108 citations · 196 across the 18 of their papers we have counts for
19 papers
Towards a foundational model for recognising diastematic Gregorian notation
Daniel Kurek, Jan Hajič
Optical recognition of Gregorian notation has recently been attempted with end-to-end methods, with four datasets introduced. However, each of these datasets is in a different enco…
MorfFlex: Handling Rich Morphology
Jaroslava Hlaváčová, Marie Mikulová, Barbora Štěpánková +2
We present MorfFlex, a morphological dictionary architecture suitable for languages with extensive regularity in both inflection and derivation. As the primary example of MorfFlex…
Meet UD_Czech-PDTC: A Large and Genre-Rich Treebank in Universal Dependencies
Marie Mikulová, Barbora Štěpánková, Daniel Zeman +3
Czech has been part of Universal Dependencies since its first release in 2015. It has also been one of the best represented languages, with the Prague Dependency Treebank being ord…
Prague Dependency Treebank -- Consolidated 2.0: Enriching a Complex Annotation Scheme
Marie Mikulová, Jiří Mírovský, Milan Straka +4
The Prague Dependency Treebank framework is unique in its attempt to systematically include and link different layers of language, including a meaning representation with several t…
Widely Interpretable Semantic Representation: Frameless Meaning Representation for Broader Applicability
Lydia Feng, Gregor Williamson, Han He +1
This paper presents a novel semantic representation, WISeR, that overcomes challenges for Abstract Meaning Representation (AMR). Despite its strengths, AMR is not easily applied to…
Quality and Efficiency of Manual Annotation: Pre-annotation Bias
Marie Mikulová, Milan Straka, Jan Štěpánek +2
This paper presents an analysis of annotation using an automatic pre-annotation for a mid-level annotation complexity task -- dependency syntax annotation. It compares the annotati…
Extending an Event-type Ontology: Adding Verbs and Classes Using Fine-tuned LLMs Suggestions
Jana Straková, Eva Fučíková, Jan Hajič +1
In this project, we have investigated the use of advanced machine learning methods, specifically fine-tuned large language models, for pre-annotating data for a lexical extension t…
What's the Meaning of Superhuman Performance in Today's NLU?
Simone Tedeschi, Johan Bos, Thierry Declerck +9
In the last five years, there has been a significant focus in Natural Language Processing (NLP) on developing larger Pretrained Language Models (PLMs) and introducing benchmarks su…
Prague Dependency Treebank -- Consolidated 1.0
Jan Hajič, Eduard Bejček, Jaroslava Hlaváčová +4
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…
European Language Grid: An Overview
Georg Rehm, Maria Berger, Ela Elsholz +33
With 24 official EU and many additional languages, multilingualism in Europe and an inclusive Digital Single Market can only be enabled through Language Technologies (LTs). Europea…
Czech Text Processing with Contextual Embeddings: POS Tagging, Lemmatization, Parsing and NER
Milan Straka, Jana Straková, Jan Hajič
Contextualized embeddings, which capture appropriate word meaning depending on context, have recently been proposed. We evaluate two meth ods for precomputing such embeddings, BERT…
Evaluating Contextualized Embeddings on 54 Languages in POS Tagging, Lemmatization and Dependency Parsing
Milan Straka, Jana Straková, Jan Hajič
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:…
UDPipe at SIGMORPHON 2019: Contextualized Embeddings, Regularization with Morphological Categories, Corpora Merging
Milan Straka, Jana Straková, Jan Hajič
We present our contribution to the SIGMORPHON 2019 Shared Task: Crosslinguality and Context in Morphology, Task 2: contextual morphological analysis and lemmatization. We submitted…
Neural Architectures for Nested NER through Linearization
Jana Straková, Milan Straka, Jan Hajič
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. W…
Understanding Optical Music Recognition
Jorge Calvo-Zaragoza, Jan Hajič, Alexander Pacha
For over 50 years, researchers have been trying to teach computers to read music notation, referred to as Optical Music Recognition (OMR). However, this field is still difficult to…
Attention as a Perspective for Learning Tempo-invariant Audio Queries
Matthias Dorfer, Jan Hajič, Gerhard Widmer
Current models for audio--sheet music retrieval via multimodal embedding space learning use convolutional neural networks with a fixed-size window for the input audio. Depending on…
LemmaTag: Jointly Tagging and Lemmatizing for Morphologically-Rich Languages with BRNNs
Daniel Kondratyuk, Tomáš Gavenčiak, Milan Straka +1
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…
Detecting Noteheads in Handwritten Scores with ConvNets and Bounding Box Regression
Jan Hajič, Pavel Pecina
Noteheads are the interface between the written score and music. Each notehead on the page signifies one note to be played, and detecting noteheads is thus an unavoidable step for…
In Search of a Dataset for Handwritten Optical Music Recognition: Introducing MUSCIMA++
Jan Hajič, Pavel Pecina
Optical Music Recognition (OMR) has long been without an adequate dataset and ground truth for evaluating OMR systems, which has been a major problem for establishing a state of th…