Search Results for author:
Found 50 papers, 23 papers with code
Findings of the Third Shared Task on Multilingual Coreference Resolution
The paper presents an overview of the third edition of the shared task on multilingual coreference resolution, held as part of the CRAC 2024 workshop.
CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text
In this third iteration of the shared task, a novel objective is to also predict empty nodes needed for zero coreference mentions (while the empty nodes were given on input in previous years).
beeFormer: Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems
In this paper, we propose beeFormer, a framework for training sentence Transformer models with interaction data.
Open-Source Web Service with Morphological Dictionary-Supplemented Deep Learning for Morphosyntactic Analysis of Czech
We present an open-source web service for Czech morphosyntactic analysis.
CWRCzech: 100M Query-Document Czech Click Dataset and Its Application to Web Relevance Ranking
We present CWRCzech, Click Web Ranking dataset for Czech, a 100M query-document Czech click dataset for relevance ranking with user behavior data collected from search engine logs of Seznam$.$cz.
ÚFAL LatinPipe at EvaLatin 2024: Morphosyntactic Analysis of Latin
Our system consists of a fine-tuned concatenation of base and large pre-trained LMs, with a dot-product attention head for parsing and softmax classification heads for morphology to jointly learn both dependency parsing and morphological analysis.
Practical End-to-End Optical Music Recognition for Pianoform Music
(c) We train and fine-tune an end-to-end model to serve as a baseline on the dataset and employ the TEDn metric to evaluate the model.
ÚFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution
We present CorPipe, the winning entry to the CRAC 2023 Shared Task on Multilingual Coreference Resolution.
DaMuEL: A Large Multilingual Dataset for Entity Linking
The dataset contains 27. 9M named entities in the knowledge base and 12. 3G tokens from Wikipedia texts.
Quality and Efficiency of Manual Annotation: Pre-annotation Bias
This paper presents an analysis of annotation using an automatic pre-annotation for a mid-level annotation complexity task -- dependency syntax annotation.
ÚFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolution
We describe the winning submission to the CRAC 2022 Shared Task on Multilingual Coreference Resolution.
Czech Grammar Error Correction with a Large and Diverse Corpus
We introduce a large and diverse Czech corpus annotated for grammatical error correction (GEC) with the aim to contribute to the still scarce data resources in this domain for languages other than English.
Character Transformations for Non-Autoregressive GEC Tagging
We propose a character-based nonautoregressive GEC approach, with automatically generated character transformations.
ÚFAL at MultiLexNorm 2021: Improving Multilingual Lexical Normalization by Fine-tuning ByT5
We present the winning entry to the Multilingual Lexical Normalization (MultiLexNorm) shared task at W-NUT 2021 (van der Goot et al., 2021a), which evaluates lexical-normalization systems on 12 social media datasets in 11 languages.
Understanding Model Robustness to User-generated Noisy Texts
We also compare two approaches to address the performance drop: a) training the NLP models with noised data generated by our framework; and b) reducing the input noise with external system for natural language correction.
RobeCzech: Czech RoBERTa, a monolingual contextualized language representation model
We present RobeCzech, a monolingual RoBERTa language representation model trained on Czech data.
Ranked #1 on
Semantic Parsing
on PTG (czech, MRP 2020)
Diacritics Restoration using BERT with Analysis on Czech language
We propose a new architecture for diacritics restoration based on contextualized embeddings, namely BERT, and we evaluate it on 12 languages with diacritics.
A matrix approach to detect temporal behavioral patterns at electric vehicle charging stations
Based on the electric vehicle (EV) arrival times and the duration of EV connection to the charging station, we identify charging patterns and derive groups of charging stations with similar charging patterns applying two approaches.
ÚFAL at MRP 2020: Permutation-invariant Semantic Parsing in PERIN
PERIN was one of the winners of the shared task.
Ranked #1 on
Semantic Parsing
on DRG (english, MRP 2020)
\'UFAL at MRP 2020: Permutation-invariant Semantic Parsing in PERIN
PERIN was one of the winners of the shared task.
Reading Comprehension in Czech via Machine Translation and Cross-lingual Transfer
We report that a XLM-RoBERTa model trained on English data and evaluated on Czech achieves very competitive performance, only approximately 2 percent points worse than a~model trained on the translated Czech data.
UDPipe at EvaLatin 2020: Contextualized Embeddings and Treebank Embeddings
We present our contribution to the EvaLatin shared task, which is the first evaluation campaign devoted to the evaluation of NLP tools for Latin.
Prague Dependency Treebank -- Consolidated 1.0
We present a richly annotated and genre-diversified language resource, the Prague Dependency Treebank-Consolidated 1. 0 (PDT-C 1. 0), the purpose of which is - as it always been the case for the family of the Prague Dependency Treebanks - to serve both as a training data for various types of NLP tasks as well as for linguistically-oriented research.
Explaining the distribution of energy consumption at slow charging infrastructure for electric vehicles from socio-economic data
We identified the most influential features correlated with energy consumption, indicating that the spatial context of the charging infrastructure affects its utilization pattern.
Prague Dependency Treebank - Consolidated 1.0
We present a richly annotated and genre-diversified language resource, the Prague Dependency Treebank-Consolidated 1. 0 (PDT-C 1. 0), the purpose of which is - as it always been the case for the family of the Prague Dependency Treebanks - to serve both as a training data for various types of NLP tasks as well as for linguistically-oriented research.
\'UFAL MRPipe at MRP 2019: UDPipe Goes Semantic in the Meaning Representation Parsing Shared Task
We present a system description of our contribution to the CoNLL 2019 shared task, CrossFramework Meaning Representation Parsing (MRP 2019).
MRP 2019: Cross-Framework Meaning Representation Parsing
The 2019 Shared Task at the Conference for Computational Language Learning (CoNLL) was devoted to Meaning Representation Parsing (MRP) across frameworks.
ÚFAL MRPipe at MRP 2019: UDPipe Goes Semantic in the Meaning Representation Parsing Shared Task
We present a system description of our contribution to the CoNLL 2019 shared task, Cross-Framework Meaning Representation Parsing (MRP 2019).
Predicting popularity of EV charging infrastructure from GIS data
The availability of charging infrastructure is essential for large-scale adoption of electric vehicles (EV).
Grammatical Error Correction in Low-Resource Scenarios
Grammatical error correction in English is a long studied problem with many existing systems and datasets.
Ranked #4 on
Grammatical Error Correction
on Falko-MERLIN
(using extra training data)
CUNI System for the Building Educational Applications 2019 Shared Task: Grammatical Error Correction
In this paper, we describe our systems submitted to the Building Educational Applications (BEA) 2019 Shared Task (Bryant et al., 2019).
Czech Text Processing with Contextual Embeddings: POS Tagging, Lemmatization, Parsing and NER
We evaluate two meth ods for precomputing such embeddings, BERT and Flair, on four Czech text processing tasks: part-of-speech (POS) tagging, lemmatization, dependency pars ing and named entity recognition (NER).
Evaluating Contextualized Embeddings on 54 Languages in POS Tagging, Lemmatization and Dependency Parsing
We present an extensive evaluation of three recently proposed methods for contextualized embeddings on 89 corpora in 54 languages of the Universal Dependencies 2. 3 in three tasks: POS tagging, lemmatization, and dependency parsing.
Ranked #1 on
Dependency Parsing
on Universal Dependencies
UDPipe at SIGMORPHON 2019: Contextualized Embeddings, Regularization with Morphological Categories, Corpora Merging
In the morphological analysis, our system placed tightly second: our morphological analysis accuracy was 93. 19, the winning system's 93. 23.
Neural Architectures for Nested NER through Linearization
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.
Ranked #3 on
Nested Mention Recognition
on ACE 2005
75 Languages, 1 Model: Parsing Universal Dependencies Universally
We present UDify, a multilingual multi-task model capable of accurately predicting universal part-of-speech, morphological features, lemmas, and dependency trees simultaneously for all 124 Universal Dependencies treebanks across 75 languages.
Ranked #2 on
Dependency Parsing
on French GSD
LemmaTag: Jointly Tagging and Lemmatizing for Morphologically Rich Languages with BRNNs
We present LemmaTag, a featureless neural network architecture that jointly generates part-of-speech tags and lemmas for sentences by using bidirectional RNNs with character-level and word-level embeddings.
CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
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.
UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task
UDPipe is a trainable pipeline which performs sentence segmentation, tokenization, POS tagging, lemmatization and dependency parsing.
Ranked #6 on
Dependency Parsing
on Universal Dependencies
LemmaTag: Jointly Tagging and Lemmatizing for Morphologically-Rich Languages with BRNNs
We present LemmaTag, a featureless neural network architecture that jointly generates part-of-speech tags and lemmas for sentences by using bidirectional RNNs with character-level and word-level embeddings.
Tokenizing, POS Tagging, Lemmatizing and Parsing UD 2.0 with UDPipe
A multilingual pipeline performing these steps can be trained using the Universal Dependencies project, which contains annotations of the described tasks for 50 languages in the latest release UD 2. 0.
CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
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.
Neural Networks for Multi-Word Expression Detection
In this paper we describe the MUMULS system that participated to the 2017 shared task on automatic identification of verbal multiword expressions (VMWEs).
UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing
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.
Merging Data Resources for Inflectional and Derivational Morphology in Czech
The paper deals with merging two complementary resources of morphological data previously existing for Czech, namely the inflectional dictionary MorfFlex CZ and the recently developed lexical network DeriNet.
