Visual Analysis of Tag Co-occurrence on Nouns and Adjectives
نویسندگان
چکیده
In recent years, due to the wide spread of photo sharing Web sites such as Flickr and Picasa, we can put our own photos on the Web and show them to the public easily. To make the photos searched for easily, it is common to add several keywords which are called as “tags” when we upload photos. However, most of the tags are added one by one independently without much consideration of association between the tags. Then, in this paper, as a preparation for realizing simultaneous recognition of nouns and adjectives, we examine visual relationship between tags, particularly noun tags and adjective tags, by analyzing image features of a large number of tagged photos in social media sites on the Web with mutual information. As a result, it was turned out that mutual information between some nouns such as “car” and “sea” and adjectives related to color such as “red” and “blue” was relatively high, which showed that their relations were stronger.
منابع مشابه
Corpus-Based Analyses of Adjectives: Automatic Clustering
Similarity analysis is a substantial issue in both corpus-based researches and language usages. This paper focuses on the semantic usages of adjectives, and analyzes the similarities among adjectives. The adjective and the semantic tag of the head noun that it modifies in a noun phrase form a co-occurrence. A two-stage algorithm is applied to clustering the adjectives according to these co-occu...
متن کاملBeyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers
Learning visual classifiers for object recognition from weakly labeled data requires determining correspondence between image regions and semantic object classes. Most approaches use co-occurrence of “nouns” and image features over large datasets to determine the correspondence, but many correspondence ambiguities remain. We further constrain the correspondence problem by exploiting additional ...
متن کاملNouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space
We propose an approach to adjective-noun composition (AN) for corpus-based distributional semantics that, building on insights from theoretical linguistics, represents nouns as vectors and adjectives as data-induced (linear) functions (encoded as matrices) over nominal vectors. Our model significantly outperforms the rivals on the task of reconstructing AN vectors not seen in training. A small ...
متن کاملThe case of Czech possessive adjectives and their head nouns: some distributional properties
If a word class is defined on the basis of its co-occurrence with another word class in texts, then its ranking distribution may be modelled well by the negative hypergeometric probability distribution, and the interaction of the two classes can be described by the same type of model as well as with the help of some similar procedures, such as the non-linear regression. Possessive adjectives an...
متن کاملAn annotation scheme for Persian based on Autonomous Phrases Theory and Universal Dependencies
A treebank is a corpus with linguistic annotations above the level of the parts of speech. During the first half of the present decade, three treebanks have been developed for Persian either originally or subsequently based on dependency grammar: Persian Treebank (PerTreeBank), Persian Syntactic Dependency Treebank, and Uppsala Persian Dependency Treebank (UPDT). The syntactic analysis of a sen...
متن کامل