Article on fst-based Abkhaz morphology


I have just drafted an article on fst-based Abkhaz morphology.
Comments are welcome.


Spring 2010 ParGram meeting (3)


we have now put up more information on the up-coming ParGram Meeting on this website:

We have pre-booked several hotel rooms. If you are planning on coming and would like to book one of these hotels, please go ahead. Just tell them you are booking under “ParGram Meeting, Miriam Butt”. If possible, also let Andrea Seeler ( know that you have booked the room (or you can even try to get her to book it for you…) so that we can keep track.

We’re working on a schedule and will have a first version of that up soon.


Spring 2010 ParGram meeting (2)


the next ParGram Meeting will be in Konstanz from March 22-26.   We will post local information on our UrduGram page shortly:

Note that our nearest airport is Zurich (Switzerland).  And various cheap airlines fly to Friedrichshafen, which is just across the lake.

In order to begin getting organized we would like to get a poll of

1) who is planning to attend?
2) what topics/talks there will be?

We have a list of proposed topics from the last ParGram meeting.  These include:

a) TNS-ASP session (Urdu, Tigrinya, Chinese)
b) Passives: statives vs. non-statives
c) Restriction — Tutorial/Discussion of Issues
d) Challenge/Taks/Corpus for Semantics (maybe first few pages of Sophie’s World?)

Please send your answers to:



LREC Parse Banking Tutorial

There will be an LFG Parse Banking tutorial at this year’s LREC in May given by Alexis Baird and Paul Meurer.

This tutorial will examine the annotation procedures used for Powerset’s LFG Parsebanking project. The tutorial will include in-depth exploration of the LFG Parsebanker developed at the University of Bergen and Uni Digital , including the process for loading data, strategies for annotating different genres of text, and extracting results.

The parsebanking tool relies on input from the LFG-based XLE parser and can support several different types of grammars. We will showcase our standard index grammar as well as our query grammar. The tutorial will include an in-depth look at how annotators select the correct parse using a series of decision points and then comment on the sentence depending on whether the correct parse was available. After demonstrating the process for loading data and annotation, we will explore more sophisticated tasks such as adding a subset of duplicate sentences to extract inter-annotator agreement metrics.

The tutorial will cover:

  1. Introduction
    • Motivation for the parsebanking tool
    • Short overview of theoretical foundations
  2. Overview of the tool
    • Loading data
    • Annotating sentences
    • Tool features
    • Generating disambiguated parses for sentences
    • Examination of potential obstacles and solutions
  3. Break
  4. Cooperative creation of a “mini corpus”
    • Participants will each work using the tool themselves
    • Depending on interest and availability of different grammars, “mini-corpus” may be multi-lingual
    • “Mini corpus” will be available as a resource after the tutorial

Spring 2010 ParGram meeting

The spring 2010 ParGram/ParSem meeting will be held at Universitaet Konstanz on March 22-26. It will be organized by Miriam Butt. Details of the agenda and the structures for comparison will be determined in late February.

LFG09 proceedings published

Tracy King announced that the LFG09 proceedings are now available on-line from CSLI publications. The past LFG proceedings as well as the HPSG proceedings are also available from this page.

Powerset internship opportunity

The Natural Language Engineering group at Powerset, a Microsoft company, is looking for candidates for a 2010 summer internship at their San Francisco office. Exact dates are flexible; all internships are 12 weeks.

The internship project will center around multiword expressions (e.g. noun-noun compounds) and ways in which to improve their analysis for search applications. The Powerset NLP technology includes finite-state morphologies, a log-linear name tagger, an LFG grammar, and a set of semantics rules. The exact nature of the project will depend on the interests and background of the intern.

Applicants must be PhD students. US citizenship is not required.

To apply for the internship, submit an application via:

Please mention natural language processing or computational linguistics in the application. (Note that the San Francisco campus does not list NLP as a research interest; do not worry about this.) By submitting your application, you will also be considered for internships at other campuses, such as Microsoft Research in Redmond, WA and Mountain View, CA.

A decision for this internship will be made in late January.

Please contact Tracy Holloway King (Tracy “dot” King “at” microsoft “dot” com) with questions about this internship.

XLFG5 announced

Dr Lionel Clément, who is Assistant Professor in Computational Linguistics at Bordeaux University, has just announced the newest version of his web-based tool for parsing with LFG grammars. The tool is accessible at

New web pages

This new website for ParGram/ParSem is being hosted by the LaMoRe group at the University of Bergen. This website has the format of a blog, with posts on the main page, and additional pages with more permanent information. Members of the ParGram/ParSem community who wish to contribute to this website can either request a login name or request specific changes. Contact Koenraad De Smedt.

Fall 2009 meeting

The ParGram meeting in the Fall of 2009 is from September 28 to October 2 in one of the Microsoft offices in San Francisco.

If you know you will be attending the meeting, or are likely to attend, please let Tracy Holloway King know.  Also contact her if you need a letter of invitation (e.g. for a visa application or to request funds from your university or company).