Realising that no single discipline will ever suffice to reveal the functioning of the human mind, cognitive science was born. The idea was to analyse complex behaviour (speaking, thinking, problem-solving) from different angles or levels and to build models that could account for them. While ambitious and intriguing, the idea looked promising enough to attract numerous researchers, and there were many opportunities then to present this kind of work. Alas, the situation has changed, the discipline has lost speed during the last decade; the reasons are multiple, ranging from lack of results to unkept promises, the fact is that funding has become more and more scarce, and so have the opportunities to present work done within this framework. In the meantime statistical approaches have gained in popularity, and evaluation has become an obligatory feature for presentation of work in the arena of computational linguistics. While there is no doubt that evaluation has certain qualities,
it does not guarantee progress or insights per se. A broader perspective is needed. To get the necessary insights and to get the big picture, we probably need to get back to the framework in which we worked in those days, which means, we should adopt and integrate multiple viewpoints, that is, take a cognitive science approach. This is the goal of this workshop. The workshop used to be called NLUCS (Natural Language Understanding and Cognitive Science), yet realising that this is too restrictive, we decided to rename it NLPCS (Natural Language Processing and Cognitive Science), as NLP is obviously more than just natural language understanding. Information Retrieval, Information Extraction, Machine Translation, Question Answering, Text Summarization, Text Generation, etc. are all part of NLP or Human Language Technology (HLT), and they all go clearly beyond language understanding. This being so, we thought it to be useful to integrate these disciplines into the debate and widen the scope of the workshop. Out of 40 papers submitted to NLPCS 21 papers were accepted as full papers, and 7 as posters covering different aspects, namely statistical methods, machine-learning based techniques, monolingual and bilingual corpora, semantic representations (interlingua), ontologies, dictionaries, thesaurus, cognitive processes (memory models), discourse (dialogue management), and metaphor analysis. Each paper was reviewed by at least two members of the programme committee who provided critical evaluations and helpful recommendations to the authors. We would like to thank both, authors and reviewers for their contribution. The keynote speaker was Yorick Wilks, who is a Professor of Computer Science at the University of Sheffield, where he directs the Institute for Language, Speech and Hearing. This workshop would not be possible without the support of the authors and dedication of our programme committee members, programme organisers, Mr. S. Hammoudi and in particular Mr. V. Pedrosa. We hope you have enjoyed NLPCS2007 and we look forward to seeing you all at NLPCS2008.
Vol. 1 - 978-972-8865-97-9