It was about one and a half years ago that I finally I arrived where I had always wanted to be and do what I had always wanted-- teach students, support small language communities and conduct research on African languages on my doorstep. The University of Cape Town and my new colleagues welcomed my efforts to establish the Centre for African Language Diversity-- CALDi as well as The African Language Archive-- TALA and I was recently appointed the Mellon Research Chair: African Language Diversity this initiative. The main aim of CALDi is to train young African scholars in descriptive linguistics and open up space for research into African languages at UCT with the hopes of countering the dominance of African linguistics outside the continent. It has been a great challenge for which my whole career has been a form of preparation...Read more
The Cambridge Handbook of Communication Disorders examines the full range of developmental and acquired communication disorders and provides the most up-to-date and comprehensive guide to the epidemiology, aetiology and clinical features of these disorders.
Semi-Supervised Learning and Domain Adaptation in Natural Language Processing
This book introduces basic supervised learning algorithms applicable to natural language processing (NLP) and shows how the performance of these algorithms can often be improved by exploiting the marginal distribution of large amounts of unlabeled data. One reason for that is data sparsity, i.e., the limited amounts of data we have available in NLP. However, in most real-world NLP applications our labeled data is also heavily biased. This book introduces extensions of supervised learning algorithms to cope with data sparsity and different kinds of sampling bias.
This book is intended to be both readable by first-year students and interesting to the expert audience. My intention was to introduce what is necessary to appreciate the major challenges we face in contemporary NLP related to data sparsity and sampling bias, without wasting too much time on details about supervised learning algorithms or particular NLP applications. I use text classification, part-of-speech tagging, and dependency parsing as running examples, and limit myself to a small set of cardinal learning algorithms. I have worried less about theoretical guarantees ("this algorithm never does too badly") than about useful rules of thumb ("in this case this algorithm may perform really well"). In NLP, data is so noisy, biased, and non-stationary that few theoretical guarantees can be established and we are typically left with our gut feelings and a catalogue of crazy ideas. I hope this book will provide its readers with both. Throughout the book we include snippets of Python code and empirical evaluations, when relevant.