Enriching Ontologies with Linguistic Content: an Evaluation Framework
نویسندگان
چکیده
In this paper, we present a framework for representing and evaluating integrations between ontological and linguistic resources, which originates and improves previous research reported in (Pazienza & Stellato, 2006b; Pazienza, Sguera, & Stellato, 2007) and articulates into two results: first, a set of coordinated RDF vocabularies providing descriptors for representing linguistic resources and their software counterparts, as well as offering metadata for describing the linguistic enrichment of ontologies, both on quantitative and qualitative grounds. The second result is a software library for evaluating the quality of automatic linguistic enrichment tools. The Linguistic Watermark suite of RDF vocabularies, in the newly presented form, provides to our framework shared vocabularies for addressing the knowledge about heterogeneous linguistic resources, for accessing and managing their content on a common basis through dedicated software components and for representing the integration of this content inside ontologies. This last part constitutes the bridge towards our novel evaluation framework, which produces quality reports based on assessed evaluation metrics taken from the Information Retrieval tradition (Van Rijsbergen, 1975) and adapted to this task. We hope that this framework could provide a stable and reusable tool for evaluating the quality of competing algorithmic solutions for linguistic enrichment of ontologies.
منابع مشابه
An Environment for Semi-automatic Annotation of Ontological Knowledge with Linguistic Content
Both the multilingual aspects which characterize the (Semantic) Web and the demand for more easy-to-share forms of knowledge representation, being equally accessible by humans and machines, push the need for a more “linguistically aware” approach to ontology development. Ontologies should thus express knowledge by associating formal content with explicative linguistic expressions, possibly in d...
متن کاملAn Open and Scalable Framework for Enriching Ontologies with Natural Language Content
Knowledge Sharing is a crucial issue in the Semantic Web: SW services expose and share knowledge content which arise from distinct languages, locales, and personal perspectives; a great effort has been spent in these years, in the form of Knowledge Representation standards and communication protocols, with the objective of acquiring semantic consensus across distributed applications. However, n...
متن کاملEnriching Videos with Light Semantics
This paper describes an ongoing prototypical framework to annotate and retrieve web videos with light semantics. The proposed framework reuses many existing vocabularies along with a video model. The knowledge is captured from three different information spaces (media content, context, document). We also describe ways to extract the semantic content descriptions from the existing usergenerated ...
متن کاملLinguistic Enrichment Of Ontologies: a methodological framework
We introduce here a framework for adding Linguistic Expressivity to conceptual knowledge, as represented in ontologies. Both the multilingual aspects which characterize the (Semantic) Web and the demand for more easy-to-share forms of knowledge representation, being equally accessible by humans and machines, push in fact the need for a linguistically motivated approach to ontology development. ...
متن کاملLinguistic Watermark 3.0: An RDF Framework and a Software Library for Bridging Language and Ontologies in the Semantic Web
In this paper, we present a framework for representing heterogeneous linguistic resources and for integrating their content with Semantic Web ontologies. This work, which extends and improves previous research conducted by these same authors, articulates into two main results: first, a set of coordinated RDF vocabularies providing descriptors for representing linguistic resources and their soft...
متن کاملذخیره 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 2008