Publication:

Neural text normalization with adapted decoding and POS features

Date

Date

Date
2019
Journal Article
Published version

Citations

Citation copied

Ruzsics, T., Lusetti, M., Göhring, A., Samardžić, T., & Stark, E. (2019). Neural text normalization with adapted decoding and POS features. Natural Language Engineering, 25(5), 585–605. https://doi.org/10.1017/S1351324919000391

Abstract

Abstract

Abstract

Text normalization is the task of mapping noncanonical language, typical of speech transcription and computer-mediated communication, to a standardized writing. This task is especially important for languages such as Swiss German, with strong regional variation and no written standard. In this paper, we propose a novel solution for normalizing Swiss German WhatsApp messages using the encoder–decoder neural machine translation (NMT) framework. We enhance the performance of a plain character-level NMT model with the integration of a wor

Metrics

Downloads

73 since deposited on 2019-11-27
Acq. date: 2025-11-13

Views

175 since deposited on 2019-11-27
Acq. date: 2025-11-13

Additional indexing

Creators (Authors)

Journal/Series Title

Journal/Series Title

Journal/Series Title

Volume

Volume

Volume
25

Number

Number

Number
5

Page range/Item number

Page range/Item number

Page range/Item number
585

Page end

Page end

Page end
605

Item Type

Item Type

Item Type
Journal Article

Language

Language

Language
English

Publication date

Publication date

Publication date
2019-09

Date available

Date available

Date available
2019-11-27

Publisher

Publisher

Publisher

ISSN or e-ISSN

ISSN or e-ISSN

ISSN or e-ISSN
1351-3249

OA Status

OA Status

OA Status
Green

Metrics

Downloads

73 since deposited on 2019-11-27
Acq. date: 2025-11-13

Views

175 since deposited on 2019-11-27
Acq. date: 2025-11-13

Citations

Citation copied

Ruzsics, T., Lusetti, M., Göhring, A., Samardžić, T., & Stark, E. (2019). Neural text normalization with adapted decoding and POS features. Natural Language Engineering, 25(5), 585–605. https://doi.org/10.1017/S1351324919000391

Green Open Access
Loading...
Thumbnail Image

Files

Files

Files
Files available to download:1

Files

Files

Files
Files available to download:1
Loading...
Thumbnail Image