You may have to Search all our reviewed books and magazines, click the sign up button below to create a free account.
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, ref...
This collection takes an interdisciplinary approach to the study of gendered technology, an emerging area of inquiry that draws on a range of fields to explore how technology is designed and used in a way that reinforces or challenges gender norms and inequalities. The volume explores different perspectives on the impact of technology on gender relations through specific cases of translation and interpreting technologies. In particular, the book considers the slow response of legal frameworks in dealing with the rise of language-based technologies, especially machine translation and large language models, and their impacts on individual and collective rights. Part I introduces the study of g...
Provides a comprehensive account of current research in computational linguistics, Fully revised and updated throughout, including 37 new chapters, Features an extended glossary to explain key terms and concepts Book jacket.
Neural networks are a family of powerful machine learning models and this book focuses on their application to natural language data. The first half of the book (Parts I and II) covers the basics of supervised machine learning and feed-forward neural networks, the basics of working with machine learning over language data, and the use of vector-based rather than symbolic representations for words. It also covers the computation-graph abstraction, which allows to easily define and train arbitrary neural networks, and is the basis behind the design of contemporary neural network software libraries. The second part of the book (Parts III and IV) introduces more specialized neural network architectures, including 1D convolutional neural networks, recurrent neural networks, conditioned-generation models, and attention-based models. These architectures and techniques are the driving force behind state-of-the-art algorithms for machine translation, syntactic parsing, and many other applications. Finally, we also discuss tree-shaped networks, structured prediction, and the prospects of multi-task learning.
Learn how to build machine translation systems with deep learning from the ground up, from basic concepts to cutting-edge research.
Extraordinary advances in machine translation over the last three quarters of a century have profoundly affected many aspects of the translation profession. The widespread integration of adaptive “artificially intelligent” technologies has radically changed the way many translators think and work. In turn, groundbreaking empirical research has yielded new perspectives on the cognitive basis of the human translation process. Translation is in the throes of radical transition on both professional and academic levels. The game-changing introduction of neural machine translation engines almost a decade ago accelerated these transitions. This volume takes stock of the depth and breadth of resulting developments, highlighting the emerging rivalry of human and machine intelligence. The gathering and analysis of big data is a common thread that has given access to new insights in widely divergent areas, from literary translation to movie subtitling to consecutive interpreting to development of flexible and powerful new cognitive models of translation.
This is the latest addition to a group of handbooks covering the field of morphology, alongside The Oxford Handbook of Case (2008), The Oxford Handbook of Compounding (2009), and The Oxford Handbook of Derivational Morphology (2014). It provides a comprehensive state-of-the-art overview of work on inflection - the expression of grammatical information through changes in word forms. The volume's 24 chapters are written by experts in the field from a variety of theoretical backgrounds, with examples drawn from a wide range of languages. The first part of the handbook covers the fundamental building blocks of inflectional form and content: morphemes, features, and means of exponence. Part 2 foc...
This is a collection of four large papers in mathematics decoted to the memory of Professor Hisao Tominaga.
Cognitive research in translation and interpreting has reached a critical threshold of maturity that is triggering rapid expansion along exciting new paths that potentially lead to deeper connections with other disciplines. Innovation and Expansion in Translation Process Research reflects this broadening scope and reach, emphasizing ongoing methodological innovations, diversification of research topics and questions, and rich interactions with adjacent fields of research. The contributions to the volume can be grouped within four loosely defined themes: advances in traditional topics in translation process research, including problems in translation, translation competence or expertise, and specialization of translators; advances in research into the emotional or affective aspects of translating and translator training; innovations in machine translation and post-editing; expansion of cognitively-oriented translation studies to include editing processes and reception studies. This timely volume highlights the burgeoning growth, diversification, and connectivity of translation process research.