Finding concepts in natural language utterances is a challenging task, especially given the scarcity of labeled data for learning semantic ambiguity. Furthermore, data mismatch issues, which arise when the expected test (target) data does not exactly match the training data, aggravate this scarcity problem. To deal with these issues, we describe an efficient semisupervised learning (SSL) approa...

With many people freely expressing their opinions and feelings on the Web, much research has gone into modeling and monetizing opinionated, and usually unstructured and textual, Web-based content. Aspect-based sentiment analysis aims to extract the fine-grained topics, or aspects, that people are talking about, together with the sentiment expressed on those aspects. This allows for a detailed a...

We participate in the English subtask B and C at SemEval-2016 Task 3 “Community Question Answering”. This paper is concerned with the description of our participating system. We propose a ranking model that combines a translation model with the cosine similarity-based method. Compared to the traditional bag of words method, the proposed model is more effective because the relationships between ...

Given a target word wi to be disambiguated, we define a class of local contexts for wi such that the sense of wi is univocally determined. We call such local contexts sense discriminative and represent them with sense discriminative (SD) patterns of lexico-syntactic features. We describe an algorithm for the automatic acquisition of minimal SD patterns based on training data in SemCor. We have ...

Today’s giant-sized image databases require content-based techniques to handle the exploration of image content on a large scale. A special part of image content retrieval is the domain of landmark recognition in images as it constitutes a basis for a lot of interesting applications on web images, personal image collections and mobile devices. We build an automatic landmark recognition system f...

Human action recognition is an increasingly important research topic in the fields of video sensing, analysis and understanding. Caused by unconstrained sensing conditions, there exist large intra-class variations and inter-class ambiguities in realistic videos, which hinder the improvement of recognition performance for recent vision-based action recognition systems. In this paper, we propose ...

We propose a discriminative latent model for annotating images with unaligned object-level textual annotations. Instead of using the bag-of-words image representation currently popular in the computer vision community, our model explicitly captures more intricate relationships underlying visual and textual information. In particular, we model the mapping that translates image regions to annotat...

This paper explores the possibility of presenting additional contextual information as a method of answer presentation Question Answering. In particular the paper discusses the result of employing Bag of Words (BoW) and Bag of Concepts (BoC) models to retrieve contextual information from a Linked Data resource, DBpedia. DBpedia provides structured information on wide variety of entities in the ...

This paper describes the participation of ELiRF-UPV team at Classification Of Spanish Election Tweets (COSET) task. We tested several approaches based on different classifiers and features representations. Our main approach is based on neural networks, concretely, Multilayer Perceptrons (MLP) with bag-of-words representation of the tweets. Our system achieved the best score on the test set of t...

Abstract. Let Fm be a free group of a finite rank m ≥ 2 and Xi, Yj be elements in Fm. A nonempty word w(x1, . . . , xn) is called a C-test word in n letters for Fm if, whenever w(X1, . . . ,Xn) = w(Y1, . . . , Yn) 6= 1, the two n-tuples (X1, . . . , Xn) and (Y1, . . . , Yn) are conjugate in Fm. In this paper we construct, for each n ≥ 2, a C-test word vn(x1, . . . , xn) with the additional prop...