— Topic classification of texts is one of the most interesting challenges in Natural Language Processing (NLP). Topic classifiers commonly use a bag-of-words approach, in which the classifier uses (and is trained with) selected terms from the input texts. In this work we present techniques based on graph similarity to classify short texts by topic. In our classifier we build graphs from the inp...

The most popular approach for document representation is the bag-of-words where terms are considered as features. In order to compute the values of these features, the term frequencies are generally scaled by a collection frequency factor to take into account the relative importance of different terms. The term frequencies can be considered as raw data about the input document. In this study, a...

Spatial information in images is considered to be of great importance in the process of object recognition. Recent studies show that human’s classification accuracy might drop dramatically if the spatial information of an image is removed. The original bag-of-words (BoW) model is actually a system simulating such a classification process with incomplete information. To handle the spatial inform...

Representation learning (RL) of knowledge graphs aims to project both entities and relations into a continuous low-dimensional space. Most methods concentrate on learning representations with knowledge triples indicating relations between entities. In fact, in most knowledge graphs there are usually concise descriptions for entities, which cannot be well utilized by existing methods. In this pa...

Briefly, what approach or combination of approaches did you test in each of your submitted runs? • all runs: video decoding using ffmpeg library, sampling every 25th frame. • F_X_NO_TNO_1: standard SURF keypoint detection, bag-of-words using 4096 prototypes from videos, indexing and querying using Lemur. • F_X_NO_TNO_2: standard SURF keypoint detection, bag-of-words using 256 prototypes from qu...

For most entity disambiguation systems, the secret recipes are feature representations for mentions and entities, most of which are based on Bag-of-Words (BoW) representations. Commonly, BoW has several drawbacks: (1) It ignores the intrinsic meaning of words/entities; (2) It often results in high-dimension vector spaces and expensive computation; (3) For different applications, methods of desi...

Binary code embedding methods can effectively compensate the quantization error of bag-of-words (BoW) model and remarkably improve the image search performance. However, the existing embedding schemes commonly generate binary code by projecting local feature from original feature space into a compact binary space. The spatial relationship between the local feature and its neighbors are ignored....

Photographic images annotation is a complex problem. Indeed, the visual characteristics of objects of a class vary with the considered instance and the shooting conditions. In this paper we proposed a visual characterization of object parts, called "Visual Phrase", robust to these variations. A Visual Phrase is a set of regions of interest built according to pre-difined criteria; a topological ...

This lecture is on dimensionality reduction, which aims at ‘squashing’ down the dimensionality while still preserving some geometric properties. The motivation behind this technique is that many types of data are high-dimensional, and it will be operationally much easier to manipulate these data in a lower dimension. For instance, the bag-of-words representation of documents, which treats every...

Measuring inter-document similarity is one of the most essential steps in text document clustering. Traditional methods rely on representing text documents using the simple Bag-of-Words (BOW) model. A document is an organized structure consisting of various text segments or passages. Such single term analysis of the text treats whole document as a single semantic unit and thus, ignores other se...