Readings In Machine Translation

The field of machine translation (MT) - the automation of translation between human languages - has existed for more than 50 years. MT helped to usher in the field of computational linguistics and has influenced methods and applications in knowledge representation, information theory, and mathematical statistics.

Designed for translators and other professional linguists, this work attempts to clarify, explain and exemplify the impact that computers have had and are having on their profession. The book concerns machine translation, computer-aided translation and the future of translation and the computer.

Many applications within natural language processing involve performing text-to-text transformations, i.e., given a text in natural language as input, systems are required to produce a version of this text (e.g., a translation), also in natural language, as output. Automatically evaluating the output of such systems is an important component in developing text-to-text applications. Two approaches have been proposed for this problem: (i) to compare the system outputs against one or more reference outputs using string matching-based evaluation metrics and (ii) to build models based on human feedback to predict the quality of system outputs without reference texts. Despite their popularity, reference-based evaluation metrics are faced with the challenge that multiple good (and bad) quality outputs can be produced by text-to-text approaches for the same input. This variation is very hard to capture, even with multiple reference texts. In addition, reference-based metrics cannot be used in production (e.g., online machine translation systems), when systems are expected to produce outputs for any unseen input. In this book, we focus on the second set of metrics, so-called Quality Estimation (QE) metrics, where the goal is to provide an estimate on how good or reliable the texts produced by an application are without access to gold-standard outputs. QE enables different types of evaluation that can target different types of users and applications. Machine learning techniques are used to build QE models with various types of quality labels and explicit features or learnt representations, which can then predict the quality of unseen system outputs. This book describes the topic of QE for text-to-text applications, covering quality labels, features, algorithms, evaluation, uses, and state-of-the-art approaches. It focuses on machine translation as application, since this represents most of the QE work done to date. It also briefly describes QE for several other applications, including text simplification, text summarization, grammatical error correction, and natural language generation.

All over the world, people are claiming their rights. Are these claims prompted by similar values and aspirations? And even if human rights are universal, what are the consequences of claiming them in different historical, cultural and material realities? The diversity of African countries considered in this book compels careful thought about these questions.

This is the first book devoted exclusively to knowledge-based machine translation. While most approaches to the machine translation for natural languages seek ways to translate source language texts into target language texts without full understanding of the text, knowledge-based machine translation is based on extracting and representing the meaning of the source text. It is scientifically the most challenging approach to the task of machine translation, and significant progress has been achieved within it in recent years. The authors introduce the general paradigm of knowledge-based MT, survey major recent developments, compare it with other approaches and present a paradigmatic view of its component processes

Learn how to build machine translation systems with deep learning from the ground up, from basic concepts to cutting-edge research.

This book compares and contrasts the principles and practices of rule-based machine translation (RBMT), statistical machine translation (SMT), and example-based machine translation (EBMT). Presenting numerous examples, the text introduces language divergence as the fundamental challenge to machine translation, emphasizes and works out word alignment, explores IBM models of machine translation, covers the mathematics of phrase-based SMT, provides complete walk-throughs of the working of interlingua-based and transfer-based RBMT, and analyzes EBMT, showing how translation parts can be extracted and recombined to automatically translate a new input.