A Small System Storing Spanish Collocations
نویسندگان
چکیده
Collocations are defined as syntactically connected and semantically compatible pairs of content components, like Spanish prestar atención ‘give attention’, presidente del país ‘president of the country’, país grande ‘large country’ or muy bien ‘very well’. The collocation databases are important for numerous applications of computational linguistics. A small system storing Spanish collocations is reported. Each collocation is accessible from both its components while querying. As compared with its Russian prototype, its size is now spare and the collocation types are limited to a few most productive ones. However, the available relation of the hyponym/hyperonym type between the systemic dictionary entries permits to infer some additional collocations at runtime. The actual statistics of the system is given.
منابع مشابه
Supervised Learning Algorithms Evaluation on Recognizing Semantic Types of Spanish Verb-Noun Collocations
The meaning of such verb-noun collocations as the wind blows, time flies, the day passes by can be generalized as ‘what is designated by the noun exists’. Likewise, the meaning of make a decision, provide support, write a letter can be generalized as ‘make what is designated by the noun’. These generalizations represent the meaning of certain groups of collocations and may be used as semantic a...
متن کاملDiscriminative Ability of WordNet Senses on the Task of Detecting Lexical Functions in Spanish Verb Noun Collocations
Collocations, or restricted lexical co-occurrence, are a difficult issue in natural language processing because their semantics cannot be derived from the semantics of their constituents. Therefore, such verb-noun combinations as “take a break,” “catch a bus,” “have lunch” can be interpreted incorrectly by automatic semantic analysis. Since collocations are combinations frequently used in texts...
متن کاملEnriching the Spanish EuroWordNet by Collocations
Collocations constitute an important type of syntagmatic information whose introduction into WordNets has not yet been addressed. The goal of our work is the integration of the collocational material for the field of emotion nouns encoded in the DIccionario de colocaciones del español (DICE) in terms of Lexical Functions into the Spanish part of the EuroWordNet (SpEWN). Two features of collocat...
متن کاملConditional Random Fields for Spanish Named Entity Recognition Using Unsupervised Features
Unsupervised features based on word representations such as word embeddings and word collocations have shown to significantly improve supervised NER for English. In this work we investigate whether such unsupervised features can also boost supervised NER in Spanish. To do so, we use word representations and collocations as additional features in a linear chain Conditional Random Field (CRF) cla...
متن کاملPapel De Los Diccionarios De Colocaciones En La Enseñanza De Español Como L2
It is generally acknowledged within the Spanish as second language (SSL) community that collocations need to be taught and that collocation dictionaries are useful. Nevertheless, no one has carried out yet any experimental study to investigate what kind of collocation information must be included into a dictionary and how to encode it for a user to take full advantage of it. We describe the res...
متن کامل