Misalignment of Semantic Relation Knowledge between WordNet and Human Intuition
WordNet provides a carefully constructed repository of semantic relations, created by specialists. But there is another source of information on semantic relations, the intuition of language users. We present the first systematic study of the degree to which these two sources are aligned. Investigating the cases of misalignment could make proper use of WordNet and facilitate its improvement. Our analysis which uses templates to elicit responses from human participants, reveals a general misalignment of semantic relation knowledge between WordNet and human intuition. Further analyses find a systematic pattern of mismatch among synonymy and taxonomic relations~(hypernymy and hyponymy), together with the fact that WordNet path length does not serve as a reliable indicator of human intuition regarding hypernymy or hyponymy relations.
Code (0)
등록된 구현이 없습니다.
Tasks
RelationSimilar Papers 제목 키워드 기반
Semantics of body parts in African WordNet: a case of Northern Sotho
This paper presents a linguistic account of the lexical semantics of body parts in African WordNet, with special reference to Northern Sotho. It focuses on external human body parts synsets in Northern Sotho. The paper s…
EoANN: Lexical Semantic Relation Classification Using an Ensemble of Artificial Neural Networks
Researchers use wordnets as a knowledge base in many natural language processing tasks and applications, such as question answering, textual entailment, discourse classification, and so forth. Lexico-semantic relations a…
General ClassificationKnowledge GraphsNatural Language InferenceQuestion Answering+3Dense Embeddings Preserving the Semantic Relationships in WordNet
In this paper, we provide a novel way to generate low dimensional vector embeddings for the noun and verb synsets in WordNet, where the hypernym-hyponym relationship is preserved in the embeddings. We call this embedding…
An overview of Portuguese WordNets
Semantic relations between words are key to building systems that aim to understand and manipulate language. For English, the “de facto” standard for representing this kind of knowledge is Princeton’s WordNet. Here, we d…
Corpus+WordNet thesaurus generation for ontology enriching
This paper presents a model to enrich an ontology with a thesaurus based on a domain corpus and WordNet. The model is applied to the data privacy domain and the initial domain resources comprise a data privacy ontology, …
Semantic Textual Similarity