Accueil > Pages Perso

Tobias MAYER

Doctorant -  UCA

Dernières publicationsHAL

pour "Tobias MAYER" :

titre
Enriching Language Models with Semantics
auteur
Tobias Mayer
article
24th European Conference on Artificial Intelligence (ECAI2020), Aug 2020, Santiago de Compostela, Spain
annee_publi
2020
resume
Recent advances in language model (LM) pre-training from large-scale corpora have shown to improve various natural language processing tasks. They achieve performances comparable to non-expert humans on the GLUE benchmark for natural language understanding (NLU). While the improvement of the different contextualized representations comes from (i) the usage of more and more data, (ii) changing the types of lexical pre-training tasks or (iii) increasing the model size, NLU is more than memorizing word co-occurrences. But how much world knowledge and common sense can those language model capture? How much can those models infer from just the lexical information? To overcome this problem, some approaches include semantic information in the training process. In this paper, we highlight existing approaches to combine different types of semantics with language models during the pre-training or fine-tuning phase.
typdoc
Communication dans un congrès
Accès au texte intégral et bibtex
https://hal.archives-ouvertes.fr/hal-02879286/file/1325_paper.pdf BibTex
titre
Transformer-based Argument Mining for Healthcare Applications
auteur
Tobias Mayer, Elena Cabrio, Serena Villata
article
24th European Conference on Artificial Intelligence (ECAI2020), Aug 2020, Santiago de Compostela, Spain
annee_publi
2020
resume
Argument(ation) Mining (AM) typically aims at identifying argumentative components in text and predicting the relations among them. Evidence-based decision making in the health-care domain targets at supporting clinicians in their deliberation process to establish the best course of action for the case under evaluation. Although the reasoning stage of this kind of frameworks received considerable attention, little effort has been devoted to the mining stage. We extended an existing dataset by annotating 500 abstracts of Randomized Controlled Trials (RCT) from the MEDLINE database, leading to a dataset of 4198 argument components and 2601 argument relations on different diseases (i.e., neoplasm, glau-coma, hepatitis, diabetes, hypertension). We propose a complete argument mining pipeline for RCTs, classifying argument components as evidence and claims, and predicting the relation, i.e., attack or support , holding between those argument components. We experiment with deep bidirectional transformers in combination with different neural architectures (i.e., LSTM, GRU and CRF) and obtain a macro F1-score of .87 for component detection and .68 for relation prediction , outperforming current state-of-the-art end-to-end AM systems.
typdoc
Communication dans un congrès
Accès au texte intégral et bibtex
https://hal.archives-ouvertes.fr/hal-02879293/file/1470_paper.pdf BibTex
titre
A Transparent Referendum Protocol with Immutable Proceedings and Verifiable Outcome for Trustless Networks
auteur
Maximilian Schiedermeier, Omar Hasan, Lionel Brunie, Tobias Mayer, Harald Kosch
article
The 8th International Conference on Complex Networks and their Applications (COMPLEX NETWORKS 2019), Dec 2019, Lisbon, Portugal
annee_publi
2019
typdoc
Communication dans un congrès
Accès au bibtex
BibTex
titre
ACTA: A Tool for Argumentative Clinical Trial Analysis
auteur
Tobias Mayer, Elena Cabrio, Serena Villata
article
IJCAI 2019 - Twenty-Eighth International Joint Conference on Artificial Intelligence, Aug 2019, Macao, China. pp.6551-6553
annee_publi
2019
resume
Argumentative analysis of textual documents of various nature (e.g., persuasive essays, online discussion blogs, scientific articles) allows to detect the main argumentative components (i.e., premises and claims) present in the text and to predict whether these components are connected to each other by argumentative relations (e.g., support and attack), leading to the identification of (possibly complex) argumentative structures. Given the importance of argument-based decision making in medicine, in this demo paper we introduce ACTA, a tool for automating the argumentative analysis of clinical trials. The tool is designed to support doctors and clinicians in identifying the document(s) of interest about a certain disease, and in analyzing the main argumentative content and PICO elements.
typdoc
Communication dans un congrès
Accès au texte intégral et bibtex
https://hal.archives-ouvertes.fr/hal-02275997/file/IJCAI__19_ACTA_DEMO.pdf BibTex
titre
Evidence Type Classification in Randomized Controlled Trials
auteur
Tobias Mayer, Elena Cabrio, Serena Villata
article
5th ArgMining@EMNLP 2018, Oct 2018, Brussels, Belgium
annee_publi
2018
resume
Randomized Controlled Trials (RCT) are a common type of experimental studies in the medical domain for evidence-based decision making. The ability to automatically extract the arguments proposed therein can be of valuable support for clinicians and practitioners in their daily evidence-based decision making activities. Given the peculiarity of the medical domain and the required level of detail, standard approaches to argument component detection in argument(ation) mining are not fine-grained enough to support such activities. In this paper, we introduce a new sub-task of the argument component identification task: evidence type classification. To address it, we propose a supervised approach and we test it on a set of RCT abstracts on different medical topics.
typdoc
Communication dans un congrès
Accès au texte intégral et bibtex
https://hal.archives-ouvertes.fr/hal-01912157/file/EMNLP_short.pdf BibTex
titre
Argument Mining on Clinical Trials
auteur
Tobias Mayer, Elena Cabrio, Marco Lippi, Paolo Torroni, Serena Villata
article
COMMA 2018 - 7th International Conference on Computational Models of Argument Proceedings, Sep 2018, Warsaw, Poland. pp.137 - 148
annee_publi
2018
resume
Argument-based decision making has been employed to support a variety of reasoning tasks over medical knowledge. These include evidence-based justifications of the effects of treatments, the detection of conflicts in the knowledge base, and the enabling of uncertain and defeasible reasoning in the health-care sector. However, a common limitation of these approaches is that they rely on structured input information. Recent advances in argument mining have shown increasingly accurate results in detecting argument components and predicting their relations from unstructured, natural language texts. In this study, we discuss evidence and claim detection from Randomized Clinical Trials. To this end, we create a new annotated dataset about four different diseases (glaucoma, diabetes, hepatitis B, and hypertension), containing 976 argument components (697 containing evidence, 279 claims). Empirical results are promising, and show the portability of the proposed approach over different branches of medicine.
typdoc
Communication dans un congrès
Accès au bibtex
BibTex
titre
On reliability in publish/subscribe systems: a survey
auteur
Tobias Mayer, Lionel Brunie, David Coquil, Harald Kosch
article
International Journal of Parallel, Emergent and Distributed Systems, Taylor & Francis, 2012, 5, 27, pp.369-386. ⟨10.1080/17445760.2012.697162⟩
annee_publi
2012
resume
On reliability in publish/subscribe systems: a survey
typdoc
Article dans une revue
Accès au bibtex
BibTex
titre
RCourse:A Robustness Benchmarking Suite for Publish/Subscribe Overlay Simulations With Peersim
auteur
Tobias Mayer, David Coquil, Christian Schörnich, Harald Kosch
article
Workshop on P2P and Dependability, European Dependable Computing Conference, May 2012, Sibiu, Romania. pp.1-6
annee_publi
2012
resume
This paper introduces the RCourse benchmarking suite, an extension to the Peersim simulatior environment. RCourse supports simulative evaluations of Publish/Subscribe systems with respect to robustness. To this end, it provides among others mechanisms for the aggregation of measurement values and for an automatic graph generation repre- senting the extracted results. The design of RCourse is characterized by its highly modular architecture, which enables the adaptation of each step of the simulation workflow to specific user needs.
typdoc
Communication dans un congrès
Accès au bibtex
BibTex
titre
Evaluating the Robustness of Publish/Subscribe Systems
auteur
Tobias Mayer, Lionel Brunie, David Coquil, Harald Kosch
article
Proceedings of the Sixth International Conference on P2P, Parallel, Grid, Cloud and Internet Computi, 2011, pp.75-82. ⟨10.1109/3PGCIC.2011.21⟩
annee_publi
2011
resume
In recent years, publish/subscribe (pub/sub) systems have evolved as serious candidates for the implementation of multicast communication. However, to date they have not been properly analysed with respect to the critical dimension of robustness. Indeed, the robustness evaluations found in the literature only cover a subset of the types of failure situations and generally lack a comprehensive architectural classification. In this context, this paper introduces the necessary foundations for systematic evaluation of the robustness of pub/sub system: a comprehensive classification scheme and a complete taxonomy of failures. We argue that both robustness evaluation of pub/sub systems and development methods of robust pub/sub systems should take rational behavior into account. We demonstrate this point through an experimental study.
typdoc
Article dans une revue
Accès au bibtex
BibTex
titre
Live-Ticker Supported Sports-Video Annotation Enabling Tactic Analysis
auteur
Tobias Mayer, David Coquil, Lyes Limam, Florian Stegmaier, Mario Döller, Harald Kosch
article
11th International Workshop of the Multimedia Metadata Community, May 2010, Barcelona, Spain. pp. 53-56
annee_publi
2010
resume
Automatic semantic annotation of videos remains an open research problem. In the domain of soccer matches, live tickers are freely available on the Internet. These tickers can be used as sources of information about the events of a soccer match: as they are written by humans, they contain semantic information. This work presents a prototype that processes live ticker texts and transforms them into machine-readable annotations. The prototype produces semantic annotated actions as RDFgraphs. The resulting annotation may be used for other purposes, such as tactical analysis of the match, semantic multimedia query processing or assistance to other video annotation tools.
typdoc
Communication dans un congrès
Accès au bibtex
BibTex
  • + de résultats dans la Collection HAL du laboratoire BCL
  • Voir l'ensemble des résultats sur la plateforme HAL
  • Anciennes productions