[PDF][PDF] Improving statistical machine translation with a multilingual paraphrase database
Abstract The multilingual Paraphrase Database (PPDB) is a freely available automatically
created resource of paraphrases in multiple languages. In statistical machine translation …
created resource of paraphrases in multiple languages. In statistical machine translation …
Linguistic features of genre and method variation in translation: A computational perspective
E Lapshinova-Koltunski, M Zampieri - … and styles: from discrete to non …, 2018 - degruyter.com
In this contribution we describe the use of text classification methods to investigate genre
and method variation in an English–German translation corpus. For this purpose we use …
and method variation in an English–German translation corpus. For this purpose we use …
Investigating genre and method variation in translation using text classification
M Zampieri, E Lapshinova-Koltunski - Text, Speech, and Dialogue: 18th …, 2015 - Springer
In this paper, we propose the use of automatic text classification methods to analyse
variation in English-German translations from both a quantitative and a qualitative …
variation in English-German translations from both a quantitative and a qualitative …
[PDF][PDF] Using comparable corpora to augment low resource smt models
A Irvine - Ann Irvine, 2014 - cis.upenn.edu
The objective of this thesis is to directly incorporate comparable corpora into the estimation
of end-to-end statistical machine translation (SMT) models. Typically, SMT models are …
of end-to-end statistical machine translation (SMT) models. Typically, SMT models are …
[PDF][PDF] Register-based machine translation evaluation with text classification techniques
M Vela, E Lapshinova-Koltunski - Proceedings of Machine …, 2015 - aclanthology.org
This paper presents a novel approach to machine translation evaluation by combining
register features–characterised by particular distributions of lexico-grammatical features …
register features–characterised by particular distributions of lexico-grammatical features …
[PDF][PDF] Using Comparable Corpora to Augment Statistical Machine Translation Models in Low Resource Settings
A Irvine - 2014 - jscholarship.library.jhu.edu
Previously, statistical machine translation (SMT) models have been estimated from parallel
corpora, or pairs of translated sentences. In this thesis, we directly incorporate comparable …
corpora, or pairs of translated sentences. In this thesis, we directly incorporate comparable …
Paraphrases for Statistical Machine Translation
R Mehdizadeh Seraj - 2015 - summit.sfu.ca
Statistical Machine Translation (SMT) is the task of automatic translation between two
natural languages (source language and target language) by using bilingual corpora. To …
natural languages (source language and target language) by using bilingual corpora. To …
Data Selection for Statistical Machine Translation
MS Duma - 2021 - ediss.sub.uni-hamburg.de
Machine Translation (MT) is a current topic in the Computational Linguistics (CL) community.
Training an MT model on a domain and using it on another domain does not yield the …
Training an MT model on a domain and using it on another domain does not yield the …
Image-image search for comparable corpora construction
Y Hong, L Yao, M Liu, T Zhang, W Zhou… - Proceedings of the …, 2016 - aclanthology.org
We present a novel method of comparable corpora construction. Unlike the traditional
methods which heavily rely on linguistic features, our method only takes image similarity into …
methods which heavily rely on linguistic features, our method only takes image similarity into …
[PDF][PDF] Obtaining SMT dictionaries for related languages
This study explores methods for developing Machine Translation dictionaries on the basis of
word frequency lists coming from comparable corpora. We investigate (1) various methods …
word frequency lists coming from comparable corpora. We investigate (1) various methods …