UniMorph 4.0: universal morphology
The Universal Morphology (UniMorph) project is a collaborative effort providing broad-
coverage instantiated normalized morphological inflection tables for hundreds of diverse …
coverage instantiated normalized morphological inflection tables for hundreds of diverse …
Resources for Turkish natural language processing: A critical survey
This paper presents a comprehensive survey of corpora and lexical resources available for
Turkish. We review a broad range of resources, focusing on the ones that are publicly …
Turkish. We review a broad range of resources, focusing on the ones that are publicly …
[PDF][PDF] Universal Derivations 1.0, A Growing Collection of Harmonised Word-Formation Resources.
L Kyjánek, Z Zabokrtský, M Sevcikova… - Prague Bull. Math …, 2020 - academia.edu
The paper deals with harmonisation of existing data resources containing word-formation
features by converting them into a common file format and partially aligning their annotation …
features by converting them into a common file format and partially aligning their annotation …
[PDF][PDF] The Design of Croderiv 2.0.
This paper deals with methods applied in the expansion and design of CroDeriv–the
Croatian derivational lexicon. The first version of the lexicon contained only verbs that were …
Croatian derivational lexicon. The first version of the lexicon contained only verbs that were …
Transferring Word-Formation Networks Between Languages
J Vidra, Z Žabokrtský - The Prague Bulletin of Mathematical …, 2023 - publications.cuni.cz
We present a method for supervised cross-lingual construction of word-formation networks
(WFNs). WFNs are resources capturing derivational, compositional and other relations …
(WFNs). WFNs are resources capturing derivational, compositional and other relations …
Harmonisation of language resources for word-formation of multiple languages
L Kyjánek - 2020 - dspace.cuni.cz
In the field of Natural Language Processing, word-formation is under-resourced comparing
to inflectional morphology. Moreover, the existing resources capturing word-formation differ …
to inflectional morphology. Moreover, the existing resources capturing word-formation differ …
Semi-supervised induction of morpheme boundaries in Czech using a word-formation network
This paper deals with automatic morphological segmentation of Czech lemmas contained in
the word-formation network DeriNet. Capturing derivational relations between base and …
the word-formation network DeriNet. Capturing derivational relations between base and …
[PDF][PDF] Compound Splitting and Analysis for Russian
D Vodolazsky, H Petrov - Resources and Tools for Derivational …, 2021 - nabil.hathout.free.fr
First, we classify whether a word is a compound. We solve this task as a binary classification
problem with a character-level bidirectional LSTM with attention. More formally, given a …
problem with a character-level bidirectional LSTM with attention. More formally, given a …
Next Step in Online Querying and Visualization of Word-Formation Networks
J Vidra, Z Žabokrtský - Text, Speech, and Dialogue: 23rd International …, 2020 - Springer
In this paper, we introduce a new and improved version of DeriSearch, a search engine and
visualizer for word-formation networks. Word-formation networks are datasets that express …
visualizer for word-formation networks. Word-formation networks are datasets that express …
[PDF][PDF] Morphological Networks for Persian and Turkish: What Can Be Induced from Morpheme Segmentation?
In this work, we propose an algorithm that induces morphological networks for Persian and
Turkish. The algorithm uses morpheme-segmented lexicons for the two languages. The …
Turkish. The algorithm uses morpheme-segmented lexicons for the two languages. The …