paper-with-me

Papers

Revisiting Neural Language Modelling with Syllables

2020-10-24 · Arturo Oncevay, Kervy Rivas Rojas

Language modelling is regularly analysed at word, subword or character units, but syllables are seldom used. Syllables provide shorter sequences than characters, they can be extracted with rules, and their segmentation typically requires less specialised effort than identifying morphemes. We reconsider syllables for an open-vocabulary generation task in 20 languages. We use rule-based syllabification methods for five languages and address the rest with a hyphenation tool, which behaviour as syllable proxy is validated. With a comparable perplexity, we show that syllables outperform characters, annotated morphemes and unsupervised subwords. Finally, we also study the overlapping of syllables concerning other subword pieces and discuss some limitations and opportunities.

📄 PDF Abstract BibTeX arXiv:2010.12881

Code (0)

등록된 구현이 없습니다.

Tasks

Language Modelling

Similar Papers 제목 키워드 기반

Revisiting Syllables in Language Modelling and their Application on Low-Resource Machine Translation

2022-10-05 · COLING 2022 10 · Arturo Oncevay, Kervy Dante Rivas Rojas, Liz Karen Chavez Sanchez, Roberto Zariquiey

Language modelling and machine translation tasks mostly use subword or character inputs, but syllables are seldom used. Syllables provide shorter sequences than characters, require less-specialised extracting rules than …

Language ModellingMachine TranslationSegmentationTranslation

Analyzing Well-Formedness of Syllables in Japanese Sign Language

2017-11-01 · IJCNLP 2017 11 · Satoshi Yawata, Makoto Miwa, Yutaka Sasaki, Daisuke Hara

This paper tackles a problem of analyzing the well-formedness of syllables in Japanese Sign Language (JSL). We formulate the problem as a classification problem that classifies syllables into well-formed or ill-formed. W…

Active Learning

Speech and Language Resources for LVCSR of Russian

2012-05-01 · LREC 2012 5 · Sergey Zablotskiy, Alex Shvets, er, Maxim Sidorov 외

A syllable-based language model reduces the lexicon size by hundreds of times. It is especially beneficial in case of highly inflective languages like Russian due to the abundance of word forms according to various gramm…

Language ModelingLanguage ModellingSentence

Learning variable length units for SMT between related languages via Byte Pair Encoding

2016-10-20 · WS 2017 9 · Anoop Kunchukuttan, Pushpak Bhattacharyya

We explore the use of segments learnt using Byte Pair Encoding (referred to as BPE units) as basic units for statistical machine translation between related languages and compare it with orthographic syllables, which are…

Machine TranslationTranslation

Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units

2021-10-31 · Anurag Katakkar, Alan W Black

Language models (LMs) for text data have been studied extensively for their usefulness in language generation and other downstream tasks. However, language modelling purely in the speech domain is still a relatively unex…

Language ModellingText Generation