M
Matko Bošnjak
Researcher at University College London
Publications - 35
Citations - 6950
Matko Bošnjak is an academic researcher from University College London. The author has contributed to research in topics: Natural language & Inference. The author has an hindex of 17, co-authored 34 publications receiving 5535 citations. Previous affiliations of Matko Bošnjak include University of Porto.
Papers
More filters
Journal ArticleDOI
REVIGO Summarizes and Visualizes Long Lists of Gene Ontology Terms
TL;DR: REVIGO is a Web server that summarizes long, unintelligible lists of GO terms by finding a representative subset of the terms using a simple clustering algorithm that relies on semantic similarity measures.
Journal ArticleDOI
A large-scale evaluation of computational protein function prediction
Predrag Radivojac,Wyatt T. Clark,Tal Ronnen Oron,Alexandra M. Schnoes,Tobias Wittkop,Artem Sokolov,Artem Sokolov,Kiley Graim,Christopher S. Funk,Karin Verspoor,Asa Ben-Hur,Gaurav Pandey,Gaurav Pandey,Jeffrey M. Yunes,Ameet Talwalkar,Susanna Repo,Susanna Repo,Michael L Souza,Damiano Piovesan,Rita Casadio,Zheng Wang,Jianlin Cheng,Hai Fang,Julian Gough,Patrik Koskinen,Petri Törönen,Jussi Nokso-Koivisto,Liisa Holm,Domenico Cozzetto,Daniel W. A. Buchan,Kevin Bryson,David T. Jones,Bhakti Limaye,Harshal Inamdar,Avik Datta,Sunitha K Manjari,Rajendra Joshi,Meghana Chitale,Daisuke Kihara,Andreas Martin Lisewski,Serkan Erdin,Eric Venner,Olivier Lichtarge,Robert Rentzsch,Haixuan Yang,Alfonso E. Romero,Prajwal Bhat,Alberto Paccanaro,Tobias Hamp,Rebecca Kaßner,Stefan Seemayer,Esmeralda Vicedo,Christian Schaefer,Dominik Achten,Florian Auer,Ariane Boehm,Tatjana Braun,Maximilian Hecht,Mark Heron,Peter Hönigschmid,Thomas A. Hopf,Stefanie Kaufmann,Michael Kiening,Denis Krompass,Cedric Landerer,Yannick Mahlich,Manfred Roos,Jari Björne,Tapio Salakoski,Andrew Wong,Hagit Shatkay,Hagit Shatkay,Fanny Gatzmann,Ingolf Sommer,Mark N. Wass,Michael J.E. Sternberg,Nives Škunca,Fran Supek,Matko Bošnjak,Panče Panov,Sašo Džeroski,Tomislav Šmuc,Yiannis A. I. Kourmpetis,Yiannis A. I. Kourmpetis,Aalt D. J. van Dijk,Cajo J. F. ter Braak,Yuanpeng Zhou,Qingtian Gong,Xinran Dong,Weidong Tian,Marco Falda,Paolo Fontana,Enrico Lavezzo,Barbara Di Camillo,Stefano Toppo,Liang Lan,Nemanja Djuric,Yuhong Guo,Slobodan Vucetic,Amos Marc Bairoch,Amos Marc Bairoch,Michal Linial,Patricia C. Babbitt,Steven E. Brenner,Christine A. Orengo,Burkhard Rost,Sean D. Mooney,Iddo Friedberg +107 more
TL;DR: Today's best protein function prediction algorithms substantially outperform widely used first-generation methods, with large gains on all types of targets, and there is considerable need for improvement of currently available tools.
Proceedings ArticleDOI
emoji2vec: Learning Emoji Representations from their Description
TL;DR: The authors proposed a pre-trained embeddings for all Unicode emoji which are learned from their description in the Unicode emoji standard, which can be readily used in downstream social natural language processing applications alongside word2vec.
Posted Content
emoji2vec: Learning Emoji Representations from their Description
TL;DR: The authors proposed a pre-trained embeddings for all Unicode emoji which are learned from their description in the Unicode emoji standard, which can be readily used in downstream social natural language processing applications alongside word2vec.
Posted Content
COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
TL;DR: This Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models of its environment and action space and can learn a variety of tasks through model-based search in very few steps and excel on structured hold-out tests of policy robustness.