warning: Creating default object from empty value in /home/local/www/molto-project.eu/sites/all/modules/i18n/i18ntaxonomy/i18ntaxonomy.pages.inc on line 34.

     

Concept and Objectives

A simple dialog system for Sage in natural language

Goal

Develop a command-line tool able to take commands in natural language and have them executed by Sage (an open-source Computer Algebra System [^1])

How to use it

Building

You'll need:

  • ghc
  • curl (so that cabal install curl succeeds)
  • a way to call [Sage][] on a terminal (usually sage command.

Manual evaluation of patents (and MOLTO at MTSummit)

The MTSummit 2011 has been this week, including a workshop specialised on patent translation. MOLTO has been presented with talk at the workshop.

There have been presentations of the most important patents offices and, as expected, all of them apply manual evaluation to their translations. It seems interesting to us to use similar criteria to theirs in our evaluation.

EPO gives OK for the patent corpus

We have now received OK from the EPO to proceed in getting a better license for the patent corpus we need for carrying out our work in WP5 and WP7. This means that we can publish the results more freely than with the previous, personal license.

First patent internal milestone accomplished

We have succeeded in parsing with a small GF grammar the first example claim which reads Mouse complement-fixing monoclonal antibody which (i) reacts with essentially all normal human peripheral T-cells but (ii) does not react with any of the normal human peripheral cells in the group comprising b cells, null cells and macrophages.

Difficulties included reducing number of ambiguities from over 100 ASTs to 4, witch are all reasonable. That was done by introducing a hierarchy of Common Noun objects. The demo of the patents project will be given on May the 3rd. Everyone is invited.

MOLTO KRI in Swedish

The MOLTO KRI already has a version in Swedish - the user can write in Swedish natural language queries to the underlying knowledge base.

Clarification of GF<->Ontology interoperability

The following three tasks can be based on this interoperability:

  1. Natural Language Generation from ontology
  2. Translation of natural language queries to SPARQL
  3. Information extraction
  1. Natural Language Generation from ontology
  2. We could follow the scheme:
    • Determine small ontology subgraphs.
    • For each ontology subgraph define natural language patterns that describe it.
    • Define GF grammars that can parse all natural language patterns.

Ontologies tutorial

Semantic Technologies Highlights

This is not a complete presentation and is not intended to be understood by simply reading through without a tutor.

  • presentation pending (size limits)

Useful presentations

Recommended starting points are Fabien Gandon's presentations " ... in a nutshell "
Really easy to understand, used in Ontotext's induction program.

Syndicate content