Results 31 to 40 of about 123,842 (329)
End-to-End Bias Mitigation by Modelling Biases in Corpora [PDF]
Annual Meeting of the Association for Computational Linguistics, 2019 Several recent studies have shown that strong natural language understanding (NLU) models are prone to relying on unwanted dataset biases without learning the underlying task, resulting in models that fail to generalize to out-of-domain datasets and are ...
Rabeeh Karimi Mahabadi +2 more
semanticscholar +1 more source
On the Use of Corpora in Second Language Acquisition – Chinese as an Example
Acta Linguistica Asiatica, 2021 This paper aims to introduce the language corpora and the advantages of their use in the process of Chinese language acquisition. We provide practical examples of the corpora's direct and indirect use for teaching and learning Chinese as a second ...
Mária Ištvánová
doaj +1 more source
Slovenski Jezik - Slovene Linguistic Studies, 2023 The article aims at presenting the methods of detection of Slovenian neologisms, used in the making of the Growing Dictionary of the Slovenian Language, accessible at the Fran portal , which integrates various dictionaries into a single whole, form 2014 ...
Domen Krvina
doaj +1 more source
Corpora for Linguists vs. Corpora for Learners
Educazione Linguistica Language Education, 2019 EL ...
Forti, Luciana, Spina, Stefania
openaire +2 more sources
Voice conversion from non-parallel corpora using variational auto-encoder [PDF]
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2016 We propose a flexible framework for spectral conversion (SC) that facilitates training with unaligned corpora. Many SC frameworks require parallel corpora, phonetic alignments, or explicit frame-wise correspondence for learning conversion functions or ...
Chin-Cheng Hsu +4 more
semanticscholar +1 more source
The Saudi Novel Corpus: Design and Compilation
Applied Sciences, 2022 Arabic has recently received significant attention from corpus compilers. This situation has led to the creation of many Arabic corpora that cover various genres, most notably the newswire genre.
Tareq Alfraidi +4 more
doaj +1 more source
Exploração de corpora para extração e descrição de léxico de especialidade
Linha D'Água, 2020 A exploração de corpora para a extração de léxico de especialidade é um método consensual e comum na construção de recursos lexicais. No entanto, as metodologias empregadas não são explicitamente discutidas, dificultando a comparação e a determinação de ...
Chiara Barbero, Raquel Amaro
doaj +1 more source
Semantics and Pragmatics, 2015 A prevalent, but to date untested, assumption about lexicalized scalar implicatures such as those from some to not all, is that they fall into the class of GCIs and as such, constitute a homogeneous class of highly regularized and context-independent ...
Judith Degen
doaj +1 more source
Morphological Tagging and Lemmatization in the Albanian Language
SEEU Review, 2021 An important element of Natural Language Processing is parts of speech tagging. With fine-grained word-class annotations, the word forms in a text can be enhanced and can also be used in downstream processes, such as dependency parsing.
Mati Diellza Nagavci +2 more
doaj +1 more source
How readers perceive translated literary works: an analysis of reader reception
Lingue e Linguaggi, 2015 - The aim of this paper is to investigate the reader’s reception of translated literary texts and to explore the reader’s expectations about literary works.
Angela D'Egidio
doaj +1 more source