Transferring Word-Formation Networks Between Languages

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475681" target="_blank" >RIV/00216208:11320/23:10475681 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=bKtH1v2k6z" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=bKtH1v2k6z</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.14712/00326585.027" target="_blank" >10.14712/00326585.027</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Transferring Word-Formation Networks Between Languages

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Transferring Word-Formation Networks Between Languages

Popis výsledku anglicky

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.

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF19_073%2F0016935" target="_blank" >EF19_073/0016935: Grantová schémata na UK</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

The Prague Bulletin of Mathematical Linguistics

ISSN

0032-6585

e-ISSN

1804-0462

Svazek periodika

Neuveden

Číslo periodika v rámci svazku

120

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

25

Strana od-do

47-71

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—