This paper presents a vector representation and a clustering of action concepts based on lexical features extracted from IMAGACT, a multilingual and multimodal ontology of actions in which concepts are represented through video prototypes. We computed vectors for 1,010 action concepts, where the dimensions correspond to verbs in 10 languages. Finally, an unsupervised clustering method has been applied on these data in order to discover action classes based on typological closeness. Those clusters are not language-specific or language-biased, and thus constitute an inter-linguistic classification of action domain.Este artículo presenta una representación vectorial y un clúster de conceptos de acción basados en características léxicas extraíd...
Action verbs are the less predictable linguistic type for bilingual dictionaries and they cause majo...
This paper presents the IMAGACT annotation infrastructure which uses both corpus-based and competenc...
Instructions written in human-language cause no perception problems for humans, but become a challen...
This paper presents a vector representation and a clustering of action concepts based on lexical fea...
Action verbs have many meanings, covering actions in different ontological types. Moreover, each lan...
IMAGACT is a corpus-based ontology of action concepts, derived from English and Italian spontaneous ...
Action verbs express important information in a sentence and they are the most frequent elements in ...
Action verbs, which are highly frequent in speech, cause disambiguation problems that are relevant t...
Action verbs express important information in a sentence and they are the most frequent elements in ...
In the last 20 years dictionaries and lexicographic resources such as WordNet have started to be enr...
1noThe paper presents IMAGACT, a freely accessible online ontology of action verbs. Based on corpora...
Action verbs are the less predictable linguistic type for bilingual dictionaries and they cause majo...
Action verbs are the less predictable linguistic type for bilingual dictionaries and they cause majo...
This paper presents the IMAGACT annotation infrastructure which uses both corpus-based and competenc...
Instructions written in human-language cause no perception problems for humans, but become a challen...
This paper presents a vector representation and a clustering of action concepts based on lexical fea...
Action verbs have many meanings, covering actions in different ontological types. Moreover, each lan...
IMAGACT is a corpus-based ontology of action concepts, derived from English and Italian spontaneous ...
Action verbs express important information in a sentence and they are the most frequent elements in ...
Action verbs, which are highly frequent in speech, cause disambiguation problems that are relevant t...
Action verbs express important information in a sentence and they are the most frequent elements in ...
In the last 20 years dictionaries and lexicographic resources such as WordNet have started to be enr...
1noThe paper presents IMAGACT, a freely accessible online ontology of action verbs. Based on corpora...
Action verbs are the less predictable linguistic type for bilingual dictionaries and they cause majo...
Action verbs are the less predictable linguistic type for bilingual dictionaries and they cause majo...
This paper presents the IMAGACT annotation infrastructure which uses both corpus-based and competenc...
Instructions written in human-language cause no perception problems for humans, but become a challen...