Milan Straka

CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text

2024 · arXiv (Cornell University)

We present CorPipe 24, the winning entry to the CRAC 2024 Shared Task on Multilingual Coreference Resolution. In this third iteration of the shared task, a novel objective is to also predict empty nodes needed …

UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing

2016

Automatic natural language processing of large texts often presents recurring challenges in multiple languages: even for most advanced tasks, the texts are first processed by basic processing steps -from tokenization to parsing.We present an extremely …

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, …

Tokenizing, POS Tagging, Lemmatizing and Parsing UD 2.0 with UDPipe

2017

We present an update to UDPipe 1.0 We provide models for all 50 languages of UD 2.0, and furthermore, the pipeline can be trained easily using data in CoNLL-U format.

Neural Architectures for Nested NER through Linearization

2019

We propose two neural network architectures for nested named entity recognition (NER), a setting in which named entities may overlap and also be labeled with more than one label. We encode the nested labels using …

75 Languages, 1 Model: Parsing Universal Dependencies Universally

2019

Dan Kondratyuk, Milan Straka. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

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 …