منابع از درگیری collocational

Collocational Grammar

ryone is fighting a fierce rearguard action struggling towards the objective of a discrete syntactic classes, all the while being forced by practical necessity to move closer and closer toward an analysis of relationships whenever they want to get anything done. Everyone is still trying to find relationships of classes rather than classes of relationships. In n-gram models relationships are use...

TANGO: Bilingual Collocational Concordancer

In this paper, we describe TANGO as a collocational concordancer for looking up collocations. The system was designed to answer user’s query of bilingual collocational usage for nouns, verbs and adjectives. We first obtained collocations from the large monolingual British National Corpus (BNC). Subsequently, we identified collocation instances and translation counterparts in the bilingual corpu...

Psycho-collocational expressives in Burmese

Building a Collocational Semantic Lexicon

Natural Language Generation (NLG) systems require access to collocational information to help determine lexical choices constrained both by syntactic and semantic concerns. Constructing linguistic resources to support these decisions can be time-consuming whereas, if the information is extracted automatically, data sparsity limits the variety of the output. This paper reports on a method for ex...

Updating LSP dictionaries with collocational information

Despite the big amount of general language dictionaries in electronic form, those coming from specialised areas are still “under construction”. There are two main reasons for this: firstly, the need for these dictionaries was/is less essential than the need for general language dictionaries, since these were/are aiming mainly to specialists, and secondly many specialised areas are changing over...

Mapping Collocational Properties into Machine Learning Features

This paper investigates interactions between collocational properties and methods for organizing them into features for machine learning. In experiments performing an event categorization task, Wiebe et al. (1997a) found that different organizations are best for different properties. This paper presents a statistical analysis of the results across different machine learning algorithms. In the e...