resources

name {dot} surname {at} um.edu.mt

Institute of Linguistics and Language Technology, Rm 111, University of Malta
Tal-Qroqq Msida MSD2080, Malta

(+356) 2340 2150

some useful resources

From time to time I put up some stuff I've done that might be useful to others.

code

  • SimpleNLG: a java library for morphological generation and syntactic realisation. This used to be hosted on Google Code, but is now on Github.

language resources

  • The GenChal Repository: an online repository of datasets related to the Generation Challenges, a series of Shared Task challenges organised since 2007.
  • The Maltese Language Resource Server (MLRS): a server for language resources and tools in Maltese. Currently hosts a corpus of ca. 100m tokens of Maltese text. This is continuously being updated.
  • The TUNA Corpus of Referring Expressions, a semantically transparent, annotated corpus of references to objects in visual domains. This corpus has been used in three Shared Task Evaluations since its development.
  • Experiment on temporal structure in narrative: I've recently run this experiment, and have collected a large corpus of narratives that I'll make available once annotation is complete. Meantime, you can read a summary here.
  • Annotated bibliography on the generation of referring expressions (and related problems)
    A collection of publications on reference and its computational treatment in generation, compiled as part of the TUNA Project. Not up to date at all!

other nlg links

NEW BOOK! Languages of Malta: Recent Studies, edited by Patrizia Paggio and Albert Gatt. Berlin: Language Science Press 2018.

Survey of Natural Language Generation systems and techniques published in the Journal of AI Research (JAIR), volume 61: 65-170.