This paper describes a pilot study with a computed-assisted translation workbench aiming at testing the integration of online and active learning features. We investigate the effect of these features on translation productivity, using interactive translation prediction (ITP) as a baseline. User activity data were collected from five beta testers using key-logging and eye-tracking. User feedback was also collected at the end of the experiments in the form of retrospective think-aloud protocols. We found that OL performs better than ITP, especially in terms of translation speed. In addition, AL provides better translation quality than ITP for the same levels of user effort. We plan to incorporate these features in the final version of the workbench.

Quality estimation (QE) for machine translation has emerged as a promising way to provide real-world applications with methods to estimate at run-time the reliability of automatic translations. Real-world applications, however, pose challenges that go beyond those of current QE evaluation settings. For instance, the heterogeneity and the scarce availability of training data might contribute to significantly raise the bar. To address these issues we compare two alternative machine learning paradigms, namely online and multi-task learning, measuring their capability to overcome the limitations of current batch methods. The results of our experiments, which are carried out in the same experimental setting, demonstrate the effectiveness of the two methods and suggest their complementarity. This indicates, as a promising research avenue, the possibility to combine their strengths into an online multi-task approach to the problem.

This paper presents a phrase table implementation for the Moses system that computes phrase table entries for phrase-based statistical machine translation (PBSMT) on demand by sampling an indexed bitext. While this approach has been used for years in hierarchical phrase-based translation, the PBSMT community has been slow to adopt this paradigm, due to concerns that this would be slow and lead to lower translation quality. The experiments conducted in the course of this work provide evidence to the contrary: without loss in translation quality, the sampling phrase table ranks second out of four in terms of speed, being slightly slower than hash table look-up (Junczys-Dowmunt, 2012) and considerably faster than current implementations of the approach suggested by Zens and Ney (2007). In addition, the underlying parallel corpus can be updated in real time, so that professionally produced translations can be used to improve the quality of the machine translation engine immediately.

In this paper we propose a cascading framework for optimizing online learning in machine translation for a computer assisted translation scenario. With the use of online learning, several hyperparameters associated with the learning algorithm are introduced. The number of iterations of online learning can affect the translation quality as well. We discuss these issues and propose a few approaches to optimize the hyperparameters and to find the number of iterations required for online learning. We experimentally show that optimizing hyperparameters and number of iterations in online learning yields consistent improvement against baseline results.

This paper describes the facilities of Converser for Healthcare 4.0, a highly interactive speech translation system which enables users to verify and correct speech recognition and machine translation. Corrections are presently useful for real-time reliability, and in the future should prove applicable to offline machine learning. We provide examples of interactive tools in action, emphasizing semantically controlled back-translation and lexical disambiguation, and explain for the first time the techniques employed in the tools’ creation, focusing upon compilation of a database of semantic cues and its connection to third-party MT engines. Planned extensions of our techniques to statistical MT are also discussed.

The purpose of the current investigation is to predict post-editor profiles based on user behaviour and demographics using machine learning techniques to gain a better understanding of post-editor styles. Our study extracts process unit features from the CasMaCat LS14 database from the CRITT Translation Process Research Database (TPR-DB). The analysis has two main research goals: We create n-gram models based on user activity and part-of-speech sequences to automatically cluster post-editors, and we use discriminative classifier models to characterize post-editors based on a diverse range of translation process features. The classification and clustering of participants resulting from our study suggest this type of exploration could be used as a tool to develop new translation tool features or customization possibilities.