
Examples of resources that provide semantic relations between lexical items, such as VerbNet, ConceptNet, BabelNet, Framester, among others. The initial idea of this project was to develop a pipeline that takes advantage of databases available on the Internet (lexical resources, semantic networks, ontologies, etc.) to automatically create new qualia relations. These relations were created manually–which is a time-consuming and costly process. However, this is a relatively small number if we take into account the total number of LUs in the database (more than 27000, including pt, en, es). Therefore, the use of qualia relations constitutes a “lexical ontology”, which is used in several processes, such as the disambiguation of LUs and parsing.įN-Br currently has more than 25000 qualia relations for LUs in English and Brazilian Portuguese. Each LUs is associated with a Frame Element of this Background frame. Because of its specific semantics, each relation is also associated with a background frame that improves and explains the semantics of the relation.

part_of, used_for, used_by, is_a, etc.) and is associated with one of the four qualia roles. Each relation has specific semantics (e.g. Agentive: values that determine the origin of the object, such as its creator, type of origin (natural or artificial), or its initial cause.Īt FN-Br, this idea was implemented by creating relations between Lexical Units (LUs).Telic: values related to information about the object’s function or purpose, such as the intention of an agent performing a given action or the object’s intrinsic function.Constitutive: values that express the relationship between a given object and its constituents or parts, such as material, weight, or characteristic parts.Formal: values that establish what differentiates a given object within its semantic domain it is typically the description of its basic category.Each role captures how humans understand objects and the relationships between these objects in the world, trying to provide some explanation for the linguistic behavior of lexical items. Basically, GL assumes that the meaning of words is structured on four generative factors, called qualia roles. These relations derive from the idea of qualia structure, proposed by Pustejovsky (1995) in the Generative Lexicon (GL) theory. Introduction ContextįN-Br has been implementing qualia relations in its database.

#BABELNET VS FRAMENET CODE#
The code itself is separated into several independent repositories according to its function (see below for links and more information). This is a stand-alone project, which means that it's not intended to integrate with an existing system as is. In short, the project deals with the enrichment of the existing lexical database with relations extracted from external knowledge sources. This is the main reposity for the FrameNet Brasil (FB-Br) Qualia Project at Google Summer of Code 2021. GSoC 2021 Qualia Project Qualia Relation Extraction and Annotation Tools
