Arrow Research search

Author name cluster

Matthias Samwald

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers
2 author rows

Possible papers

7

EAAI Journal 2024 Journal Article

Model-agnostic explainable artificial intelligence for object detection in image data

  • Milad Moradi
  • Ke Yan
  • David Colwell
  • Matthias Samwald
  • Rhona Asgari

In recent years, deep neural networks have been widely used for building high-performance Artificial Intelligence (AI) systems for computer vision applications. Object detection is a fundamental task in computer vision, which has been greatly progressed through developing large and intricate AI models. However, the lack of transparency is a big challenge that may not allow the widespread adoption of these models. Explainable artificial intelligence is a field of research where methods are developed to help users understand the behavior, decision logics, and vulnerabilities of AI systems. Previously, few explanation methods were developed for object detection based on random masking. However, random masks may raise some issues regarding the actual importance of pixels within an image. In this paper, we design and implement a black-box explanation method named Black-box Object Detection Explanation by Masking (BODEM) through adopting a hierarchical random masking approach for object detection systems. We propose a hierarchical random masking framework in which coarse-grained masks are used in lower levels to find salient regions within an image, and fine-grained mask are used to refine the salient regions in higher levels. Experimentations on various object detection datasets and models showed that BODEM can effectively explain the behavior of object detectors. Moreover, our method outperformed Detector Randomized Input Sampling for Explanation (D-RISE) and Local Interpretable Model-agnostic Explanations (LIME) with respect to different quantitative measures of explanation effectiveness. The experimental results demonstrate that BODEM can be an effective method for explaining and validating object detection systems in black-box testing scenarios.

Details DOI

NeurIPS Conference 2023 Conference Paper

CSMeD: Bridging the Dataset Gap in Automated Citation Screening for Systematic Literature Reviews

  • Wojciech Kusa
  • Oscar E. Mendoza
  • Matthias Samwald
  • Petr Knoth
  • Allan Hanbury

Systematic literature reviews (SLRs) play an essential role in summarising, synthesising and validating scientific evidence. In recent years, there has been a growing interest in using machine learning techniques to automate the identification of relevant studies for SLRs. However, the lack of standardised evaluation datasets makes comparing the performance of such automated literature screening systems difficult. In this paper, we analyse the citation screening evaluation datasets, revealing that many of the available datasets are either too small, suffer from data leakage or have limited applicability to systems treating automated literature screening as a classification task, as opposed to, for example, a retrieval or question-answering task. To address these challenges, we introduce CSMED, a meta-dataset consolidating nine publicly released collections, providing unified access to 325 SLRs from the fields of medicine and computer science. CSMED serves as a comprehensive resource for training and evaluating the performance of automated citation screening models. Additionally, we introduce CSMED-FT, a new dataset designed explicitly for evaluating the full text publication screening task. To demonstrate the utility of CSMED, we conduct experiments and establish baselines on new datasets.

PDF Details

NeurIPS Conference 2022 Conference Paper

BigBio: A Framework for Data-Centric Biomedical Natural Language Processing

  • Jason Fries
  • Leon Weber
  • Natasha Seelam
  • Gabriel Altay
  • Debajyoti Datta
  • Samuele Garda
  • Sunny Kang
  • Rosaline Su

Training and evaluating language models increasingly requires the construction of meta-datasets -- diverse collections of curated data with clear provenance. Natural language prompting has recently lead to improved zero-shot generalization by transforming existing, supervised datasets into a variety of novel instruction tuning tasks, highlighting the benefits of meta-dataset curation. While successful in general-domain text, translating these data-centric approaches to biomedical language modeling remains challenging, as labeled biomedical datasets are significantly underrepresented in popular data hubs. To address this challenge, we introduce BigBio a community library of 126+ biomedical NLP datasets, currently covering 13 task categories and 10+ languages. BigBio facilitates reproducible meta-dataset curation via programmatic access to datasets and their metadata, and is compatible with current platforms for prompt engineering and end-to-end few/zero shot language model evaluation. We discuss our process for task schema harmonization, data auditing, contribution guidelines, and outline two illustrative use cases: zero-shot evaluation of biomedical prompts and large-scale, multi-task learning. BigBio is an ongoing community effort and is available at https: //github. com/bigscience-workshop/biomedical

PDF Details

JBHI Journal 2021 Journal Article

Explaining Black-Box Models for Biomedical Text Classification

  • Milad Moradi
  • Matthias Samwald

In this paper, we propose a novel method named Biomedical Confident Itemsets Explanation (BioCIE), aiming at post-hoc explanation of black-box machine learning models for biomedical text classification. Using sources of domain knowledge and a confident itemset mining method, BioCIE discretizes the decision space of a black-box into smaller subspaces and extracts semantic relationships between the input text and class labels in different subspaces. Confident itemsets discover how biomedical concepts are related to class labels in the black-box's decision space. BioCIE uses the itemsets to approximate the black-box's behavior for individual predictions. Optimizing fidelity, interpretability, and coverage measures, BioCIE produces class-wise explanations that represent decision boundaries of the black-box. Results of evaluations on various biomedical text classification tasks and black-box models demonstrated that BioCIE can outperform perturbation-based and decision set methods in terms of producing concise, accurate, and interpretable explanations. BioCIE improved the fidelity of instance-wise and class-wise explanations by 11. 6% and 7. 5%, respectively. It also improved the interpretability of explanations by 8%. BioCIE can be effectively used to explain how a black-box biomedical text classification model semantically relates input texts to class labels. The source code and supplementary material are available at https://github.com/mmoradi-iut/BioCIE.

Details DOI

ECAI Conference 2020 Conference Paper

Dividing the Ontology Alignment Task with Semantic Embeddings and Logic-Based Modules

  • Ernesto Jiménez-Ruiz
  • Asan Agibetov
  • Jiaoyan Chen 0001
  • Matthias Samwald
  • Valerie Cross

Large ontologies still pose serious challenges to state-of-the-art ontology alignment systems. In this paper we present an approach that combines a neural embedding model and logic-based modules to accurately divide an input ontology matching task into smaller and more tractable matching (sub)tasks. We have conducted a comprehensive evaluation using the datasets of the Ontology Alignment Evaluation Initiative. The results are encouraging and suggest that the proposed method is adequate in practice and can be integrated within the workflow of systems unable to cope with very large ontologies.

Details

AIIM Journal 2010 Journal Article

Semantic SenseLab: Implementing the vision of the Semantic Web in neuroscience

  • Matthias Samwald
  • Huajun Chen
  • Alan Ruttenberg
  • Ernest Lim
  • Luis Marenco
  • Perry Miller
  • Gordon Shepherd
  • Kei-Hoi Cheung

Objective Integrative neuroscience research needs a scalable informatics framework that enables semantic integration of diverse types of neuroscience data. This paper describes the use of the Web Ontology Language (OWL) and other Semantic Web technologies for the representation and integration of molecular-level data provided by several of SenseLab suite of neuroscience databases. Methods Based on the original database structure, we semi-automatically translated the databases into OWL ontologies with manual addition of semantic enrichment. The SenseLab ontologies are extensively linked to other biomedical Semantic Web resources, including the Subcellular Anatomy Ontology, Brain Architecture Management System, the Gene Ontology, BIRNLex and UniProt. The SenseLab ontologies have also been mapped to the Basic Formal Ontology and Relation Ontology, which helps ease interoperability with many other existing and future biomedical ontologies for the Semantic Web. In addition, approaches to representing contradictory research statements are described. The SenseLab ontologies are designed for use on the Semantic Web that enables their integration into a growing collection of biomedical information resources. Conclusion We demonstrate that our approach can yield significant potential benefits and that the Semantic Web is rapidly becoming mature enough to realize its anticipated promises. The ontologies are available online at http: //neuroweb. med. yale. edu/senselab/.

Details DOI
v2026.09.13