Natural Language Processing

Opinion mining and sentiment analysis, machine translation, named entity recognition and classification, dialog systems, classifiers

Natural Language Processing (NLP) is a field that combines Computer Science technologies (such as Artificial Intelligence, Machine Learning, and Statistical inference) with Applied Linguistics in order to allow computer-supported understanding and processing of information expressed in human language for specific tasks, including machine translation, interactive dialog systems, opinion mining, etc. Vicomtech-IK4 understands that this important technology is a key factor for comprehensive interaction and understanding in a multimedia environment, as many forms of multimedia content and applications are closely related to language.

Vicomtech-IK4’s dedicated research into NLP covers mainly the following fields:

  • Opinion Mining and Sentiment Analysis is an important part of NLP that deals with the computational analysis of texts produced by human beings, with the goal being to extract and process measurable levels of related opinions and sentiments.
  • Machine Translation (MT) deals with the computer-supported translation of texts from one human language to another. There are myriad MT approaches and techniques, depending on the translation’s context and its focus (e.g., statistical, rule-based and hybrid)
  • Named Entity Recognition and Classification (NERC) is a relevant subfield of Information Extraction that deals with the location, identification and classification of individual, atomic elements called “named entities” in texts, such as proper nouns, expressions related to dates, percentages, numbers, etc.
  • Dialog Systems help people interact with a computer system (e.g., operate a computer application) using written (and even spoken) dialogs that are similar to those between human beings on a specific subject.
  • Classifiers and other Pattern Recognition technologies allow classifying information according to predefined criteria. The information may vary in nature: visual, textual, acoustic, etc.

Gallery

Outstanding projects