Genre Transfer in NMT: Creating Synthetic Spoken Parallel Sentences using Written Parallel Data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475925" target="_blank" >RIV/00216208:11320/23:10475925 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.lcs2.in/ICON-2022/index.html" target="_blank" >https://www.lcs2.in/ICON-2022/index.html</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Genre Transfer in NMT: Creating Synthetic Spoken Parallel Sentences using Written Parallel Data

Popis výsledku v původním jazyce

Text style transfer (TST) aims to control attributes in a given text without changing the content. The matter gets complicated when the boundary separating two styles gets blurred. We can notice similar difficulties in the case of parallel datasets in spoken and written genres. Genuine spoken features like filler words and repetitions in the existing spoken genre parallel datasets are often cleaned during transcription and translation, making the texts closer to written datasets. This poses several problems for spoken genre-specific tasks like simultaneous speech translation. This paper seeks to address the challenge of improving spoken language translations. We start by creating a genre classifier for individual sentences and then try two approaches for data augmentation using written examples: (1) a novel method that involves assembling and disassembling spoken and written neural machine translation (NMT) models, and (2) a rule-based method to inject spoken features. Though the observed results for (1) are not promising, we get some interesting insights into the solution. The model proposed in (1) fine-tuned on the synthesized data from (2) produces naturally looking spoken translations for writtenRIGHTWARDS ARROWspoken genre transfer in En-Hi translation systems. We use this system to produce a second-stage En-Hi synthetic corpus, which however lacks appropriate alignments of explicit spoken features across the languages. For the final evaluation, we fine-tune Hi-En spoken translation systems on the synthesized parallel corpora. We observe that the parallel corpus synthesized using our rule-based method produces the best results.

Název v anglickém jazyce

Genre Transfer in NMT: Creating Synthetic Spoken Parallel Sentences using Written Parallel Data

Popis výsledku anglicky

Text style transfer (TST) aims to control attributes in a given text without changing the content. The matter gets complicated when the boundary separating two styles gets blurred. We can notice similar difficulties in the case of parallel datasets in spoken and written genres. Genuine spoken features like filler words and repetitions in the existing spoken genre parallel datasets are often cleaned during transcription and translation, making the texts closer to written datasets. This poses several problems for spoken genre-specific tasks like simultaneous speech translation. This paper seeks to address the challenge of improving spoken language translations. We start by creating a genre classifier for individual sentences and then try two approaches for data augmentation using written examples: (1) a novel method that involves assembling and disassembling spoken and written neural machine translation (NMT) models, and (2) a rule-based method to inject spoken features. Though the observed results for (1) are not promising, we get some interesting insights into the solution. The model proposed in (1) fine-tuned on the synthesized data from (2) produces naturally looking spoken translations for writtenRIGHTWARDS ARROWspoken genre transfer in En-Hi translation systems. We use this system to produce a second-stage En-Hi synthetic corpus, which however lacks appropriate alignments of explicit spoken features across the languages. For the final evaluation, we fine-tune Hi-En spoken translation systems on the synthesized parallel corpora. We observe that the parallel corpus synthesized using our rule-based method produces the best results.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GX19-26934X" target="_blank" >GX19-26934X: Neuronové reprezentace v multimodálním a mnohojazyčném modelování</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

19th International Conference on Natural Language Processing

ISBN

978-1-959429-38-8

ISSN

—

e-ISSN

—

Počet stran výsledku

10

Strana od-do

224-233

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Delhi, India

Datum konání akce

15. 12. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—