Shortening of the results of machine translation using paraphrasing dataset

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10476206" target="_blank" >RIV/00216208:11320/23:10476206 - isvavai.cz</a>

Výsledek na webu

<a href="https://ceur-ws.org/Vol-3498/paper15.pdf" target="_blank" >https://ceur-ws.org/Vol-3498/paper15.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Shortening of the results of machine translation using paraphrasing dataset

Popis výsledku v původním jazyce

As machine translation applications continue to expand into the realm of real-time events, the need for faster and more concise translation becomes increasingly important. One such application is simultaneous speech translation, an emission of subtitles in the target language given speech in the source language. In this work, we focus on easing reader&apos;s comprehension of subtitles by making the translation shorter while preserving its informativeness. For this, we use the S, M and L version of the Paraphrase Database (PPDB), and exploit their property that some of the paraphrasing rules differ in length of the left and right side. Selecting rules that make the output shorter, we fine-tune an MT model to naturally generate shorter translations. The results show that the model&apos;s conciseness improves by up to 0.61%, which leaves the space for improvements using bigger versions of PPDB in future work.

Název v anglickém jazyce

Shortening of the results of machine translation using paraphrasing dataset

Popis výsledku anglicky

As machine translation applications continue to expand into the realm of real-time events, the need for faster and more concise translation becomes increasingly important. One such application is simultaneous speech translation, an emission of subtitles in the target language given speech in the source language. In this work, we focus on easing reader&apos;s comprehension of subtitles by making the translation shorter while preserving its informativeness. For this, we use the S, M and L version of the Paraphrase Database (PPDB), and exploit their property that some of the paraphrasing rules differ in length of the left and right side. Selecting rules that make the output shorter, we fine-tune an MT model to naturally generate shorter translations. The results show that the model&apos;s conciseness improves by up to 0.61%, which leaves the space for improvements using bigger versions of PPDB in future work.

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

Proceedings of the 23rd Conference Information Technologies – Applications and Theory (ITAT 2023)

ISBN

—

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

10

Strana od-do

121-130

Název nakladatele

23rd Conference on Information Technologies – Applications and Theory

Místo vydání

Košice, Slovakia

Místo konání akce

Tatranské Matliare, Slovakia

Datum konání akce

22. 9. 2023

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

—