Multilingual Central Repository: a Cross-lingual Framework for Developing Wordnets [PDF]
arXiv, 2021 Language resources are necessary for language processing,but building them is costly, involves many researches from different areas and needs constant updating. In this paper, we describe the crosslingual framework used for developing the Multilingual Central Repository (MCR), a multilingual knowledge base that includes wordnets of Basque, Catalan ...
arxiv
Interlinguistic similarity and language death dynamics [PDF]
, 2005 We analyze the time evolution of a system of two coexisting languages (Castillian Spanish and Galician, both spoken in northwest Spain) in the framework of a model given by Abrams and Strogatz [Nature 424, 900 (2003)]. It is shown that, contrary to the model's initial prediction, a stable bilingual situation is possible if the languages in competition ...
arxiv +1 more source
Exploring the Representation of Word Meanings in Context: A Case Study on Homonymy and Synonymy [PDF]
ACL-IJCNLP 2021, 2021 This paper presents a multilingual study of word meaning representations in context. We assess the ability of both static and contextualized models to adequately represent different lexical-semantic relations, such as homonymy and synonymy. To do so, we created a new multilingual dataset that allows us to perform a controlled evaluation of several ...
arxiv
Achegas a un dicionario de refráns galego-castelán, castelán-galego [PDF]
Cadernos de Fraseoloxía Galega, 2003 Monográfico. Este terceiro número de “Cadernos de Fraseoloxía Galega” é unha monografía da autoría de María do Rosario Soto Arias. Nela ofrécenos equivalencias castelás duns 4.400 refráns galegos e as equivalencias galegas duns 4.100 refráns casteláns ...
María Rosario Soto Arias
doaj
milIE: Modular & Iterative Multilingual Open Information Extraction [PDF]
arXiv, 2021 Open Information Extraction (OpenIE) is the task of extracting (subject, predicate, object) triples from natural language sentences. Current OpenIE systems extract all triple slots independently. In contrast, we explore the hypothesis that it may be beneficial to extract triple slots iteratively: first extract easy slots, followed by the difficult ones
arxiv
Aplicacións didácticas dos refráns [PDF]
Cadernos de Fraseoloxía Galega, 2004 O obxectivo deste traballo eminentemente práctico é ofrecer aos docentes de bacharelato un pequeno corpus de exercicios cuxa materia prima son os refráns galegos.
María Rosario Soto Arias +1 more
doaj
Linguistic Descriptions for Automatic Generation of Textual Short-Term Weather Forecasts on Real Prediction Data [PDF]
, 2014 We present in this paper an application which automatically generates textual short-term weather forecasts for every municipality in Galicia (NW Spain), using the real data provided by the Galician Meteorology Agency (MeteoGalicia). This solution combines in an innovative way computing with perceptions techniques and strategies for linguistic ...
arxiv +1 more source
SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding [PDF]
arXiv, 2022 This paper presents the shared task on Multilingual Idiomaticity Detection and Sentence Embedding, which consists of two subtasks: (a) a binary classification task aimed at identifying whether a sentence contains an idiomatic expression, and (b) a task based on semantic text similarity which requires the model to adequately represent potentially ...
arxiv
Mentres máis somos... Apuntamentos paremiolóxicos romances co gallo dos cinco refráns máis votados na enquisa 'Els refranys més usuals de la llengua catalana' [PDF]
, 2018 The project 'Els refranys més usuals de la llengua catalana' (http://www.refranysmesusuals.cat/) (The most common proverbs in the Catalan language) succeeded in collecting, between January 2014 and January 2015, eight hundred eighty-four (884) surveys ...
Fontana, Joan, 1977- +1 more
core
Sample Efficient Approaches for Idiomaticity Detection [PDF]
arXiv, 2022 Deep neural models, in particular Transformer-based pre-trained language models, require a significant amount of data to train. This need for data tends to lead to problems when dealing with idiomatic multiword expressions (MWEs), which are inherently less frequent in natural text.
arxiv