Advanced search engine

We offer both:  

1- The expertise for customized search engine integration according to various search criteria and platforms, that address the following issues of:

  • interoperability
  • scalability for large volumes of data and expanded systems
  • indexing data streams arising from documents, social media networks, audio or video sources

2- The expertise for extending search engine capabilities through semantic exploration

Computer-assisted information searching has become commonplace, as anyone with search engine availability can easily access documents in response to user-supplied subjects of interest. Nevertheless, polysemy (a word capable of having multiple meanings, such as “draft” in the sense of “preliminary form of writing” or “draft” in the sense of “gust of wind”) still represents a major problem to information searching, since it often leads to irrelevant results.

Information searching can also be performed in a question-answer manner, where the user is interested in a precise answer (e.g.: In what year did Mozart die?), in contrast to a list of documents on the subject (as in a Wikipedia page on Mozart). This avenue encompasses a vast area of research that includes natural language processing (***see other section) and possibly, in addition, the use of semantic Web (***see other section) for encoding the information in a more structured fashion.

Teams

Publications

Recent news

  • CRIM Blog - Deep learning applied to graphs
    16/10/2018

    An article by Jade Guisiano, data science intern at CRIM.

    +

Upcoming event

  • ICTAC 2018
    19 October 2018 0:00
    Stellenbosch, Afrique du Sud
    CRIM will present a paper at the 15th International Colloquium on the Theoretical Aspects of Computing to take place 16-19 October 2018 in Stellenbosch, South Africa.
    +

Recent Publications

  • Towards Automatic Feature Extraction for Activity Recognition from Wearable Sensors: A Deep Learning Approach

    +
  • État des lieux des technologies web

    +