans learn language and how to interact with the world through our different senses, grounding our language in what we can see, touch, hear, and smell. We call these streams of information different modalities, and our efficient processing and synthesis of the interactions between different modalities is a cornerstone of our intelligence. Therefore, it is important to study how we can build multimodal language models, where machine learning models learn from more than just text. This is particularly important in the era of large language models (LLMs), where their general capabilities are unclear and unreliable. This thesis investigates learning and reasoning in multimodal language models, and their capabilities to compositionally generalise in visual question answering tasks. Compositional generalisation is the process in which we produce and understand novel sentences, by systematically combining words and sentences to uncover the meaning in language, and has proven a challenge for neural networks. Previously, the literature has focused on compositional generalisation in text-only language models. One of the main contributions of this work is the extensive investigation of text-image language models. The experiments in this thesis compare three neural network-based models, and one neuro-symbolic method, and operationalise language grounding as the ability to reason with relevant functions over object affordances.

    In order to better understand the capabilities of multimodal models, this thesis introduces CLEVR-Math as a synthetic benchmark of visual mathematical reasoning. The CLEVR-Math dataset involve tasks such as adding and removing objects from 3D scenes based on textual instructions, such as \emph{Remove all blue cubes. How many objects are left?}, and is given as a curriculum of tasks of increasing complexity. The evaluation set of CLEVR-Math includes extensive testing of different functional and object attribute generalisations. We open up the internal representations of these models using a technique called probing, where linear classifiers are trained to recover concepts such as colours or named entities from the internal embeddings of input data. The results show that while models are fairly good at generalisation with attributes (i.e.~solving tasks involving never before seen objects), it is a big challenge to generalise over functions and to learn abstractions such as categories. The results also show that complexity in the training data is a driver of generalisation, where an extended curriculum improves the general performance across tasks and generalisation tests. Furthermore, it is shown that training from scratch versus transfer learning has significant effects on compositional generalisation in models.

    The results identify several aspects of how current methods can be improved in the future, and highlight general challenges in multimodal language models. A thorough investigation of compositional generalisation suggests that the pre-training of models allow models access to inductive biases that can be useful to solve new tasks. Contrastingly, models trained from scratch show much lower overall performance on the synthetic tasks at hand, but show lower relative generalisation gaps. In the conclusions and outlook, we discuss the implications of these results as well as future research directions.

    Download full text (pdf)
    fulltext
    Download (pdf)
    spikblad
  • 5.
    Dahlgren Lindström, Adam
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Abraham, Savitha Sam
    Örebro University, Sweden.
    CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning2022In: CEUR Workshop Proceedings / [ed] d'Avila Garcez A.; Jimenez-Ruiz E.; Jimenez-Ruiz E., CEUR-WS , 2022, Vol. 3212Conference paper (Refereed)
    Abstract [en]

    We introduce CLEVR-Math, a multi-modal math word problems dataset consisting of simple math word problems involving addition/subtraction, represented partly by a textual description and partly by an image illustrating the scenario. The text describes actions performed on the scene that is depicted in the image. Since the question posed may not be about the scene in the image, but about the state of the scene before or after the actions are applied, the solver envision or imagine the state changes due to these actions. Solving these word problems requires a combination of language, visual and mathematical reasoning. We apply state-of-the-art neural and neuro-symbolic models for visual question answering on CLEVR-Math and empirically evaluate their performances. Our results show how neither method generalise to chains of operations. We discuss the limitations of the two in addressing the task of multi-modal word problem solving.

    Download full text (pdf)
    fulltext
  • 6.
    Dahlgren Lindström, Adam
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Björklund, Johanna
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Bensch, Suna
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Drewes, Frank
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Probing Multimodal Embeddings for Linguistic Properties: the Visual-Semantic Case2020In: Proceedings of the 28th International Conference on Computational Linguistics (COLING), 2020, p. 730-744Conference paper (Refereed)
    Abstract [en]

    Semantic embeddings have advanced the state of the art for countless natural language processing tasks, and various extensions to multimodal domains, such as visual-semantic embeddings, have been proposed. While the power of visual-semantic embeddings comes from the distillation and enrichment of information through machine learning, their inner workings are poorly understood and there is a shortage of analysis tools. To address this problem, we generalize the notion of probing tasks to the visual-semantic case. To this end, we (i) discuss the formalization of probing tasks for embeddings of image-caption pairs, (ii) define three concrete probing tasks within our general framework, (iii) train classifiers to probe for those properties, and (iv) compare various state-of-the-art embeddings under the lens of the proposed probing tasks. Our experiments reveal an up to 12% increase in accuracy on visual-semantic embeddings compared to the corresponding unimodal embeddings, which suggest that the text and image dimensions represented in the former do complement each other

    Download full text (pdf)
    fulltext
  • 7.
    Woldemariam, Yonas Demeke
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Dahlgren, Adam
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Adapting language specific components of cross-media analysis frameworks to less-resourced languages: the case of Amharic2020In: Proceedings of the 1st Joint SLTU and CCURL Workshop (SLTU-CCURL 2020) / [ed] Dorothee Beermann; Laurent Besacier; Sakriani Sakti; Claudia Soria, 2020, p. 298-305Conference paper (Refereed)
    Abstract [en]

    We present an ASR based pipeline for Amharic that orchestrates NLP components within a cross media analysis framework (CMAF). One of the major challenges that are inherently associated with CMAFs is effectively addressing multi-lingual issues. As a result, many languages remain under-resourced and fail to leverage out of available media analysis solutions. Although spoken natively by over 22 million people and there is an ever-increasing amount of Amharic multimedia content on the Web, querying them with simple text search is difficult. Searching for, especially audio/video content with simple key words, is even hard as they exist in their raw form. In this study, we introduce a spoken and textual content processing workflow into a CMAF for Amharic. We design an ASR-named entity recognition (NER) pipeline that includes three main components: ASR, a transliterator and NER. We explore various acoustic modeling techniques and develop an OpenNLP-based NER extractor along with a transliterator that interfaces between ASR and NER. The designed ASR-NER pipeline for Amharic promotes the multi-lingual support of CMAFs. Also, the state-of-the art design principles and techniques employed in this study shed light for other less-resourced languages, particularly the Semitic ones.

    Download full text (pdf)
    fulltext
1 - 7 of 7
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf