<--- Back to Details
First PageDocument Content
Natural language processing / Evaluation of machine translation / Computational linguistics / Applied linguistics / Chunking / Moses / BLEU / Statistical machine translation / Language acquisition / Linguistics / Machine translation / Science
Date: 2009-09-10 05:00:21
Natural language processing
Evaluation of machine translation
Computational linguistics
Applied linguistics
Chunking
Moses
BLEU
Statistical machine translation
Language acquisition
Linguistics
Machine translation
Science

Decoding by dynamic chunking for statistical machine translation

Add to Reading List

Source URL: www.mt-archive.info

Download Document from Source Website

File Size: 126,69 KB

Share Document on Facebook

Similar Documents

Computing / Computational linguistics / Linguistics / Information science / Artificial neural network / SPARQL / Semantic parsing / Word-sense disambiguation / Semantic Web / Natural language processing / Query language / Question answering

Neural Machine Translation for Query Construction and Composition Tommaso Soru 1 Edgard Marx 1 Andr´e Valdestilhas 1 Diego Esteves 2 Diego Moussallem 1 Gustavo Publio 1 Abstract Research on question answering with know

DocID: 1xU5z - View Document

Learning to Generate Pseudo-code from Source Code using Statistical Machine Translation Yusuke Oda, Hiroyuki Fudaba, Graham Neubig, Hideaki Hata, Sakriani Sakti, Tomoki Toda, and Satoshi Nakamura Graduate School of Infor

DocID: 1vqGB - View Document

The UMD Machine Translation Systems at IWSLT 2016: English-to-French Translation of Speech Transcripts Xing Niu, Marine Carpuat Dept. of Computer Science University of Maryland, College Park {xingniu,marine}@cs.umd.edu

DocID: 1vn4e - View Document

Learning to Translate in Real-time with Neural Machine Translation † ‡ ♦

DocID: 1viZS - View Document

Domain Adaptation in Machine Translation Cristina España-Bonet, Georg Heigold Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI) 15th March, 2017 This project has received funding from the

DocID: 1vfls - View Document