Semantic tuples for evaluation of image sentence generation

Autor: Ellebracht, Lily Delores, Ramisa Ayats, Arnau, Shantharam Madhyastha, Pranava Swaroop, Cordero Rama, Jose Alejandro, Moreno-Noguer, Francesc, Quattoni, Ariadna Julieta|||0000-0002-7879-7174

Publikováno v: Recercat. Dipósit de la Recerca de Catalunya
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)

The automatic generation of image captions has received considerable attention. The problem of evaluating caption generation systems, though, has not been that much explored. We propose a novel evaluation approach based on comparing the underlying vi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::24b8c5aa53889caf655cffc7708b17b6
https://hdl.handle.net/2117/84419

Unsupervised spectral learning of finite-state transducers

Autor: Bailly, Raphaël, Carreras Pérez, Xavier, Quattoni, Ariadna Julieta

Publikováno v: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
Universitat Jaume I

Finite-State Transducers (FST) are a standard tool for modeling paired inputoutput sequences and are used in numerous applications, ranging from computational biology to natural language processing. Recently Balle et al. presented a spectral algorith

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::fbe33477c34a1add9b38a5ee7b7e0ba3
http://hdl.handle.net/2117/21077

A latent variable ranking model for content-based retrieval

Autor: Quattoni, Ariadna Julieta, Carreras Pérez, Xavier, Torralba, Antonio

Publikováno v: Recercat. Dipósit de la Recerca de Catalunya
instname
Other University Web Domain
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)

34th European Conference on IR Research, ECIR 2012, Barcelona, Spain, April 1-5, 2012. Proceedings
Since their introduction, ranking SVM models [11] have become a powerful tool for training content-based retrieval systems. All we need for traini

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::9b9013354ac56b7e7bd5cf1ea29cd38d
http://hdl.handle.net/2117/15649

Low-rank regularization for high-dimensional sparse conjunctive feature spaces in information extraction

Autor: Primadhanty, Audi

Publikováno v: TDX (Tesis Doctorals en Xarxa)
TDR. Tesis Doctorales en Red
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)

One of the challenges in Natural Language Processing (NLP) is the unstructured nature of texts, in which useful information is not easily identifiable. Information Extraction (IE) aims to alleviate it by enabling automatic extraction of structured in

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::03bd802d6c4f9c454935d9cec1564edb
https://hdl.handle.net/10803/4616822117/114220