EXCOM: An Automatic Annotation Engine for Semantic Information

نویسندگان

  • Brahim Djioua
  • Jorge J. García Flores
  • Antoine Blais
  • Jean-Pierre Desclés
  • Gaëll Guibert
  • Agata Jackiewicz
  • Florence Le Priol
  • Leila Nait-Baha
  • Benoît Sauzay
چکیده

In this position paper we describe the actual state of the development of an integrated set of tools (called EXCOM) for automatic semantic annotation. Annotation is generally used as an operation for marking textual segments to express some morphological and syntactic information. Establishing the semantic web on a large scale implies the widespread annotation of web documents with ontologybased knowledge markup. For this purpose, tools have been developed that allow for semi-automatic annotation of web documents with ontology-based metadata. This paper describes an automatic engine for semantic annotations based on linguistic knowledge and making use of XML technologies. We are persuaded that using linguistic information (especially the semantic organization of texts) can help retrieving information faster and better in the web. The basis aim of this engine is to construct automatically semantic metadata for texts that would allow us to search and extract data from texts annotated in that.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Indexing Documents by Discourse and Semantic Contents from Automatic Annotations of Texts

The basic aim of the model proposed here is to automatically build semantic metatext structure for texts that would allow us to search and extract discourse and semantic information from texts indexed in that way. This model is built up from two engines: The first engine, called EXCOM (Djioua et al., 2006), is an XML based system for an automatic annotation of texts according to discourse and s...

متن کامل

Automatic Annotation of Localization and Identification Relations in Platform EXCOM

Semantic annotation of localization and identification relations falls under an immense project of automatic annotation of relations embodied in the platform EXCOM. While localization and identification relations have been defined by Applicative and Cognitive Grammar, they are described here from the perspective of language processing, based on contextual exploration method, with the goal to de...

متن کامل

Automatic Annotation of Discourse and Semantic Relations Supplemented by Terminology Extraction for Domain Ontology Building and Information Retrieval

In this article, we develop a framework for the building of domain ontologies and a semantic index based on two technologies: terminology extraction with LEXTER (© EDF R&D) and discourse and semantic annotation with EXCOM. We have selected two specific points of view for this study: causality and part-whole notions. In the first part of this paper, we explain the contributions of a terminology ...

متن کامل

Automatic Annotation and Information Retrieval

Textual information extraction, and particularly the extraction of information from web-based text, requires the annotation of a great number of documents very quickly, using standard categories: syntactical, grammatical (identifying tenses and aspects), lexical (the identification of " transfer " verbs, " donation " verbs, " localization " verbs …) and communicative categories (identifying rel...

متن کامل

BioExcom: Automatic Annotation and categorization of speculative sentences in biological literature by a Contextual Exploratio

Biological research papers are replete with speculative sentences. This paper presents the BioExcom software, an adaptation of EXCOM platform to biology field, which annotates automatically all speculative sentences in full texts papers by the means of the Contextual Exploration processing. This annotation process is based on a concise semantic analysis of the multiple ways of expressing specul...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2006