Communications

1. Rafael C. Carrasco, Jan Daciuk, and Mikel L. Forcada. An implementation of deterministic tree automata minimization. CIAA2007 12th International Conference on Implementation and Application of Automata, Proceedings, to appear. [ bib | Pdf ]
2. Enrique Sánchez Villamil, Carlos González Muñoz, and Rafael C. Carrasco. Xmlibrary search: An xml search engine oriented to digital libraries. In Andreas Rauber, Stavros Christodoulakis, and A. Min Tjoa, editors, ECDL 2005, volume 3652 of Lecture Notes in Computer Science, pages 81-91. Springer, 2005.
   [ bib | Pdf ]
3. Enrique Sánchez Villamil, Mikel L. Forcada, and Rafael C. Carrasco. Unsupervised training of a finite-state sliding-window part-of-speech tagger. In José Luis Vicedo González, Patricio Martínez-Barco, Rafael Muñoz, and Maximiliano Saiz-Noeda, editors, Advances in Natural Language Processing, 4th International Conference, EsTAL 2004, Alicante, Spain, October 20-22, 2004, Proceedings, volume 3230 of Lecture Notes in Computer Science, pages 454-463. Springer, 2004.
   [ bib | Pdf ]
4. Jose L. Verdú-Mas, Jorge Calera-Rubio, and Rafael C. Carrasco. Smoothing techniques for tree-k-grammar-based natural language modeling. In Francisco J. Perales López, Aurélio C. Campilho, Nicolas Pérez de la Blanca, and Alberto Sanfeliu, editors, Pattern Recognition and Image Analysis, First Iberian Conference, IbPRIA 2003, Puerto de Andratx, Mallorca, Spain, June 4-6, 2003, Proceedings, volume 2652 of Lecture Notes in Computer Science, pages 1057-1065. Springer, 2003.
   [ bib | Pdf ]
5. Jose L. Verdú-Mas, Jorge Calera-Rubio, and Rafael C. Carrasco. Learning probabilistic context-free grammars from treebanks. In Alberto Sanfeliu and José Ruiz-Shulcloper, editors, Progress in Pattern Recognition, Speech and Image Analysis, 8th Iberoamerican Congress on Pattern Recognition, CIARP 2003, Havana, Cuba, November 26-29, 2003, Proceedings, volume 2905 of Lecture Notes in Computer Science, pages 537-544. Springer, 2003.
   [ bib ]
6. Enrique Sánchez Villamil, José Manuel Iñesta Quereda, Rafael C. Carrasco, and Günter Mühlberger. El proyecto METAe (meta-data engine project): concepto, implementación e integración en bibliotecas digitales. In Eduardo Mena and Jesús Tramullas, editors, IV Jornadas de Bibliotecas Digitales, JBIDI 2003, Alicante, Spain, pages 177-186, 2003.
   [ bib ]
7. Enrique Sánchez Villamil and Rafael C. Carrasco. Buscadores de contenidos para bibliotecas digitales: Desarrollo de una arquitectura para un buscador XML. In Eduardo Mena and Jesús Tramullas, editors, IV Jornadas de Bibliotecas Digitales, JBIDI 2003, Alicante, Spain, pages 59-68, 2003.
   [ bib ]
8. Sergio Ortiz-Rojas and Rafael C. Carrasco. Presentación sinóptica de textos bilingües mediante distancias de edición. In Eduardo Mena and Jesús Tramullas, editors, IV Jornadas de Bibliotecas Digitales, JBIDI 2003, Alicante, Spain, pages 29-37, 2003.
   [ bib ]
9. Alicia Garrido-Alenda, Mikel L. Forcada, and Rafael C. Carrasco. Incremental construction and maintenance of morphological analysers based on augmented letter transducers. In Proceedings of TMI 2002 (Theoretical and Methodological Issues in Machine Translation, Keihanna/Kyoto, Japan, March 2002, pages 53-62, 2002.
   [ bib ]
10. Jose Luis Verdú-Mas, Mikel L. Forcada, Rafael C. Carrasco, and Jorge Calera-Rubio. Tree k-grammar models for natural language modelling and parsing. In Terry Caelli, Adnan Amin, Robert P. W. Duin, Mohamed S. Kamel, and Dick de Ridder, editors, Structural, Syntactic, and Statistical Pattern Recognition, Joint IAPR International Workshops SSPR 2002 and SPR 2002, Windsor, Ontario, Canada, Proceedings, volume 2396 of Lecture Notes in Computer Science, pages 53-63. Springer, 2002.
    [ bib | Pdf ]
11. Juan Ramón Rico-Juan, Jorge Calera-Rubio, and Rafael C. Carrasco. Stochastic k-testable tree languages and applications. In Menno van Zaanen Pieter W. Adriaans, Henning Fernau, editor, Grammatical Inference: Algorithms and Applications, 6th International Colloquium: ICGI 2002, volume 2484 of Lecture Notes in Computer Science, pages 199-212, 2002.
    [ bib ]
12. Rafael C. Carrasco, Alejandro Bia, , Mikel L. Forcada, and Pedro M. Pérez-Antón. Turning DTDs into specialized tree-automata-based schemata to match a collection of marked-up documents. Technical report, Universidad de Alicante, 2002.
    [ bib | Postscript ]
13. Mikel L.Forcada and Rafael C. Carrasco. Simple stable encodings of finite-state machines in dynamic recurrent networks. In John F. Kolen and Stefan C. Kremer, editors, A field guide to dynamical recurrent network. IEEE Press, 2001.
    [ bib ]
14. Mikel Forcada and Rafael Carrasco. Finite-state computation in analog neural networks: Steps towards biologically plausible models? In David Willshaw Stefan Wermter, Jim Austin, editor, Emergent Neural Computational Architectures based on Neuroscience, volume 2036 of Lecture Notes in Computer Science, pages 487-501. Springer, March 2001.
    [ bib ]
15. Alejandro Bia and Rafael C. Carrasco. Automatic DTD simplification by examples. In ACH/ALLC 2001. The Association for Computers and the Humanities, The Association for Literary and Linguistic Computing, The 2001 Joint International Conference, pages 7-9, New York University, New York City, June 2001.
    [ bib ]
16. Alejandro Bia, Rafael C. Carrasco, and Mikel L. Forcada. Identifying a reduced DTD from marked up documents. In Proc. of the IX Spanish Symposium on Pattern Recognition and Image Analysis (SNRFAI-20001), pages 385-390, 2001.
    [ bib | Postscript ]
17. M. Pérez-Francisco, J.M. Iñesta, J. Calera, and R.C. Carrasco. Genetic algorithms for surface simplification. In Proc. of the IX Spanish Symposium on Pattern Recognition and Image Analysis (SNRFAI-20001), pages 355-360, 2001.
    [ bib | Postscript ]
18. Mikel L. Forcada and Rafael C. Carrasco. Encoding nondeterministic finite-state tree automata in sigmoid recursive neural networks. In F.J. Ferri, J.M. Iñesta, A. Amin, and P. Pudil, editors, Advances in Pattern Recognition, Proceedings Joint IAPR International Workshops SSPR 2000 and SPR 2000, (Alicante, Spain), volume 1876 of Lecture Notes in Computer Science, pages 203-210, Berlin, 2000. Springer.
    [ bib ]
19. J.R. Rico-Juan, J. Calera-Rubio, and R.C. Carrasco. Lossless compression of surfaces described as points. In F.J. Ferri, J.M. Iñesta, A. Amin, and P. Pudil, editors, Advances in Pattern Recognition, Proceedings Joint IAPR International Workshops SSPR 2000 and SPR 2000, (Alicante, Spain), volume 1876 of Lecture Notes in Computer Science, pages 457-461, Berlin, 2000. Springer.
    [ bib ]
20. J.L. Verdú-Mas, J. Calera-Rubio, and R.C. Carrasco. A comparison of pcfg models. In C. Cardie, W. Daelemans, C. Nédellec, and E. Tjong-Kim-Sang, editors, Proceedings of CoNLL-2000 and LLL-2000, Lisbon (Portugal), pages 123-125, New Brunswick, NJ (USA), September 2000. Association for Computational Linguistics.
    [ bib | Postscript ]

    In this paper, we compare three different approaches to build a probabilistic context-free grammar for natural language parsing from a tree bank corpus: 1) a model that simply extracts the rules contained in the corpus and counts the number of occurrences of each rule 2) a model that also stores information about the parent node's category and, 3) a model that estimates the probabilities according to a generalized k-gram scheme with k=3. The last one allows for a faster parsing and decreases the perplexity of test samples.

21. J.R. Rico-Juan, J. Calera-Rubio, and R.C. Carrasco. Probabilistic k-testable tree-languages. In A.L. Oliveira, editor, Proceedings of 5th International Colloquium, ICGI 2000, Lisbon (Portugal), volume 1891 of Lecture Notes in Computer Science, pages 221-228, Berlin, 2000. Springer.
    [ bib | Postscript ]

    In this paper, we present a natural generalization of k-gram models for tree stochastic languages based on the k-testable class. In this class of models, frequencies are estimated for a probabilistic regular tree grammar wich is bottom-up deterministic. One of the advantages of this approach is that the model can be updated in an incremental fashion. This method is an alternative to costly learning algorithms (as inside-outside-based methods) or algorithms that require larger samples (as many state merging/splitting methods)

22. Jorge Calera-Rubio, Rafael C. Carrasco, and Jose Oncina. Tree languages arithmetic compression. In M.I. Torres and A. Sanfeliu, editors, Pattern Recognition and Applications. Frontiers in Artificial Intelligence and Applications, volume 56, pages 51-58. IOS Press, 2000.
    [ bib ]
23. Ramón P. Ñeco, Mikel L. Forcada, Rafael C. Carrasco, and M.Ángeles Valdés-Muñoz. Encoding of sequential translators in discrete-time recurrent neural networks. In Proc. ESANN'99 (Bruges, Belgium, 21-24 April 1999), pages 375-380, April21-24 1999.
    [ bib | Postscript ]

    In recent years, there has been a lot of interest in the use of discrete-time recurrent neural nets (DTRNN) to learn finite-state tasks, and in the computational power of DTRNN, particularly in connection with finite-state computation. This paper describes a simple strategy to devise stable encodings of sequential finite-state translators (SFST) in a second-order DTRNN with units having bounded, strictly growing, continuous sigmoid activation functions. The strategy relies on bounding criteria based on a study of the conditions under which the DTRNN is actually behaving as a SFST.

24. Rafael C. Carrasco, Jose Oncina, and Mikel L. Forcada. Efficient encodings of finite automata in discrete-time recurrent neural networks. In Proceedings of ICANN'99 (Edinburgh, Scotland, September 1999), volume 2, pages 673-677, 1999.
    [ bib ]

    A number of researchers have used discrete-time recurrent neural nets (DTRNN) to learn finite-state machines (FSM) from samples of input and output strings; trained DTRNN usually shows FSM behaviour for strings up to a certaing length, but not beyond; this is usually called instability. Other authors have shown that DTRNN may actually behave as FSM for strings of any length and have devised strategies to construct such DTRNN. In these strategies, m-state deterministic FSM are encoded and the number of state units in the DTRNN is O(m). This paper shows that more efficient sigmoid DTRNN encodings exist for a subclass of deterministic finite automata (DFA), namely, when the size of an equivalent nondeterministic finite automata (NFA) is smaller, because n-state NFA may directly be encoded in DTRNN with a O(n) units.

25. Jorge Calera-Rubio, Rafael C. Carrasco, and Jose Oncina. Tree languages arithmetic compression. In M.I.Torres and A.Sanfeliu, editors, Pattern Recognition and Image Analysis. Proceedings of the VIII Simposium Nacional de Reconocimiento de Formas y Análisis de Imágenes. Bilbao, 1999, volume I, pages 405-411. Ediciones Geneve, 1999.
    [ bib | Postscript ]

    In this paper, we explore the applicability to compression tasks of the algorithms for regular language inference from stochastic samples. We compare two arithmetic encoders based upon two different kinds of formal languages: string languages and tree languages. The experiments show that tree-based methods outperform the predictive capability of string-based methods when they are applied to files containing structural information and, then, they allow for better compression rates.

26. Rafael C. Carrasco, Jose Oncina, and Jorge Calera. Stochastic inference of regular tree languages. In V. Honavar and G. Slutzki, editors, Proceedings of the Fourth International Colloquium on Grammatical Inference (ICGI98), volume 1433 of Lecture Notes in Computer Science, pages 187-198, Berlin, 1998. Springer.
    [ bib | Postscript ]

    We generalize a former algorithm for regular language identification from stochastic samples to the case of tree languages or, equivalently, string languages where structural information is available. We also describe a method to compute efficiently the relative entropy between the target grammar and the inferred one, useful for the evaluation of the inference.

27. Rafael C. Carrasco, M. L. Forcada, and Laureano Santamaría. Inferring stochastic regular grammars with recurrent neural networks. In Laurent Miclet and Colin de la Higuera, editors, Proceedings of the Third International Colloquium on Grammatical Inference (ICGI96): Learning Syntax from Sentences, volume 1147 of Lecture Notes in Artificial Intelligence, pages 274-281, Berlin, September25-27 1996. Springer.
    [ bib | Postscript ]

    Recent work has shown that the extraction of symbolic rules improves the generalization performance of recurrent neural networks trained with complete (positive and negative) samples of regular languages. This paper explores the possibility of inferring the rules of the language when the network is trained instead with stochastic, positive-only data. For this purpose, a recurrent network with two layers is used. If instead of using the network itself, an automaton is extracted from the network after training and the transition probabilities of the extracted automaton are estimated from the sample, the relative entropy with respect to the true distribution is reduced.

28. Rafael C. Carrasco and M. L. Forcada. Second-order recurrent neural networks can learn regular grammars from noisy strings. In J. Mira and F. Sandoval, editors, From Natural to Artificial Neural Computation: Proceedings of IWANN'95, volume 930 of Lecture Notes in Computer Science, pages 605-610. Springer Verlag, 1995.
    [ bib | Postscript ]

    Recent work has shown that second-order recurrent neural networks (2ORNNs) may be used to infer deterministic finite automata (DFA) when trained with positive and negative string examples. This paper shows that 2ORNN can also learn DFA from samples consisting of pairs (W, nw) where W is a noisy string of inputs vectors describing the degree of resemblance of every input to the symbols in the alphabet, and nw is the degree of acceptance of the noisy string, computed with a DFA whose behavior has been extended to deal with noisy strings.

    Keywords: noisy strings, pattern recognition, recurrent neural networks, second-order

29. Rafael C. Carrasco and Jose Oncina. Learning stochastic regular grammars by means of a state merging method. In Rafael C. Carrasco and Jose Oncina, editors, Proceedings of the Second International Colloqium on Grammatical Inference and Applications (ICGI94), volume 862 of Lecture Notes in Artificial Intelligence, pages 139-152, Berlin, September 1994. Springer Verlag.
    [ bib ]

    We propose a new algorithm which allows for the identification of any stochastic deterministic regular language as well as the determination of the probabilities of the strings in the language. Tha algorithm builds the prefix tree acceptor from the sample set and merges systematically equivalent states. Experimentally, it proves very fast and the time needed grows only linearly with the size of the sample set.

30. E. Oset, F. Cano, J.A. Gomez-Tejedor, S. Kamalov, M.J. Vicente-Vacas, R.C. Carrasco, A. Ramos, L.L. Salcedo, and H. Toki. One and two pion photoproduction and related photon absorption processes. In Frontier 96: Nuclear Physics Frontiers with Electro-Weak Probes (Osaka, Japan), 1996.
    [ bib ]
31. E. Oset, R.C. Carrasco, J.A. Gomez-Tejedor, A. Ramos, L.L. Salcedo, and M.J. Vicente-Vacas. Photonuclear reactions leading to nn, npi,pipi emission. In 2nd International Workshop on Electromagnetically Induced Two-nucleon Emission. Gent, Belgium, 17-20 May 1995, 1995.
    [ bib ]
32. M.J. Vicente-Vacas, R.C. Carrasco, and E. Oset. Inclusive (gamma,n), (gamma,nn) and (gamma,npi) reactions in nuclei. In A. Pascolini, editor, Particles and Nuclei. Proceedings of the XIII International Conference (Perugia, Italy, 28 June-2 July 1993), volume 1. World Scientific, 1994.
    [ bib ]
33. R. C. Carrasco, M. J. Vicente, and E. Oset. Inclusive (gamma,n), (gamma,n n) ... reactions in nuclei at intermediate energies. In Ts. D. Vylov, editor, Weak and Electromagnetic Interactions in Nuclei: Proceedings of 3rd International Symposium, pages 826-832. World Scientific, 1992.
    [ bib ]
34. R.C. Carrasco and E. Oset. Photon absorption and inclusive (gamma,pi). In M.J. Vicente-Vacas E. Oset and C. Garcia-Recio, editors, Pions in Nuclei, pages 544-554. World Scientific, 1992.
    [ bib ]
35. E. Oset, R. C. Carrasco, and L. L. Salcedo. Photon and pion nuclear absorption mechanisms. In E. Truhlik and R. Mach, editors, Mesons and Light Nuclei, volume 5 of Few Body Syst. Suppl., pages 159-164. Springer Verlag, 1992.
    [ bib ]
36. R. C. Carrasco, E. Oset, and L. L. Salcedo. Photonuclear reactions at intermediate energies. In M. Schumacher and G. Tamas, editors, Perspectives on Photon Interactions with Hadrons and Nuclei, number 365 in Lecture Notes in Physics, pages 207-224. Springer-Verlag, 1990. Workshop on Vector Dominance Phenomena in the Interaction of Photons with Hadrons and Nuclei, Gottingen, Germany, Feb 1990.
    [ bib ]
37. R. C. Carrasco, E. Oset, and W. Weise. Dipole sum rule enhancement in nuclei. In M. Schumacher and G. Tamas, editors, Perspectives on Photon Interactions with Hadrons and Nuclei, number 365 in Lecture Notes in Physics, pages 246-251. Springer-Verlag, 1990. Workshop on Vector Dominance Phenomena in the Interaction of Photons with Hadrons and Nuclei, Gottingen, West Germany, Feb 1990.
    [ bib ]
38. R. C. Carrasco and E. Oset. Two nucleon and three nucleon mechanisms in nuclear photon absorption. In S. Boffi, editor, International Workshop on Two Nucleon Emission Reactions, Elba (Italy), 1989.
    [ bib ]
39. R. C. Carrasco. Many body approach to electron scattering. In HUGS at CEBAF Proceedings, pages 197-204. Hampton University, 1989.
    [ bib ]