H
Héctor Martínez Alonso
Researcher at Thomson Reuters
Publications - 57
Citations - 1392
Héctor Martínez Alonso is an academic researcher from Thomson Reuters. The author has contributed to research in topics: Parsing & Dependency grammar. The author has an hindex of 15, co-authored 57 publications receiving 1209 citations. Previous affiliations of Héctor Martínez Alonso include French Institute for Research in Computer Science and Automation & University of Copenhagen.
Papers
More filters
Proceedings ArticleDOI
CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Daniel Zeman,Martin Popel,Milan Straka,Jan Hajič,Joakim Nivre,Filip Ginter,Juhani Luotolahti,Sampo Pyysalo,Slav Petrov,Martin Potthast,Francis M. Tyers,Elena Badmaeva,Memduh Gökırmak,Anna Nedoluzhko,Silvie Cinková,Jaroslava Hlaváčová,Václava Kettnerová,Zdenka Uresova,Jenna Kanerva,Stina Ojala,Anna Missilä,Christopher D. Manning,Sebastian Schuster,Siva Reddy,Dima Taji,Nizar Habash,Herman Leung,Marie-Catherine de Marneffe,Manuela Sanguinetti,Maria Simi,Hiroshi Kanayama,Valeria dePaiva,Kira Droganova,Héctor Martínez Alonso,Ça ugrı Çöltekin,Umut Sulubacak,Hans Uszkoreit,Vivien Macketanz,Aljoscha Burchardt,Kim Harris,Katrin Marheinecke,Georg Rehm,Tolga Kayadelen,Mohammed Attia,Ali Elkahky,Zhuoran Yu,Emily Pitler,Saran Lertpradit,Michael Mandl,Jesse Kirchner,Hector Fernandez Alcalde,Jana Strnadová,Esha Banerjee,Ruli Manurung,Antonio Stella,Atsuko Shimada,Sookyoung Kwak,Gustavo Mendonça,Tatiana Lando,Rattima Nitisaroj,Josie Li +60 more
TL;DR: The task and evaluation methodology is defined, how the data sets were prepared, report and analyze the main results, and a brief categorization of the different approaches of the participating systems are provided.
Proceedings ArticleDOI
When is multitask learning effective? Semantic sequence prediction under varying data conditions
TL;DR: In this article, the authors evaluate a range of semantic sequence labeling tasks in a multi-task learning setup and show that MTL is not always effective, significant improvements are obtained only for 1 out of 5 tasks.
Journal ArticleDOI
Multilingual Projection for Parsing Truly Low-Resource Languages
Željko Agić,Anders Johannsen,Barbara Plank,Barbara Plank,Héctor Martínez Alonso,Héctor Martínez Alonso,Natalie Schluter,Anders Søgaard +7 more
TL;DR: This work proposes a novel approach to cross-lingual part-of-speech tagging and dependency parsing for truly low-resource languages that consistently provides top-level accuracies, close to established upper bounds, and outperforms several competitive baselines.
Proceedings ArticleDOI
Inverted indexing for cross-lingual NLP
Anders Søgaard,Żeljko Agić,Héctor Martínez Alonso,Barbara Plank,Bernd Bohnet,Anders Johannsen +5 more
TL;DR: A novel, count-based approach to obtaining inter-lingual word representations based on inverted indexing of Wikipedia that enables multi-source crosslingual learning and improves over using state-of-the-art bilingual embeddings.
Proceedings ArticleDOI
What's in a p-value in NLP?
TL;DR: It is shown that significance results following current research standards are unreliable and, in addition, very sensitive to sample size, covariates such as sentence length, as well as to the existence of multiple metrics.