Comparative Stylistics In An Integrated Machine Translation System

Abstract: "Comparative stylistics is a subfield of stylistics that attempts to account for the differences in style between languages. Rules of comparative stylistics are commonly presented, in textbooks of translation, as 'rules of thumb', but if we hope to incorporate a knowledge of comparative stylistics into natural language understanding systems, we must take a more formal approach. In particular, we will develop a computational model of comparative stylistics for machine translation that could be used to guide translation and thereby improve the quality of the translated output. An implementation of this model would provide additional information to the machine translation system about the potential modulations to the translated text and their effects, enabling it to make a more informed decision. In this thesis, we develop a set of formal rules of syntactic French-English comparative stylistics to be used as a component of a model of comparative stylistics. As the foundation for the formal rules, we adapt theoretical rules of syntactic French-English comparative stylistics compiled by Guillemin-Flescher [1981] and the formal representation of syntactic style developed by DiMarco [1990]. A corpus of French sentences and their English translations is analyzed to convert the theoretical rules to a set of formal rules that builds on DiMarco's grammars of syntactic style. Thus, we present a formal grammar of French- English comparative stylistics. We also suggest a method for incorporating these rules into an existing machine translation system."

Recognizing that the generation of natural language is a goal- driven process, where many of the goals are pragmatic (i.e., interpersonal and situational) in nature, this book provides an overview of the role of pragmatics in language generation. Each chapter states a problem that arises in generation, develops a pragmatics-based solution, and then describes how the solution is implemented in PAULINE, a language generator that can produce numerous versions of a single underlying message, depending on its setting.

Contrastive Linguistics (CL), Translation Studies (TS) and Machine Translation (MT) have common grounds: They all work at the crossroad where two or more languages meet. Despite their inherent relatedness, methodological exchange between the three disciplines is rare. This special issue touches upon areas where the three fields converge. It results directly from a workshop at the 2011 German Association for Language Technology and Computational Linguistics (GSCL) conference in Hamburg where researchers from the three fields presented and discussed their interdisciplinary work. While the studies contained in this volume draw from a wide variety of objectives and methods, and various areas of overlaps between CL, TS and MT are addressed, the volume is by no means exhaustive with regard to this topic. Further cross-fertilisation is not only desirable, but almost mandatory in order to tackle future tasks and endeavours.}

Post-editing is possibly the oldest form of human-machine cooperation for translation. It has been a common practice for just about as long as operational machine translation systems have existed. Recently, however, there has been a surge of interest in post-editing among the wider user community, partly due to the increasing quality of machine translation output, but also to the availability of free, reliable software for both machine translation and post-editing. As a result, the practices and processes of the translation industry are changing in fundamental ways. This volume is a compilation of work by researchers, developers and practitioners of post-editing, presented at two recent events on post-editing: The first Workshop on Post-editing Technology and Practice, held in conjunction with the 10th Conference of the Association for Machine Translation in the Americas, held in San Diego, in 2012; and the International Workshop on Expertise in Translation and Post-editing Research and Application, held at the Copenhagen Business School, in 2012.

This is the first volume that brings together research and practice from academic and industry settings and a combination of human and machine translation evaluation. Its comprehensive collection of papers by leading experts in human and machine translation quality and evaluation who situate current developments and chart future trends fills a clear gap in the literature. This is critical to the successful integration of translation technologies in the industry today, where the lines between human and machine are becoming increasingly blurred by technology: this affects the whole translation landscape, from students and trainers to project managers and professionals, including in-house and freelance translators, as well as, of course, translation scholars and researchers. The editors have broad experience in translation quality evaluation research, including investigations into professional practice with qualitative and quantitative studies, and the contributors are leading experts in their respective fields, providing a unique set of complementary perspectives on human and machine translation quality and evaluation, combining theoretical and applied approaches.

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.