paper-with-me

홈 › Papers

Rediscovering the Slavic Continuum in Representations Emerging from Neural Models of Spoken Language Identification

2020-10-22 · VarDial (COLING) 2020 12 · Badr M. Abdullah, Jacek Kudera, Tania Avgustinova, Bernd Möbius, Dietrich Klakow

Deep neural networks have been employed for various spoken language recognition tasks, including tasks that are multilingual by definition such as spoken language identification. In this paper, we present a neural model for Slavic language identification in speech signals and analyze its emergent representations to investigate whether they reflect objective measures of language relatedness and/or non-linguists' perception of language similarity. While our analysis shows that the language representation space indeed captures language relatedness to a great extent, we find perceptual confusability between languages in our study to be the best predictor of the language representation similarity.

📄 PDF Abstract BibTeX arXiv:2010.11973

Code (0)

등록된 구현이 없습니다.

Tasks

Language IdentificationSpoken language identification

Similar Papers 제목 키워드 기반

Multi-source morphosyntactic tagging for spoken Rusyn

2017-04-01 · WS 2017 4 · Yves Scherrer, Achim Rabus

This paper deals with the development of morphosyntactic taggers for spoken varieties of the Slavic minority language Rusyn. As neither annotated corpora nor parallel corpora are electronically available for Rusyn, we pr…

Morphological TaggingPart-Of-Speech Tagging

Modeling the Impact of Syntactic Distance and Surprisal on Cross-Slavic Text Comprehension

2022-06-01 · LREC 2022 6 · Irina Stenger, Philip Georgis, Tania Avgustinova, Bernd Möbius 외

We focus on the syntactic variation and measure syntactic distances between nine Slavic languages (Belarusian, Bulgarian, Croatian, Czech, Polish, Slovak, Slovene, Russian, and Ukrainian) using symmetric measures of inse…

Cloze TestReading Comprehension

Lexicon Induction for Spoken Rusyn -- Challenges and Results

2017-04-01 · WS 2017 4 · Achim Rabus, Yves Scherrer

This paper reports on challenges and results in developing NLP resources for spoken Rusyn. Being a Slavic minority language, Rusyn does not have any resources to make use of. We propose to build a morphosyntactic diction…

Transfer Learning for an Endangered Slavic Variety: Dependency Parsing in Pomak Across Contact-Shaped Dialects

2026-03-30 · Sercan Karakaş arxiv

This paper presents new resources and baselines for Dependency Parsing in Pomak, an endangered Eastern South Slavic language with substantial dialectal variation and no widely adopted standard. We focus on the variety sp…

Dependency ParsingTransfer Learning

Cross-Domain Adaptation of Spoken Language Identification for Related Languages: The Curious Case of Slavic Languages

2020-08-02 · Badr M. Abdullah, Tania Avgustinova, Bernd Möbius, Dietrich Klakow

State-of-the-art spoken language identification (LID) systems, which are based on end-to-end deep neural networks, have shown remarkable success not only in discriminating between distant languages but also between close…

DiversityDomain AdaptationLanguage IdentificationSpoken language identification+1