Machine Learning in Translation Corpora Processing

Krzysztof Wołk holds a PhD Eng. degree in Computer Science, and is a graduate of the Polish-Japanese Academy of Information Technology. He is currently an associate professor at the Cathedral of Multimedia at the same university. His research is mostly related to natural language processing and machine learning based on statistical methods, neural networks and deep learning; and is interested in IT and its challenges, and engages in interdisciplinary projects, particularly those related to HCI, UX, medicine and psychology. In addition, he has worked as a lecturer at the Warsaw School of Photography & Graphic Design, and as an IT trainer. His specialties as a teacher are primarily deep learning, machine learning, natural language processing, computational linguistics, multimedia, HCI, UX, mobile applications, HTML 5, Adobe applications and server products from Apple and Microsoft. As far as his didactic work is concerned, he leads classrooms at the faculty of computer science and at the new media art department at the Polish-Japanese Academy of Information Technology and he also used to lead classes and lectures at the Warsaw School of Photography & Graphic Design.

Table of contents

Preface

Introduction

Background and context

Machine translation (MT)

Statistical machine translation and comparable corpora

Overview of SMT

Textual Components and Corpora

Moses Tool Environment For SMT

Aspects of SMT processing

Evaluation of SMT Quality

State of the Art

Current methods and results in spoken language translation

Recent methods in comparable corpora exploration

Author’s solutions to PL-EN corpora processing problems

Parallel data mining improvements

Multi-threaded, Tuned and GPU-accelerated Yalign

Tuning of Yalign method

Minor improvements in mining for Wikipedia exploration

Parallel data mining using other methods

SMT Metric Enhancements

Alignment and filtering of corpora

Baseline system training

Description of experiments

Results and conclusions

Machine translation results

Evaluation of obtained comparable corpora

Quasi comparable corpora exploration

Other fields of MT techniques application

Final conclusions

References