• Publications
  • Influence
Using Machine Learning to Maintain Rule-based Named-Entity Recognition and Classification Systems
TLDR
The results are very encouraging, showing that this alternative use of machine learning can assist significantly in the maintenance of rule-based systems.
Automatic Processing of Proper Names in Texts
TLDR
The problems raised by proper names in natural language processing are shown and the knowledge representation structure based on conceptual graphs is introduced, followed by the performance of the system and the further works it intends to deal with.
Using Learning-based Filters to Detect Rule-based Filtering Obsolescence
TLDR
A method which automatically detects filtering obsolescence is developed, which involves making a learning-based control filter using a set of documents which have been categorised as relevant or not relevant by the rule-based filter.
Producing NLP-based On-line Contentware
TLDR
TalLab is described, a powerful architecture for on-line contentware which fulfils the requirements of malleability, efficiency, and ease of exploitation of NLP applications.
Training Context-Sensitive Neural Networks with Few Relevant Examples for the TREC-9 Routing
TLDR
Two main improvements are proposed: • The feature selection defines target words for which vectors of local contexts are subsequently defined, which help disambiguate the target words and are defined by an analysis of both the relevant and the irrelevant documents of the training set.
Multilingual XML-Based Named Entity Recognition for E-Retail Domains
TLDR
XML is used as the common exchange format and the monolingual NERC components use a combination of rule-based and machine-learning techniques to process web pages which contain heavily structured data where text is intermingled with HTML and other code.
Spying as an Object-Oriented Programming Paradigm
TLDR
Spying, a novel way of programming with objects, based on capsule programming and reflective facilities, is introduced, which allows easy building of monitoring systems, such as tracers, debuggers.
Representation of Complex Objects: Multiple Facets with Part-Whole Hierarchies
TLDR
A working system that integrates in a homogeneous way multi-facets and part-whole hierarchies and some form of compilation to gain speed is presented.
Two-Step Feature Selection and Neural Network Classification for the TREC-8 Routing
TLDR
A methodology for the AFP corpus is developed and its application to the TREC-8 corpus, where the top 1000 documents are ranked in order of decreasing relevance.
Visualization of Diseases at Risk in the COVID-19 Literature
This paper presents a project, named VIDAR-19, able to extract automatically diseases from the CORD-19 dataset, and also diseases which might be considered as risk factors. The project relies on the
...
1
2
...