R&D Manager at IPsoft.
Numeric and Symbolic NLP: A Promising Engagement
Numeric, statistical and machine learning approaches to NLP have seen great success in the past decade. Classification, search and retrieval applications have led a revolution in computer science and created tremendous business value. But what about the grand goals of deep understanding and reasoning articulated at the dawn of research into Artificial Intelligence? Are they still relevant, and how can they be addressed? What are the current limitations of numerical approaches? What are the areas where symbolic and numerical approaches can work productively together to address currently unsolved problems?
This talk will attempt to provide an orientation to current research in symbolic NLP, including knowledge representation and ontology. Some pointers to current work that combines numeric and symbolic representations will also be presented.
Speaker Bio: Adam Pease is the Cognitive R&D Manager at IPsoft, where he and his team are building a conversational agent for customer service applications. He has led research in ontology, linguistics, and formal inference, including development of the Suggested Upper Merged Ontology (SUMO), the Controlled English to Logic Translation (CELT) system, the Core Plan Representation (CPR), and the Sigma knowledge engineering environment. Sharing research under open licenses, in order to achieve the widest possible dissemination and technology transfer, has been a core element of his research program. He is the author of the book “Ontology: A Practical Guide”
Departament de Llenguatges i Sistemes Informàtics
Centre de Recerca TALP
Universitat Politècnica de Catalunya
Title: “FreeLing: All you wanted to know and were afraid to ask”
Abstract: This talk will present FreeLing, and open-source tool suite for language processing, with support for over a dozen languages. The general capabilities of FreeLing will be described, as well as some applications and projects in which it has been used.
Being a library, FreeLing is better exploited by custom user programs that access the processing modules. Thus, the internal architecture and data structures of the library, as well as several practical usage examples will be presented.
Finally, an example of how to add a new language to the Library will be demonstrated.
Presentation Slides: FreeLing-STIL-2015