Center of Scientific Research
The Research Group on Artificial Intelligence at the Pontifical Catholic University of Peru is recognized, since May 2017 as a Center for Scientific Research by the National Council on Science and Technology CONCYTEC. The Center has strong áreas in the fields of Artificial Intelligence, Machine Learning, Images Processing, Data Mining, Computer Visión, and Natural Language Processing.
Strengths
Production
Research Fields
-
Bioinformatics
It is a discipline that allows applying computer tools to the study and management of biology data. In his field interact diverse areas of knowledge such as computer science, statistics and chemistry. Major research efforts in these fields include sequence alignment, gene prediction, genome assembly, structural protein alignment, protein structure prediction, gene expression prediction, protein-protein interactions, and evolution modeling.
-
Computer Vision (2D & 3D)
Comprende el análisis y la interpretación de la información visual. La comprensión de la imagen se considera como un proceso que parte en una imagen o secuencia de imágenes (por ejemplo, proyecciones 2D de una escena estática o dinámica) y termina en una descripción interna de la escena. Los problemas de la interpretación de imágenes son el núcleo de los esfuerzos actuales para permitir hacer una máquina que tenga interacciones "inteligentes" con su entorno.
-
Natural Language Processing
Tiene como objetivo conseguir que las computadoras procesen el lenguaje humano en sus diferentes niveles, como el morfológico, sintáctico o semántico. A partir de ello, se pueden desarrollar aplicaciones de diversa complejidad, desde un corrector ortográfico hasta un traductor automático.
-
Knowledge Engineering
La ingeniería del conocimiento forma parte de la Inteligencia Artificial y su objetivo es diseñar y desarrollar de Sistemas Expertos intentando representar el conocimiento y razonamiento humanos en un determinado dominio.
Current Projects
Repeat proteins analysis, and prediction
Repeat proteins are a widespread class of non-globular proteins carrying heterogeneous functions involved in several diseases.
Hybrid Machine Translation (MT) for Peruvian indigenous languages
Automatic text translation between native languages of the Peruvian jungle and spanish
Symmetry analysis and 3D Object Restoration
Computational tools to facilitate the conservation and restoration of cultural heritage material. Symmetry as a specification of structure.
Causality detection in genomic data
Detecting causal gene interactions from temporal gene expression profiles is a key issue in genomics, since it could reduce the need of interventional assays.
Automatic Cell Detection
A Deep Learning approach for automatic immune cell detection in gastric cancer tissue
A platform for semantic annotation and visualization of web documents
Documents in the web requires special tools in order to perform efficient search, but their are spread through different domains.
Automatic diagnostic of the coffee rust disease
Image processing for the automatic diagnostic of the coffee rust disease.
Automatic evaluation of masculine fertility
Through micrographic images analysis, it was automatically analyzed sperm cell features, such as concentration, motility and morphology.
Publications
-
ChAnot: An intelligent annotation tool for indigenous and highly agglutinative languages in Peru
Mercado, R., Pereira, J., Sobrevilla-Cabezudo, M. & Oncevay-Marcos, A. (2018). In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). (In-press)
-
WordNet-Shp: Towards the building of a lexical database for a Peruvian minority language
Maguiño, D., Oncevay-Marcos, A. & Sobrevilla-Cabezudo, M. (2018). In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). (In-press)
-
Corpus building and evaluation of aspect-based opinion summaries from tweets in Spanish
Peñaloza, D., López, R., Tenorio, J., Gómez, H., D., Oncevay-Marcos, A. & Sobrevilla-Cabezudo, M. (2018). In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). (In-press)
-
Language identification with scarce data: A case study from Peru
Espichán-Linares, A. & Oncevay-Marcos, A. (2018). In Information Management and Big Data: Fourth Annual International Symposium, SIMBig 2017, Lima, Peru, September 4-6, 2017, Revised Selected Papers. Springer International Publishing. (In-press)
-
Classification of β-hairpin repeat proteins.
Roche, D.; Do Viet, P.; Bakulina, A.; HIRSH, L.; Tosatto, S. y Kajava, A. (2017). Elsevier Editorial System(tm) for Journal of Structural Biology.
-
Spell-checking based on syllabification and character-level graphs for a Peruvian agglutinative language
Alva, C. & Oncevay-Marcos, A. (2017). In Proceedings of the EMNLP 2017 Workshop on Subword and Character Level Models in NLP, SCLeM 2017. ACL Anthology.
-
Corpus creation and initial SMT experiments between Spanish and Shipibo-konibo
Galarreta, A. P., Melgar, A., & Oncevay-Marcos, A. (2017). In Proceedings of the International Conference on Recent Advances in Natural Language Processing, RANLP 2017.
-
Exploratory analysis for ontology learning of events on social media streaming in Spanish
Valeriano, E. & Oncevay-Marcos, A. (2017). In Proceedings of the IWCS 2017 Workshop on Language, Ontology, Terminology and Knowledge Structures, LOTKS 2017. ACL Anthology.
-
Ship-LemmaTagger: building an NLP toolkit for a Peruvian native language
Pereira, J., Mercado, R., Melgar, A., Sobrevilla-Cabezudo, M., & Oncevay-Marcos, A. (2017). In Text, Speech, and Dialogue: 20th International Conference, TSD 2017, Prague, Czech Republic, August 27-31, 2017, Proceedings (pp. 473-481). Springer International Publishing.
-
SenseDependency-Rank: A word sense disambiguation method based on random walks and dependency trees
Sobrevilla-Cabezudo, M., Oncevay-Marcos, A., & Melgar, A. (2017). In Computational Linguistics and Intelligent Text Processing: 18th International Conference, CICLing 2017, Budapest, Hungary, April 17-23, 2017, Proceedings. Springer International Publishing. (In-press)
-
Scalable 3d shape retrieval using local features and the signature quadratic form distance
Sipiran, I., Lokoc̆, J., Bustos, B., & Skopal, T. (2017). The Visual Computer, 33(12), 1571-1585.
-
From reassembly to object completion: A complete systems pipeline
Papaioannou, G., Schreck, T., Andreadis, A., Mavridis, P., Gregor, R., Sipiran, I., & Vardis, K. (2017). Journal on Computing and Cultural Heritage (JOCCH), 10(2), 8.
-
Automatic Lymphocyte Detection on Gastric Cancer IHC Images Using Deep Learning
E. Garcia, R. Hermoza, C. B. Castanon, L. Cano, M. Castillo and C. Castaneda, 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS), Thessaloniki, 2017, pp. 200-204.
-
Analysis of Partial Axial Symmetry on 3D Surfaces and Its Application in the Restoration of Cultural Heritage Objects.
Sipiran, I. (2017). In The IEEE International Conference on Computer Vision (ICCV) (Vol. 2).
-
3D Reconstruction of Incomplete Archaeological Objects Using a Generative Adversary Network
Hermoza, R., & Sipiran, I. (2017). arXiv preprint arXiv:1711.06363.
-
Identification of repetitive units in protein structures with ReUPred
HIRSH, L.; Piovesan, D.; Paladin, L. y Tosatto, S. (2016). Amino Acids, 48 (6), pp. 1391-1400.
-
RepeatsDB 2.0: improved annotation, classification, search and visualization of repeat protein structures
Paladin, L.; HIRSH, L.; Piovesan, D.; Andrade, M.; Kajava, A. y Tosatto, S. (2016). Nucleic Acids Research, d1 (45), pp. 308-312.
-
Guiding the Exploration of Scatter Plot Data Using Motif-based Interest Measures
Shao, L., Schleicher, T., Behrisch, M., Schreck, T., Sipiran, I., & Keim, D. A. (2016). Journal of Visual Languages & Computing, 36, 1-12.
-
Coh-Metrix-Esp: A Complexity Analysis Tool for Documents Written in Spanish
Quispersaravia, A., Perez, W., Sobrevilla, M., & Alva-Manchengo, F. (2016). In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).