Transferring Word-Formation Networks Between Languages
![Thumbnail](/bitstream/handle/20.500.14178/2316/art-vidra-zabokrtsky.pdf.jpg?sequence=5&isAllowed=y)
Publication date
2023Published in
The Prague Bulletin of Mathematical LinguisticsVolume / Issue
Neuveden (120)ISBN / ISSN
ISSN: 0032-6585Metadata
Show full item recordCollections
This publication has a published version with DOI 10.14712/00326585.027
Abstract
We present a method for supervised cross-lingual construction of word-formation networks (WFNs). WFNs are resources capturing derivational, compositional and other relations between lexical units in a single language. Current state-of-the-art methods for automatically creating them typically rely on supervised or unsupervised pattern-matching of affixes in string representations of words, with few recent inroads into deep learning. All methods known to us work purely in a monolingual setting, limiting the use of higher-quality supervised models to high-resource languages.In this paper, we present two methods, one based on cross-lingual word alignments and translation and another based on cross-lingual word embeddings and neural networks. Both methods are capable of transfer of WFNs into languages for which no word-formational data are available. We evaluate our models on manually-annotated word-formation data from the Universal Derivations and UniMorph projects.
Keywords
word formation, multilinguality, wordnet
Permanent link
https://hdl.handle.net/20.500.14178/2316License
Full text of this result is licensed under: Creative Commons Uveďte původ-Neužívejte dílo komerčně-Nezpracovávejte 3.0 Unported