(1) Flexible relation extraction from patent claims; (2) Collocations in Computer Assisted Language Learning

Gabriela Ferraro (NICTA)

NICTA SML SEMINAR

DATE: 2013-05-09
TIME: 11:15:00 - 12:15:00
LOCATION: NICTA - 7 London Circuit
CONTACT: JavaScript must be enabled to display this email address.

ABSTRACT:
Flexible relation extraction from patent claims The extraction of relations is at the core of NLP and many of its applications such as lexicon construction, question answering, text generation, etc. I'm interested in the extraction of relations between complex objects described in patent claims. With their abstract vocabulary and overly long sentences, patent claims are notoriously difficult to read and comprehend, especially for layman, but also for NLP applications. In the claims inventions are described in terms of their compositional and functional features. Thus, in order to better understand them, it is necessary to identify not only the components of the invention in question, but also how these components interact with each other. In my research, I tracked this problem via a relation extraction and generalization approach.

Collocations in Computer Assisted Language Learning The correct use of collocations is one of the most difficult tasks that the student faces when learning a second language. I have been working on the problem of automatic recognition and classification of collocations from corpora. For the time being, I have been focused on Spanish collocation production in the context of Computer Assisted Language Learning.

BIO:
Gabriela grew up in San Rafael Mendoza, Argentina. She attended at the Champagnat University and received BA in Computer Science in 2004. After finished her studies in Argentina Gabriela moved to Barcelona where she received a Master degree in Science of Language and Applied Linguistics at the University Institute for Applied Linguistics (IULA) at Universitat Pompeu Fabra (UPF). Since 2005 she was part of the TALN Research Group that nowadays forms part of the Centre for Autonomous Systems and Neuro-Robotics at UPF. During the springtime of 2011, Gabriela spent a pre-doctoral internship at the Human Language Technology Group of Fundazione Bruno Kessler in Trento, Italy. In 2012 she received a PhD under the supervision of Leo Wanner. Gabrielaas main research interest is Natural Language Processing (NLP). She works in the areas of Text Simplification, Information Extraction and Computational Lexicology. She is especially interested in applying NLP technologies to make scientific and technical information accessible to laymen. For example, by applying simplification strategies to texts which are difficult to comprehend, such as patent documents.