MonoTrans: Statistical Machine Translation from Monolingual Data

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F17%3A10372173" target="_blank" >RIV/00216208:11320/17:10372173 - isvavai.cz</a>

Result on the web

<a href="http://ceur-ws.org/Vol-1885/201.pdf" target="_blank" >http://ceur-ws.org/Vol-1885/201.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

MonoTrans: Statistical Machine Translation from Monolingual Data

Original language description

We present MonoTrans, a statistical machine translation system which only uses monolingual source language and target language data, without using any parallel corpora or language-specific rules. It translates each source word by the most similar target word, according to a combination of a string similarity measure and a word frequency similarity measure. It is designed for translation between very close languages, such as Czech and Slovak or Danish and Norwegian. It provides a low-quality translation in resource-poor scenarios where parallel data, required for training a high-quality translation system, may be scarce or unavailable. This is useful e.g. for cross-lingual NLP, where a trained model may be transferred from a resource-rich source language to a resource-poor target language via machine translation. We evaluate MonoTrans both intrinsically, using BLEU, and extrinsically, applying it to cross-lingual tagger and parser transfer. Although it achieves low scores, it does surpass the baselines

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year

2017

Confidentiality

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

Article name in the collection

Proceedings of the 17th conference ITAT 2017: Slovenskočeský NLP workshop (SloNLP 2017)

ISBN

978-1-974274-74-1

ISSN

1613-0073

e-ISSN

neuvedeno

Number of pages

8

Pages from-to

201-208

Publisher name

CreateSpace Independent Publishing Platform

Place of publication

Praha, Czechia

Event location

Martinské hole, Malá Fatra, Slovakia

Event date

Sep 23, 2017

Type of event by nationality

CST - Celostátní akce

UT code for WoS article

—