Mark Anderson

Learnable Frontends that do not Learn: Quantifying Sensitivity to Filterbank Initialisation

Feb 20, 2023
Mark Anderson, Tomi Kinnunen, Naomi Harte

Figure 2 for Learnable Frontends that do not Learn: Quantifying Sensitivity to Filterbank Initialisation

Figure 3 for Learnable Frontends that do not Learn: Quantifying Sensitivity to Filterbank Initialisation

Figure 4 for Learnable Frontends that do not Learn: Quantifying Sensitivity to Filterbank Initialisation

* Accepted at ICASSP 2023, 5 pages, 2 figures, 2 tables

Access Paper or Ask Questions

Parsing linearizations appreciate PoS tags - but some are fussy about errors

Oct 27, 2022
Alberto Muñoz-Ortiz, Mark Anderson, David Vilares, Carlos Gómez-Rodríguez

Figure 2 for Parsing linearizations appreciate PoS tags - but some are fussy about errors

Figure 3 for Parsing linearizations appreciate PoS tags - but some are fussy about errors

Figure 4 for Parsing linearizations appreciate PoS tags - but some are fussy about errors

* Accepted at AACL 2022

Access Paper or Ask Questions

Learnable Acoustic Frontends in Bird Activity Detection

Oct 03, 2022
Mark Anderson, Naomi Harte

Figure 2 for Learnable Acoustic Frontends in Bird Activity Detection

Figure 3 for Learnable Acoustic Frontends in Bird Activity Detection

Figure 4 for Learnable Acoustic Frontends in Bird Activity Detection

* Submitted and presented at IWAENC, September 2022, 5 Pages, 1 Figure, 3 Tables

Access Paper or Ask Questions

The Impact of Edge Displacement Vaserstein Distance on UD Parsing Performance

Sep 15, 2022
Mark Anderson, Carlos Gómez-Rodríguez

* Computational Linguistics, 48(3):517-554, 2022
* This is the final peer-reviewed manuscript accepted for publication in Computational Linguistics. The journal version with the final editorial and typesetting changes is available open-access at https://doi.org/10.1162/coli_a_00440

Access Paper or Ask Questions

Assessing the Limits of the Distributional Hypothesis in Semantic Spaces: Trait-based Relational Knowledge and the Impact of Co-occurrences

May 16, 2022
Mark Anderson, Jose Camacho-Collados

Figure 1 for Assessing the Limits of the Distributional Hypothesis in Semantic Spaces: Trait-based Relational Knowledge and the Impact of Co-occurrences

Figure 2 for Assessing the Limits of the Distributional Hypothesis in Semantic Spaces: Trait-based Relational Knowledge and the Impact of Co-occurrences

Figure 3 for Assessing the Limits of the Distributional Hypothesis in Semantic Spaces: Trait-based Relational Knowledge and the Impact of Co-occurrences

Figure 4 for Assessing the Limits of the Distributional Hypothesis in Semantic Spaces: Trait-based Relational Knowledge and the Impact of Co-occurrences

* Due to appear in the proceedings of *SEM 2022: The 11th Joint Conference on Lexical and Computational Semantics

Access Paper or Ask Questions

Low Resource Species Agnostic Bird Activity Detection

Dec 16, 2021
Mark Anderson, John Kennedy, Naomi Harte

Figure 2 for Low Resource Species Agnostic Bird Activity Detection

Figure 3 for Low Resource Species Agnostic Bird Activity Detection

Figure 4 for Low Resource Species Agnostic Bird Activity Detection

* IEEE Workshop on Signal Processing Systems (SiPS), 2021, pp. 34-39
* This paper is accepted and presented at the IEEE Workshop on Signal Processing Systems (SiPS) October 2021, 3 Figures, 5 Tables

Access Paper or Ask Questions

Bioacoustic Event Detection with prototypical networks and data augmentation

Dec 16, 2021
Mark Anderson, Naomi Harte

Figure 2 for Bioacoustic Event Detection with prototypical networks and data augmentation

Figure 3 for Bioacoustic Event Detection with prototypical networks and data augmentation

Figure 4 for Bioacoustic Event Detection with prototypical networks and data augmentation

* 5 pages, 2 Figures, 3 Tables, Technical Report for DCASE2021 Challenge Task 5, June 2021

Access Paper or Ask Questions

Learning from learning machines: a new generation of AI technology to meet the needs of science

Nov 27, 2021
Luca Pion-Tonachini, Kristofer Bouchard, Hector Garcia Martin, Sean Peisert, W. Bradley Holtz, Anil Aswani, Dipankar Dwivedi, Haruko Wainwright, Ghanshyam Pilania, Benjamin Nachman, Babetta L. Marrone, Nicola Falco, Prabhat, Daniel Arnold, Alejandro Wolf-Yadlin, Sarah Powers, Sharlee Climer, Quinn Jackson, Ty Carlson, Michael Sohn, Petrus Zwart, Neeraj Kumar, Amy Justice, Claire Tomlin, Daniel Jacobson, Gos Micklem, Georgios V. Gkoutos, Peter J. Bickel, Jean-Baptiste Cazier, Juliane Müller, Bobbie-Jo Webb-Robertson, Rick Stevens, Mark Anderson, Ken Kreutz-Delgado, Michael W. Mahoney, James B. Brown

Figure 2 for Learning from learning machines: a new generation of AI technology to meet the needs of science

Figure 3 for Learning from learning machines: a new generation of AI technology to meet the needs of science

Figure 4 for Learning from learning machines: a new generation of AI technology to meet the needs of science

Access Paper or Ask Questions

Splitting EUD graphs into trees: A quick and clatty approach

Jul 18, 2021
Mark Anderson, Carlos Gómez-Rodríguez

Figure 2 for Splitting EUD graphs into trees: A quick and clatty approach

Figure 3 for Splitting EUD graphs into trees: A quick and clatty approach

Figure 4 for Splitting EUD graphs into trees: A quick and clatty approach

* IWPT 2021 Shared Task system description. To be published in proceedings of the 17th International Conference on Parsing Technologies

Access Paper or Ask Questions