Conference Papers2009
Poveda, J. and Surdeanu, M. and Turmo, J. An Analysis of Bootstrapping for the Recognition
of Temporal Expressions. In Proc. of the NAACL-HLT 2009 Workshop on Semi-supervised Learning
for Natural Language Processing, pp. 49—57.
Boulder, Colorado (USA), June 2009. Association for Computational Linguistics (ACL).
[pdf]
[slides] 2007Poveda, J. and Surdeanu, M. and Turmo, J. A Comparison of Statistical and Rule-Induction Learners for Automatic Tagging of Time Expressions in English. In Proc. of the 14th International Symposium on Temporal Representation and Reasoning (TIME 2007), pp. 141—149. Alicante (Spain), June 2007. IEEE Computer Society. [pdf] [slides] 2006
Poveda, J. and Vellido, A. Neural Network Models for Language Acquisition: A
Brief Survey. In Proc. of the 7th International Conference on Intelligent
Data Engineering and Automated Learning (IDEAL 2006). LNCS Vol. 4224, pp. 1346—1357.
Burgos (Spain), September 2006. Springer.
[pdf]
[slides] Technical Reports2007
Poveda, J. and Surdeanu, M. and Turmo, J. A Bootstrapping Architecture for
Time Expression Recognition in Unlabelled Corpora via Syntactic-Semantic
Patterns. Technical Report LSI-07-25-R (LSI Dept., UPC). June 2007.
[pdf] 2006Poveda, J. and Surdeanu, M. SVMs for the Temporal Expression Chunking Problem. Technical Report LSI-06-37-R (LSI Dept., UPC). December 2006. [pdf] [Top]Seminar talks2008
Seminar talk for the NLP group @ University of Sheffield, 14th October 2008: Thesis-related stuff2008Poveda, J. A Combination of Machine Learning Methods for the Recognition of Temporal Expressions. Thesis Project (Thesis Proposal). January 2008. [pdf] [Top]Other (pre-Ph.D. work)Master's Dissertation (Automatic Video Summarisation)
My dissertation paper for the degree of MSc in Multimedia Computing at Brunel University of West London.
It is in the topic of Video Summarization, in particular, a combination of navigation records from users
and a genetic algorithm is utilised to automatically build a skim (i.e. summary in the form of a succession of
video segments) from a video. The navigational information is used as a supervised measure of relevance for the
different video segments, while the genetic algorithm optimizes a function that integrates this relevance alongside
other desirable criteria for a video summary. Degree Project (Cryptography Service for Mobile Agents)
The written report of my end-of-degree project for my Computer Engineering degree (Bachelor's), in Catalan.
It describes the design and implementation of a cryptography service for a mobile agents platform in the JAVA
programming language. Relevant keywords are: encryption and decryption algorithms, digital signatures and
digital envelopes. |

