Federico Sangati's Homepage
Federico Sangati
Post-Doc
Institute for Language, Cognition and Computation (ILCC)
University of Edinburgh

I'm a Post-Doc at the ILCC, University of Edinburgh.
I'm currently working on Natural Language Processing, more specifically on dependency and constituency parsing.
I'm part of the Syn-Sem project together with Frank Keller, Mirella Lapata, and William Blacoe.

I was a Ph.D student at the ILLC, University of Amsterdam, supervised by Rens Bod and Willem Zuidema.


Address
School of Informatics,
Room IF-4.27
10 Crichton Street
Edinburgh EH8 9AB
Contacts
E-mail: {firstname} (dot) {lastname} (at) gmail (dot) com
Telephone: +44 (0) 131 651 3173
Mobile:    +44 (0) 777 491 3434

PUBLICATIONS:

    2013

Federico Sangati and Frank Keller. 2013. Incremental Tree Substitution Grammar for Parsing and Sentence Prediction. In Transactions of the Association for Computational Linguistics (TACL), vol 1.     PDF     bibtex

Ekaterina Abramova, Raquel Fernández, and Federico Sangati. 2013. Automatic Labeling of Phonesthemic Senses. In Proceedings of CogSci 2013, the 35th annual meeting of the Cognitive Science Society, Berlin, Germany.     PDF

    2012

Ph.D. dissertation     Decomposing and Regenerating Syntactic Trees     bibtex

    2011

Federico Sangati and Willem Zuidema. 2011. Accurate Parsing with Compact Tree-Substitution Grammars: Double-DOP. In proceedings of EMNLP.     PDF     slides     bibtex     software

Andreas van Cranenburgh, Remko Scha, and Federico Sangati. 2011. Discontinuous Data-Oriented Parsing: A mildly context-sensitive all-fragments grammar. In proceedings of SPMRL.     PDF     bibtex

    2010

Federico Sangati. 2010. A Probabilistic Generative Model for an Intermediate Constituency-Dependency Representation. In proceedings of the SRW, ACL.     PDF     poster     slides     bibtex

Daniil Umanski and Federico Sangati. 2010. How Spoken Language Corpora Can Refine Current Speech Motor Training Methodologies. In proceedings of the SRW, ACL.     PDF     bibtex

Federico Sangati, Willem Zuidema, and Rens Bod. 2010. Efficiently extract recurring tree fragments from large treebanks. In proceedings of LREC.     PDF     bibtex     poster

Maarten Versteegh, Federico Sangati, and Willem Zuidema. 2010. Simulations Of Socio-Linguistic Change: Implications for Unidirectionality. In proceedings of Evolang8.

    2009

Federico Sangati and Chiara Mazza. 2009. An English Dependency Treebank à la Tesnière. Proceedings TLT8.     PDF     slides     bibtex     software

Federico Sangati. 2009. Generative re-ranking model for dependency parsing of Italian sentences. Proceedings Evalita.     PDF     bibtex

Federico Sangati. 2009. A simple DOP model for constituency parsing of Italian sentences. Proceedings Evalita.     PDF     bibtex

Federico Sangati, Willem Zuidema, and Rens Bod. 2009. A generative re-ranking model for dependency parsing. Proceedings IWPT.     PDF     poster     slides     bibtex

Federico Sangati and Willem Zuidema. 2009. Unsupervised Methods for head assignments. Proceedings EACL.     PDF     extra notes     slides     bibtex

    2008

Federico Sangati and Willem Zuidema, Communication, Cooperation, and Coherence. 2008. Proceedings Evolang, pg. 491-492.     link     poster     applet

    2007

Federico Sangati. 2007. Towards simpler tree substitution grammars. MSc Thesis.     PDF


Software:

Double-DOP parser   Extract recurring fragments (FragmentSeeker) and use them to parse with the Double-DOP model.

TDS viewer and converter   Convert and view the Penn WSJ Treebank in Tesnière Dependency Structure.

FragmentSeeker   Kenel based tool to extract recurring fragments from large PS treebanks (last update 15.11.2010, all versions).

EvalC   Graphical tool for constituency parsing evaluation, similar to EvalB (last update 25.05.2010).

EvalD   Graphical tool for dependency parsing evaluation (last update 02.06.2010).

ConstTreeViewer   Constituency Structures Viewer (last update 13.05.2010).

DepTreeViewer   Dependency Structures Viewer (last update 17.02.2010).

CCGTreeViewer   CCG Structures Viewer (last update 17.02.2010).

Parc2Heads   Enriching the Penn WSJ treebank with head annotation from the Parc700 corpus.

TigerDB2Heads   Enriching the Tiger treebank with head annotation from the Tiger DB corpus.

Applet   Simulation on Evolution of Communication Conventions

TreeGrammars   The entire source code on Tree Grammars including most of the things above (last update 12.07.2013)


Fun:

Eleusis     Eleusis Game     Test Eleusis Rules

Cellular Automata     Conway Game of Life Applet