This book constitutes the refereed proceedings of the 25th Canadian Conference on Artificial Intelligence, Canadian AI 2012, held in Toronto, Canada, in May 2012. The 23 regular papers, 16 short papers, and 4 papers from the Graduate Student Symposium presented were carefully reviewed and selected for inclusion in this book. The papers cover a broad range of topics presenting original work in all areas of artificial intelligence, either theoretical or applied.

In recent years, online social networking has revolutionized interpersonal communication. The newer research on language analysis in social media has been increasingly focusing on the latter's impact on our daily lives, both on a personal and a professional level. Natural language processing (NLP) is one of the most promising avenues for social media data processing. It is a scientific challenge to develop powerful methods and algorithms that extract relevant information from a large volume of data coming from multiple sources and languages in various formats or in free form. This book will discuss the challenges in analyzing social media texts in contrast with traditional documents. Research methods in information extraction, automatic categorization and clustering, automatic summarization and indexing, and statistical machine translation need to be adapted to a new kind of data. This book reviews the current research on NLP tools and methods for processing the non-traditional information from social media data that is available in large amounts, and it shows how innovative NLP approaches can integrate appropriate linguistic information in various fields such as social media monitoring, health care, and business intelligence. The book further covers the existing evaluation metrics for NLP and social media applications and the new efforts in evaluation campaigns or shared tasks on new datasets collected from social media. Such tasks are organized by the Association for Computational Linguistics (such as SemEval tasks), the National Institute of Standards and Technology via the Text REtrieval Conference (TREC) and the Text Analysis Conference (TAC), or the Conference and Labs of the Evaluation Forum (CLEF). In this third edition of the book, the authors added information about recent progress in NLP for social media applications, including more about the modern techniques provided by deep neural networks (DNNs) for modeling language and analyzing social media data.

Current natural language generation or machine translation systems cannot distinguish among near-synonyms - words that share the same core meaning but vary in their lexical nuances. This is due to a lack of knowledge about differences between near-synonyms in existing computational lexical resources. In this work, I automatically acquired a lexical knowledge-base of near-synonym differences from multiple sources, using an unsupervised decision- list algorithm. The main types of differences are: stylistic (for example, "inebriated" is more formal than "drunk"), attitudinal (for example, "skinny" is more pejorative than "slim"), and denotational (for example, "blunder" implies "accident" and "ignorance," while "error" does not). To show how the knowledge-base can be used in practice, I designed Xenon, a natural language generation system system that chooses the near-synonym that best matches a set of input preferences. I implemented Xenon by adding a near-synonym choice module and a near-synonym collocation module to an existing general-purpose surface realizer.