* * * * * * * * * * * * * * * * * * * * * * * *
LINGUIST List logo Eastern Michigan University Wayne State University *
* People & Organizations * Jobs * Calls & Conferences * Publications * Language Resources * Text & Computer Tools * Teaching & Learning * Mailing Lists * Search *
* *
LINGUIST List 21.2741

Mon Jun 28 2010

Confs: Computational Linguistics, Semantics/Sweden

Editor for this issue: Elyssa Winzeler <elyssalinguistlist.org>

LINGUIST is pleased to announce the launch of an exciting new feature: Easy Abstracts! Easy Abs is a free abstract submission and review facility designed to help conference organizers and reviewers accept and process abstracts online. Just go to: http://www.linguistlist.org/confcustom, and begin your conference customization process today! With Easy Abstracts, submission and review will be as easy as 1-2-3!
        1.    Marco Pennacchiotti, ACLWorkshop GEometrical Models of Natural Language Semantics

Message 1: ACLWorkshop GEometrical Models of Natural Language Semantics
Date: 28-Jun-2010
From: Marco Pennacchiotti <pennacyahoo-inc.com>
Subject: ACLWorkshop GEometrical Models of Natural Language Semantics
E-mail this message to a friend

ACLWorkshop GEometrical Models of Natural Language Semantics
Short Title: GEMS-2010

Date: 16-Jul-2010 - 16-Jul-2010
Location: Uppsala, Sweden
Contact: Marco Pennacchiotti
Contact Email: pennacyahoo-inc.com
Meeting URL: http://art.uniroma2.it/gems010/

Linguistic Field(s): Computational Linguistics; Semantics

Meeting Description:

ACL 2010 Workshop
GEMS-2010 : GEometrical Models of Natural Language Semantics

July 16, 2010
Venue A, Room II
Uppsala University, Sweden

URL: http://art.uniroma2.it/gems010/

Distributional models and semantic spaces represent a core topic in contemporary
computational linguistics for their impact on advanced tasks and on other
knowledge fields (such as social science and the humanities). Semantic spaces
based on simple contextual units have been early used in information retrieval.
Later on, more linguistically principled spaces have been introduced for
large-scale natural language learning problems, such as the acquisition of
lexical taxonomies, word sense discrimination, pattern acquisition and
conceptual clustering. More recently, specialized distributional models have
been successfully applied to solve complex NLP tasks such as question answering,
textual entailment and sentiment analysis.

The goal of GEMS-2010, is to consolidate the experience of the first GEMS
workshop, held at EACL in 2009. GEMS aims to stimulate research on semantic
spaces and distributional methods for NLP, push for an interdisciplinary view,
and amplify exchange of ideas, results and resources among often independent

In particular, the workshop aims at gathering contemporary contributions to
large scale problems in meaning representation, acquisition and use, based on
distributional and vector space models. The workshop aims also to shed new light
on the use of such techniques on complex linguistic tasks, such as linguistic
knowledge acquisition, semantic role labeling, textual entailment recognition,
question answering, document understanding/summarization and ontology learning.


Register at:


9:25 - 9:30 Welcome and Opening

Session : Geometry and Semantics

9:30 - 10:00 David Jurgens and Keith Stevens
Capturing Nonlinear Structure in Word Spaces Through Dimensionality Reduction

10:00 - 10:30 Danilo Croce and Daniele Previtali
Manifold Learning for the Semi-supervised Induction of FrameNet Predicates: An
Empirical Investigation

10:30 - 11:00 Coffee Break

11:00 - 12:10 Invited Talk:
Katrin Erk
'What is word meaning, really? (And how can distributional models help us
describe it?)'

Session : Lexical Acquisition (1)

12:10 - 12:40 Georgiana Dinu
Relatedness Curves for Acquiring Paraphrases

12:40 - 13:10 Emiliano Guevara
A Regression Model of Adjective-Noun Compositionality in Distributional Semantics

12:45 - 13:45 Lunch break

Session : Lexical Acquisition (2)

14:30 - 15:00 Daoud Clarke, Rudi Lutz and David Weir
Semantic Composition with Quotient Algebras

15:00 - 15:30 Justin Washtell
Expectation Vectors: A Semiotics Inspired Approach to Geometric Lexical-Semantic

15:30 - 16:00 Coffee break

Session :

16:00 - 16:30 Amit Goyal, Jagadeesh Jagaralamudi, Hal Daumé III and Suresh
Sketch Techniques for Scaling Distributional Similarity to the Web

16:30 - 17:00 Andreas Vlachos, Zoubin Ghahramani and Ted Briscoe
Active Learning for Constrained Dirichlet Process Mixture Models

17:00 - 17:55 Panel

17:55 - 18:00 Closing

Workshop Committee


Roberto Basili, University of Roma Tor Vergata, Italy
Marco Pennacchiotti, Yahoo! Labs, US


Enrique Alfonseca, Google Research, US
Marco Baroni, University of Trento, Italy
Paul Buitelaar, National University of Ireland, Ireland
John A. Bullinaria, University of Birmingham, UK
Carlotta Domeniconi, George Mason University, US
Katrin Erk, University of Texas, US
Stefan Evert, University of Osnabruck, Germany
Alfio Massimiliano Gliozzo, STLab - ISTC - CNR, Italy
Gregory Grefenstette, Exalead S.A., France
Alpa Jain, Yahoo Labs, US
Jussi Kalgren, Swedish Institute for Computer Science, Sweden
Alessandro Lenci, University of Pisa, Italy
Alessandro Moschitti, University of Trento, Italy
Sebastian Pado, Stuttgart University, Germany
Ted Pedersen, University of Minnesota, US
Yves Peirsman, University of Leuven, Belgium
Ana-Maria Popescu, Yahoo Labs, US
Magnus Sahlgren, Swedish institute of Computer Science, Sweden
Sabine Schulte imWalde, University of Stuttgart, Germany
Hristo Tanev, Yahoo UK, UK
Tim Van de Cruys, University of Groningen, The Netherlands
Peter D. Turney, National Research Council Canada, Canada
Yorick Wilks, University of Sheffield, UK
Fabio Massimo Zanzotto, University of Roma Tor Vergata, Italy


Roberto Basili
Department of Computer Science
University of Roma Tor Vergata, Italy

Marco Pennacchiotti
Yahoo! Inc.
Sunnyvale, US
Read more issues|LINGUIST home page|Top of issue

Page Updated: 28-Jun-2010

Supported in part by the National Science Foundation       About LINGUIST    |   Contact Us       ILIT Logo
While the LINGUIST List makes every effort to ensure the linguistic relevance of sites listed on its pages, it cannot vouch for their contents.