Wilker Aziz

NEWS

[28/01/12] Back to the island and to developing =P
[25/12/12] European winter in Brazilian summer =) finally a break!!!
[18/08/12] PET is now on github
[06/08/12] I'm now an intern at Xerox Research (XRCE) in Grenoble working on really cool PB-SMT stuff.
[29/06/12] We have just released our post-editing tool PET under LGPL. The tool (jar), the user manual and examples are already available, the code will be available soon.

I am a third year Ph.D. candidate at the University of Wolverhampton supervised by Dr Lucia Specia and Professor Ruslan Mitkov.

Before coming to Wolverhampton, I enrolled an 1-year internship programme at
the Xerox Research Centre Europe supervised by Marc Dymetman and Lucia Specia.
My project on OOV handling in SMT via Textual Entailment was funded by the European
consortium PASCAL2 in collaboration with the Bar-Ilan University.
For my talk on "Improving SMT by Using Textual Entailment" I was given
the first prize of the September 2009's XRCE Intern's day.
Our findings resulted in one paper and the filing of two US patents.

I first obtained my B.Sc. degree in Computer Engineering from the Engineering School of the University of São Paulo, Brazil in 2010.
During my undergraduation I was a member of the Interinstitutional Center for
Research and Development in Computational Linguistics (NILC) supervised by
Ivandré Paraboni and Thiago Pardo.

Statistical Machine Translation
Machine Learning
Textual Entailment
Semantic Role Labeling
Quality Estimation for Machine Translation

I am currently researching semantic models for SMT.
I am very interested in benefiting from the machinery from theory of computation and formal languages.
I have also been doing some work on bringing semantic knowledge to MT evaluation and paraphrasing.

Aziz, W.; Specia, L. (2013). Multilingual WSD-like Constraints for Paraphrase Extraction. To appear in CoNLL. (pdf, bibtex)

Aziz, W.; Mitkov, R.; Specia, L. (2013). Ranking Machine Translation Systems via Post-Editing. To appear in Text, Speech and Dialogue. (pdf, bibtex, data)

Koponen, M.; Aziz, W.; Ramos, L.; Specia, L. (2012). Post-editing Time as a Measure of Cognitive Effort. In the AMTA 2012 Workshop on Post-Editing Technology and Practice (WPTP 2012), pages 11-20, San Diego, USA. (pdf, bibtex, data)

Rios, M.; Aziz, W.; Specia, L. (2012). UOW: Semantically Informed Text Similarity. In The First Joint Conference on Lexical and Computational Semantics -- Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012), pages 673--678, Montreal, Canada. (pdf, bibtex)

Aziz, W.; Sousa, S. C. M.; Specia, L. (2012). Cross-lingual Sentence Compression for Subtitles. In The 16th Annual Conference of the European Association for Machine Translation, EAMT ’12, pages 103--110, Trento, Italy. (pdf, bibtex)

Aziz, W.; Specia, L. (2012). PET: a Tool for Post-editing and Assessing Machine Translation. In The 16th Annual Conference of the European Association for Machine Translation, EAMT ’12, page 99, Trento, Italy. (pdf)

Aziz, W.; Sousa, S. C. M.; Specia, L. (2012). PET: a tool for post-editing and assessing machine translation. In The Eighth International Conference on Language Resources and Evaluation, LREC ’12, Istanbul, Turkey. (pdf, bibtex, PET)

Specia, L.; Hajlaoui, N.; Hallett, C.; Aziz, W. (2011). Predicting Machine Translation Adequacy. In The Thirteenth Machine Translation Summit (MTSummit-2011), pages 513--520, Xiamen, China. (pdf, bibtex)

Aziz, W.; Rios, M.; Specia, L. (2011). Shallow Semantic Trees for SMT. In Proceedings of the Sixth Workshop on Statistical Machine Translation (WMT-2011), pages 316--322, Edinburgh, Scotland. (pdf, bibtex)

Rios, M.; Aziz, W.; Specia, L. (2011). TINE: A Metric to Assess MT Adequacy. In Proceedings of the Sixth Workshop on Statistical Machine Translation (WMT-2011), pages 116--122, Edinburgh, Scotland. (pdf, bibtex)

Aziz, W.; Rios, M.; Specia, L. (2011). Improving Chunk-based Semantic Role Labeling with Lexical Features. In Proceedings of the International Conference Recent Advances in Natural Language Processing 2011, pages 226--232, Hissar, Bulgaria. (pdf, bibtex)

Sousa, S. C. M.; Aziz, W.; Specia, L. (2011). Assessing the post-editing effort for automatic and semi-automatic translations of DVD subtitles. In Proceedings of the International Conference Recent Advances in Natural Language Processing 2011, pages 79--103, Hissar, Bulgaria. (pdf, bibtex)

Aziz, W.; Specia, L. (2011). Fully Automatic Compilation of Portuguese-English and Portuguese-Spanish Parallel Corpora. In Proceedings of the 8th Brazilian Symposium in Information and Human Language Technology (STIL-2011), Cuiaba, Brazil. (pdf, bibtex, data)

Aziz, W.; Dymetman, M.; Mirkin, S.; Specia, L.; Cancedda, N.; Dagan, I. (2010). Learning an Expert from Human Annotations in Statistical Machine Translation: the Case of Out-of-Vocabulary Words. 14th Annual Conference of the European Association for Machine Translation (EAMT-2010), pages 28--35, Saint-Raphael, France. (pdf, bibtex)

Aziz, W.; Specia, L. (2010). Combining Dictionaries and Contextual Information for Cross-Lingual Lexical Substitution. ACL SigLex Workshop Evaluation Exercises on Semantic Evaluation (SemEval-2010), pages 117--122, Uppsala, Sweden. (pdf, bibtex)

Aziz, W.; Pardo, T.; Paraboni, I. (2009). Fine-tuning in Portuguese-English SMT. 7th Brazilian Symposium in Information and Human Language Technology (STIL-2009). São Carlos, 7-11 September. (pdf, bibtex)

Aziz, W.; Pardo, T.; Paraboni, I. (2009). Statistical Phrase-based Machine Translation: Experiments with Brazilian Portuguese. XXIX CSBC VII Encontro Nacional de Inteligência Artificial (ENIA-2009). Bento Gonçalves, 20-24 July, pp. 769-778. (pdf, bibtex)

Aziz, W.; Pardo, T.; Paraboni, I. (2008). Building a Spanish-Portuguese Parallel Corpus for Statistical Machine Translation. VI Workshop on Information and Human Language Technology (TIL-2008) Vila Velha, October 27-28. XIV Brazilian Symposium on Multimedia and the Web. (pdf, bibtex)

Aziz, W.; Pardo, T.; Paraboni, I. (2008). An Experiment in Portuguese-Spanish Statistical Machine Translation. 19th Brazilian Symposium on Artificial Intelligence (SBIA-2008) Salvador, October 26-30. Springer-Verlag, LNAI 5249, pp. 248-257. (pdf, bibtex)

Aziz, W.; Pardo, T.; Paraboni, I. (2007). Construção de um córpus paralelo alinhado para a tradução automática estatística. VI Encontro de Lingüística de Córpus. USP / FFLCH, São Paulo, September. (pdf)