Filip Ginter

Universal Dependencies v1: A Multilingual Treebank Collection

2016

Cross-linguistically consistent annotation is necessary for sound comparative evaluation and cross-lingual learning experiments.It is also useful for multilingual system development and comparative linguistic studies.Universal Dependencies is an open community effort to create cross-linguistically consistent treebank …

Neural Dependency Parsing of Biomedical Text: TurkuNLP entry in the CRAFT Structural Annotation Task

2019

We present the approach taken by the TurkuNLP group in the CRAFT Structural Annotation task, a shared task on dependency parsing. Our approach builds primarily on the Turku neural parser, a native dependency parser that …

Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection

2020 · Uppsala University Publications (Uppsala University)

Universal Dependencies is an open community effort to create cross-linguistically consistent treebank annotation for many languages within a dependency-based lexicalist framework. The annotation consists in a linguistically motivated word segmentation; a morphological layer comprising lemmas, …

Explaining Classes through Stable Word Attributions

2022 · Findings of the Association for Computational Linguistics: ACL 2022

Input saliency methods have recently become a popular tool for explaining predictions of deep learning models in NLP. Nevertheless, there has been little work investigating methods for aggregating prediction-level explanations to the class level, nor …

CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

2017

Daniel Zeman, Martin Popel, Milan Straka, Jan Hajič, Joakim Nivre, Filip Ginter, Juhani Luotolahti, Sampo Pyysalo, Slav Petrov, Martin Potthast, Francis Tyers, Elena Badmaeva, Memduh Gokirmak, Anna Nedoluzhko, Silvie Cinková, Jan Hajič jr., Jaroslava Hlaváčová, …

CoNLL 2018 Shared Task : Multilingual Parsing from Raw Text to Universal Dependencies

2018 · Conference on Computational Natural Language Learning

Every year, the Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets. In 2018, one of two tasks was …

Multilingual is not enough: BERT for Finnish

2019 · arXiv (Cornell University)

Deep learning-based language models pretrained on large unannotated text corpora have been demonstrated to allow efficient transfer learning for natural language processing, with recent approaches such as the transformer-based BERT model advancing the state of …