1 |
AUTOLEX: An Automatic Framework for Linguistic Exploration ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models
|
|
|
|
In: NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies ; https://hal.inria.fr/hal-03251105 ; NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun 2021, Mexico City, Mexico (2021)
|
|
BASE
|
|
Show details
|
|
3 |
SD-QA: Spoken Dialectal Question Answering for the Real World ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
SD-QA: Spoken Dialectal Question Answering for the Real World ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Machine Translation into Low-resource Language Varieties ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Code to Comment Translation: A Comparative Study on Model Effectiveness & Errors ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Systematic Inequalities in Language Technology Performance across the World's Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Towards More Equitable Question Answering Systems: How Much More Data Do You Need? ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Cross-Lingual Text Classification of Transliterated Hindi and Malayalam ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Evaluating the Morphosyntactic Well-formedness of Generated Texts ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Evaluating the Morphosyntactic Well-formedness of Generated Texts ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Towards more equitable question answering systems: How much more data do you need? ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Lexically Aware Semi-Supervised Learning for OCR Post-Correction ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
When is Wall a Pared and when a Muro? -- Extracting Rules Governing Lexical Selection ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
When is Wall a Pared and when a Muro?: Extracting Rules Governing Lexical Selection ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Lexically-Aware Semi-Supervised Learning for OCR Post-Correction ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
AlloVera: a multilingual allophone database
|
|
Mortensen, David,; Li, Xinjian; Littell, Patrick; Michaud, Alexis; Rijhwani, Shruti; Anastasopoulos, Antonios; Black, Alan; Metze, Florian; Neubig, Graham
|
|
In: LREC 2020: 12th Language Resources and Evaluation Conference ; https://halshs.archives-ouvertes.fr/halshs-02527046 ; LREC 2020: 12th Language Resources and Evaluation Conference, European Language Resources Association, May 2020, Marseille, France ; https://lrec2020.lrec-conf.org/ (2020)
|
|
Abstract:
International audience ; We introduce a new resource, AlloVera, which provides mappings from 218 allophones to phonemes for 14 languages. Phonemes are contrastive phonological units, and allophones are their various concrete realizations, which are predictable from phonological context. While phonemic representations are language specific, phonetic representations (stated in terms of (allo)phones) are much closer to a universal (language-independent) transcription. AlloVera allows the training of speech recognition models that output phonetic transcriptions in the International Phonetic Alphabet (IPA), regardless of the input language. We show that a "universal" allophone model, Allosaurus, built with AlloVera, outperforms "universal" phonemic models and language-specific models on a speech-transcription task. We explore the implications of this technology (and related technologies) for the documentation of endangered and minority languages. We further explore other applications for which AlloVera will be suitable as it grows, including phonological typology.
|
|
Keyword:
[SHS.LANGUE]Humanities and Social Sciences/Linguistics; [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing; Allophones; Phoneme
|
|
URL: https://halshs.archives-ouvertes.fr/halshs-02527046/file/MultilingualAllophoneResourceforNearUniversalASR.pdf https://halshs.archives-ouvertes.fr/halshs-02527046/document https://halshs.archives-ouvertes.fr/halshs-02527046
|
|
BASE
|
|
Hide details
|
|
|
|