Scaling up a NLU system from text to dialogue understanding
SETQA-NLP '09 Proceedings of the Workshop on Software Engineering, Testing, and Quality Assurance for Natural Language Processing
Answering why-questions in closed domains from a discourse model
STEP '08 Proceedings of the 2008 Conference on Semantics in Text Processing
Semantic and pragmatic computing with GETARUNS
STEP '08 Proceedings of the 2008 Conference on Semantics in Text Processing
Abstractive summarization of voice communications
LTC'09 Proceedings of the 4th conference on Human language technology: challenges for computer science and linguistics
| Hi-index | 0.00 |
The topic of this book is the theoretical foundations of a theory LSLT - Lexical Semantic Language Theory - and its implementation in a the system for text analysis and understanding. There are two main tenets of the theory which are supporting the construction of the system is that it is possible to reduce access to domain world knowledge by means of contextual reasoning, i.e. reasoning triggered independently by contextual or linguistic features of the text under analysis. In other words, it adopts what could be termed the Shallow Processing Hypothesis: access to WordNet is reduced and substituted whenever links are missing through inferences on the basis of hand-coded lexical and grammatical knowledge given to the system, which are worked out in a fully general manner.The purpose of the book is to present in detail the scientific foundations of the architecture and components of a (yet to be) implemented system for text understanding and generation, and at the same time to discuss critically some of the possible applications in real world domains in which such an approach could be fruitful.