Learning Language in Logic (Lecture Notes in Computer Science (1925))

This volume has its origins in the ?rst Learning Language in Logic (LLL) wo- shop which took place on 30 June 1999 in Bled, Slovenia immediately after the Ninth International Workshop on Inductive Logic Programming (ILP’99) and the Sixteenth International Conference on Machine Learning (ICML’99). LLL is a research area lying at the intersection of computational linguistics, machine learning, and computational logic. As such it is of interest to all those working in these three ?elds. I am pleased to say that the workshop attracted subm- sions from both the natural language processing (NLP) community and the ILP community, re?ecting the essentially multi-disciplinary nature of LLL. Eric Brill and Ray Mooney were invited speakers at the workshop and their contributions to this volume re?ect the topics of their stimulating invited talks. After the workshop authors were given the opportunity to improve their papers, the results of which are contained here. However, this volume also includes a substantial amount of two sorts of additional material. Firstly, since our central aim is to introduce LLL work to the widest possible audience, two introductory chapters have been written. Dzeroski, ? Cussens and Manandhar provide an - troduction to ILP and LLL and Thompson provides an introduction to NLP. An Introduction to Inductive Logic Programming and Learning Language in Logic....Pages 3-35 A Brief Introduction to Natural Language Processing for Non-linguists....Pages 36-48 A Closer Look at the Automatic Induction of Linguistic Knowledge....Pages 49-56 Learning for Semantic Interpretation: Scaling Up without Dumbing Down....Pages 57-66 Learning to Lemmatise Slovene Words....Pages 69-88 Achievements and Prospects of Learning Word Morphology with Inductive Logic Programming....Pages 89-109 Learning the Logic of Simple Phonotactics....Pages 110-124 Grammar Induction as Substructural Inductive Logic Programming....Pages 127-142 Experiments in Inductive Chart Parsing....Pages 143-156 ILP in Part-of-Speech Tagging — An Overview....Pages 157-169 Iterative Part-of-Speech Tagging....Pages 170-183 DCG Induction Using MDL and Parsed Corpora....Pages 184-198 Learning Log-Linear Models on Constraint-Based Grammars for Disambiguation....Pages 199-217 Unsupervised Lexical Learning with Categorial Grammars Using the LLL Corpus....Pages 218-236 Induction of Recursive Transfer Rules....Pages 237-246 Learning for Text Categorization and Information Extraction with ILP....Pages 247-258 Corpus-Based Learning of Semantic Relations by the ILP System, Asium....Pages 259-278 Improving Learning by Choosing Examples Intelligently in Two Natural Language Tasks....Pages 279-299

This book provides a self-contained introduction to Learning Language in Logic (LLL) and, at the same time, competently surveys the current state of the art of research in the area. The book has its origin in the first LLL workshop which took place in Bled, Slovenia in June 1999. Beyond revised workshop papers, a number of additional chapters were solicited from leading researchers in order to achieve complete coverage of all current aspects and to introduce the new area to a broader audience.
As the first book devoted to LLL, this thoroughly cross-reviewed state-of-the-art survey will become a valuable source of reference for researchers active in the area. Newcomers or professionals interested in advanced LLL applications will find this book an ideal guide to an exciting new field.

This book provides a self-contained introduction to Learning Language in Logic (LLL) and, at the same time, competently surveys the current state of the art of research in the area. The book has its origin in the first LLL workshop which took place in Bled, Slovenia in June 1999. Beyond revised workshop papers, a number of additional chapters were solicited from leading researchers in order to achieve complete coverage of all current aspects and to introduce the new area to a broader audience. As the first book devoted to LLL, this thoroughly cross-reviewed state-of-the-art survey will become a valuable source of reference for researchers active in the area. Newcomers or professionals interested in advanced LLL applications will find this book an ideal guide to an exciting new field Learning Language in Logic (LLL) is an emerging research area lying at the intersection of computational logic, machine learning and natural language processing (Fig 1).