Awards

BioASQ 2021 Winner - second place in one batch on the BioASQ document retrieval task and four second places on the Synergy task
DGES Merit Award - Awarded by DGES to the top 25 students (2018/2019) of the Aveiro University
BioASQ 2020 Winner - One first place and two second places in the BioASQ document retrieval task
Prémio BPI - Awarded by the Aveiro University to the best graduate student of a bachelor or integrated master's degree in engineering that is not awarded with specific prize.
NEI mention - Best student of BSc in Informatics Engineering - Awarded by NEI (Núcleo de Estudantes de Informática).

Publications

  • Chemical detection and indexing in PubMed full text articles using deep learning and rule-based methods
  • Tiago Almeida, Rui Antunes, João Figueira Silva, João Almeida, Sérgio Matos
    Proceedings of the BioCreative VII Challenge Evaluation Workshop, Online event, p. 210-213, November 2021
  • Chemical–protein relation extraction in PubMed abstracts using BERT and neural networks
  • Rui Antunes, Tiago Almeida, João Figueira Silva, Sérgio Matos
    Proceedings of the BioCreative VII Challenge Evaluation Workshop, Online event, p. 210-213, November 2021
  • Drug mention recognition in Twitter posts using a deep learning approach
  • João Figueira Silva, Tiago Almeida, Rui Antunes, João Almeida, Sérgio Matos
    Proceedings of the BioCreative VII Challenge Evaluation Workshop, Online event, p. 210-213, November 2021
  • Universal passage weighting mechanism (UPWM) in BioASQ 9b
  • Tiago Almeida & Sérgio Matos
    Proceedings of the Working Notes of CLEF 2021
  • BioASQ Synergy: A strong and simple baseline rooted in relevance feedback
  • Tiago Almeida & Sérgio Matos
    Proceedings of the Working Notes of CLEF 2021
  • Benchmarking a transformer-FREE model for ad-hoc retrieval
  • Tiago Almeida & Sérgio Matos
    16th Conference of the European Chapter of the Association for Computational Linguistics
  • BIT. UA@ TREC 2020 Precision Medicine Track
  • Tiago Almeida & Sérgio Matos
    Text Retrieval Conference 2020
  • BIT. UA@ TREC 2020 Deep Learning Track
  • Tiago Almeida & Sérgio Matos
    Text Retrieval Conference 2020
  • Evaluating a lightweight neural reranking model for biomedical question answering
  • Tiago Almeida & Sérgio Matos
    26th Portuguese Conference on Pattern Recognition
  • BIT.UA at BioASQ 8 Lightweight neural document ranking with zero-shot snippet retrieval
  • Tiago Almeida & Sérgio Matos
    BioASQ workshop 2020 - CLEF 2020
  • Frugal neural reranking: evaluation on the Covid-19 literature
  • Tiago Almeida & Sérgio Matos
    1st Workshop onNLP for COVID-19 (Part 2) at EMNLP 202
  • Calling attention to passages for biomedical question answering
  • Tiago Almeida & Sérgio Matos
    ECIR 2020, Advances in Information Retrieval pp 69-77
  • Neural-based snippet extraction for biomedical question answering.
  • Tiago Almeida & Sérgio Matos
    25th Portuguese Conference on Pattern Recognition (2019), 79–80
  • Microtransactions in the Company’s and the Player’s Perspective: A Manual and Automatic Analysis
  • Gusmão, P., Almeida, T., Lopes, F., Muryn, Y., Martins, J., & Au-Yong-Oliveira, M.
    New Knowledge in Information Systems and Technologies. WorldCIST’19 2019 (pp. 440–451)

    Projects

    European Health Data and Evidence Network
    Ref: info:eu-repo/grantAgreement/EC/H2020/806968/EU
    Funding: European Commission (Horizon 2020 Framework Programme (H2020))
    Participation: Masters research grant ( 2019/09/01 - )
    European Medical Information Framework
    Ref: info:eu-repo/grantAgreement/EC/FP7/115372/EU
    Funding: European Commission (SEVENTH FRAMEWORK PROGRAMME (FP7))
    Participation: Research integration grant ( 2018/04/01 - 2019/03/31)

    Presentations and Posters

  • Neural-based snippet extraction for biomedical question answering.
  • Almeida, T., & Matos, S.
    25th Portuguese Conference on Pattern Recognition (2019), 79–80

    Public software

    Polus - Functional deep learning training framework based on tensorflow, focused on research and performance
    Covid Search - Deep Learning powerd Search engine over the CORD-19 corpus. With purpose to facilitate the biomedical search about covid-19.
    Multidimesional RNN library with Keras and Tensorflow - Open source library that exposes multidimensional recurrent neural networks following a Keras API
    SuperCool - A three.js game inspered on SuperHot made for the VI class, jointly done with Yuriy Muryn
    BioASQ 7b document ranking - Adaptation of the DeepRank model with attention layers for the BioASQ 7b document retrieval task. It also supports an unsupervised way of snippet extraction.