Page
%P
-
Article
Open AccessA user study of neural interactive translation prediction
Machine translation (MT) on its own is generally not good enough to produce high-quality translations, so it is common to have humans intervening in the translation process to improve MT output. A typical inte...
-
Chapter
Closing Remarks
-
Chapter
Learning from Parallel Text
The previous chapter provided formal foundations for syntax-based translation models, along with a taxonomy of formalism types. But where do grammars come from? In this chapter, we describe the concrete method...
-
Chapter
Decoding III: String Decoding
String decoding has a lot in common with tree decoding. Almost all of the search machinery from the previous chapter can be redeployed here (in fact, the methods were originally developed for string decoding)....
-
Book
-
Chapter
Decoding II: Tree Decoding
This chapter describes tree decoding, a two-stage approach to decoding in which the input sentence is first parsed and then the resulting parse tree is translated. We will focus on the second stage, assuming t...
-
Chapter
Selected Topics
The central focus of this book has been on the use of syntax to model the ways that phrases are reordered between languages. This has taken six chapters, but even still, we are far from covering all of the way...
-
Chapter
Models
During the last 20 years, researchers have proposed a wide range of syntax-based approaches to statistical machine translation. While a core set of methods has now crystallized and become dominant, much of the...
-
Chapter
Decoding I: Preliminaries
Decoding in statistical machine translation is the computational process of searching for the most probable translation (or k most probable translations) of a source sentence according to a model. For the models ...
-
Article
Interactive translation prediction versus conventional post-editing in practice: a study with the CasMaCat workbench
We conducted a field trial in computer-assisted professional translation to compare interactive translation prediction (ITP) against conventional post-editing (PE) of machine translation (MT) output. In contra...
-
Article
Monte Carlo techniques for phrase-based translation
Recent advances in statistical machine translation have used approximate beam search for NP-complete inference within probabilistic translation models. We present an alternative approach of sampling from the p...
-
Article
Review of Cyril Goutte, Nicola Cancedda, Marc Dymetman, and George Foster (eds): Learning machine translation
-
Article
A process study of computer-aided translation
We investigate novel types of assistance for human translators, based on statistical machine translation methods. We developed the computer-aided tool Caitra that makes suggestions for sentence completion, shows ...
-
Chapter and Conference Paper
Pharaoh: A Beam Search Decoder for Phrase-Based Statistical Machine Translation Models
We describe Pharaoh, a freely available decoder for phrase-based statistical machine translation models. The decoder is the implement at ion of an efficient dynamic programming search algorithm with lattice ge...
-
Article
Translation with Scarce Bilingual Resources
Machine translation of human languages is a field almost as old as computers themselves. Recent approaches to this challenging problem aim at learning translation knowledge automatically (or semi-automatically...
-
Chapter and Conference Paper
Combining Multiclass Maximum Entropy Text Classifiers with Neural Network Voting
We improve a high-accuracy maximum entropy classifier by combining an ensemble of classifiers with neural network voting. In our experiments we demonstrate significantly superior performance both over a single...
