• Aucun résultat trouvé

Knowledge Extraction with Saffron: A Framework and Research Program

N/A
N/A
Protected

Academic year: 2022

Partager "Knowledge Extraction with Saffron: A Framework and Research Program"

Copied!
1
0
0

Texte intégral

(1)

Knowledge Extraction with Saffron: A Framework and Research Program

Paul Buitelaar

Unit for Natural Language Processing

Insight Centre for Data Analytics, National University of Ireland, Galway IDA Business Park, Lower Dangan

Galway, Ireland

paul.buitelaar@insight-centre.org

Knowledge extraction from text is a longstanding challenge and ambition in Natural Language Processing and AI in general. Success and failure in this area depends however on definitions and use cases of ’knowledge’, which I will address in this talk. Saffron1 is a framework for knowledge extraction from text that has been developed over several years and was tested in a wide range of use cases. In the talk I will present the basic architecture and functionality of Saffron and its use in several applications. In the second part of the talk I will address some of the shortcomings of Saffron, which are the subject of our current research program.

1http://saffron.insight-centre.org/

Proceedings of the conference Terminology and Artificial Intelligence 2015 (Granada, Spain) 3

Références

Documents relatifs

In informatics and linguistics, parsing is the process that can determine the morpho-syntactic structure of a sentence; parsing associates a sentence expressed in a natural

The difficulties we encounter when we decide to develop a framework for managing I&C knowledge are double: the diversity of concepts (from level 0 to level 2 of the CIM -

Additionally, given that most of the planners accept planning problems in Planning Domain Definition Language (PDDL) [17] as their input, the inference engine looks up

In this paper, we presented a framework for build- ing a knowledge repository that: (1) applies a cus- tomisable text mining workflow to extract infor- mation in the form of

Multilingual aspect: Defining the labels in the ontology in different languages allows to visualize the graph in a multilingual form as shown in Figure 1 which describes the

Named entity recognition and automatic semantic data generation from natural language text has already been investigated and several knowledge extraction systems already exist [3]

These languages extend Datalog with features such as existential quantifiers, equalities, and the falsum in rule heads and negation in rule bodies, and, at the same time,

This phase introduces new knowledge in the text, and several dierent annotators can contribute, enriching the text with dierent kinds of knowledge, but mostly with External