Aligning FrameNet and WordNet based on Semantic Neighborhoods

摘要: This paper presents an algorithm for aligning FrameNet lexical units to WordNet synsets. Both, and WordNet, are well-known as well widely-used resources by the entire research community. They help systems in comprehension of semantics texts, therefore, finding strategies link involves challenges related a better understanding human language. Such deep analysis is exploited researchers improve performance their applications. The alignment achieved exploiting particular characteristics each lexical-semantic resource, with special emphasis on explicit, formal semantic relations each. Semantic neighborhoods computed lemmas, calculates correlation scores comparing such neighborhoods. results suggest that proposed appropriate hierarchies. Furthermore, can aid increasing coverage FrameNet, building FrameNets other languages, creating system querying joint FrameNet-WordNet hierarchy.