Linguistic Knowledge Acquisition and Representation:
Bootstrapping Annotated Language Data

List of accepted papers for oral presentations

Motivation and Aims

Provision of large-scale labelled language resources, such as tagged corpora or repositories of pre-classified text documents, is a crucial key to steady progress in an extremely wide spectrum of research, technological and business areas in the HLT sector. The continuously changing demands for language-specific and application-dependent annotated data (e.g. at the syntactic or at the semantic level), indispensable for design validation and efficient software prototyping, however, are daily confronted by the labelled-data bottleneck. Hand-crafted resources are often too costly and time-consuming to be produced at a sustainable pace, and, in some cases, they even exceed the limits of human conscious awareness and descriptive capability.

Possible ways to circumvent, or at least minimise, this problem come from the literature on automatic knowledge acquisition and, more generally, from the machine-learning community. Annotated data are bootstrapped by training a machine-learning classifier with a small sample of pre-annotated data and by using the induced classifier to annotate more data. Co-learning provides an alternative methodology, which essentially consists in iterative cooperation of two or more independent learning systems. Another promising route consists in automatically tracking down recurrent knowledge patterns in unstructured or implicit information sources (such as free texts or machine readable dictionaries) for this information to be moulded into explicit representation structures (e.g. subcategorisation frames, syntactic-semantic templates, ontology hierarchies etc.).

We believe that all these attempts at bootstrapping labelled data are not only of practical interest (for continuous updating, management and validation of dynamic resources), but also point to a bunch of germane theoretical issues. In particular, the workshop intends to focus on the issue of interaction between techniques for inducing structured knowledge from raw data and formal methods of linguistic knowledge representation. Gaining insights into this issue is an essential requirement for explaining the effective use of linguistic knowledge by cognitive agents. Although the cognitive and engineering views of the form and acquisition of linguistic knowledge need not be related, data from neuroscience and psychology are indeed relevant when evaluating different ways of representing information in artificial systems, and different models for linguistic knowledge acquisition.

We encourage in-depth analysis of underlying assumptions of the proposed bootstrapping methods and discussion of possible relevant connections with existing annotation and representation schemes. This investigation is likely to have significant repercussions on the way linguistic resources will be designed, developed and used for applications in the years to come. As the two aspects of knowledge representation and acquisition are profoundly interrelated, progress on both fronts can only be achieved, in our view of things, through a full appreciation of this deep interdependency.

Topics of Interest

Possible themes for participation are:

Important Dates

Deadline for workshop abstract submission 25th February 2002
Notification of acceptance 20th March 2002
Final version of paper for workshop proceedings 20th April 2002
Workshop 1st June 2002 (full day session)

Submissions

The organizers welcome contributions describing existing research related to the topics of the workshop. Each presentation will be 25 minutes long (20 minutes for presentation and 5 minutes for questions and discussion). Submissions should include: title; author(s); affiliation(s); and contact author's e-mail address, postal address, telephone and fax numbers.
Abstracts (maximum 500 words, plain-text format) must be sent to: simo@ilc.pi.cnr.it

The final version of the accepted papers should not be longer than 4,000 words or 10 A4 pages. Instructions for formatting and presentation of the final version will be sent to authors upon notification of acceptance.

Organising Committee

Alessandro Lenci UniversitÓ di Pisa (Italy)
Simonetta Montemagni Istituto di Linguistica Computazionale, CNR (Italy)
Vito Pirrelli Istituto di Linguistica Computazionale, CNR (Italy)

Provisional Programme Committee

Harald Baayen (Max Planck Institute for Psycholinguistics, Nijmegen (The Netherlands)
Rens Bod University of Amsterdam (Holland)
Michael R. Brent Washington University (USA)
Nicoletta Calzolari Istituto di Linguistica Computazionale, CNR (Italy)
Jean-Pierre Chanod Xerox Research Centre Europe, Grenoble (France)
Walter Daelemans University of Antwerp (Belgium)
Dekang Lin University of Alberta, Edmonton (Canada)
Horacio Rodriguez Universidad Politecnica de Catalunya
Fabrizio Sebastiani Istituto per l'Elaborazione dell'Informazione, CNR (Italy)
Lucy Vanderwende Microsoft Research, Redmond (USA)
Franšois Yvon Ecole Nationale Superieure des Telecommunications, Paris (France)
Menno van Zaanen University of Amsterdam (The Netherlands)

Contact Person

Simonetta Montemagni
Istituto di Linguistica Computazionale (ILC) - CNR
Area della Ricerca CNR
Via Alfieri 1 (San Cataldo)
I-56010 PISA (Italy)
Email: simo@ilc.pi.cnr.it

Workshop Registration Fees

The registration fees for the workshop are:

Accepted Papers

N.

Authors

Title

 

Pablo Gamallo, Alexandre Agustini, and Gabriel P. Lopes

A Corpus-Based Approach To Learn Syntactic And Semantic Subcategorisation

 

Anja Belz

Learning Grammars For Noun Phrase Extraction By Partition Search

 

Necip Fazil Ayan, Bonnie J. Dorr

Generating A Parsing Lexicon From Lexical-Conceptual Structure

 

Lavelli, Magnini, Sebastiani

Building Thematic Lexical Resources By Bootstrapping And Machine Learning

 

Fermin Moscoso del Prado Martin, Magnus Sahlgren

An Integration Of Vector-Based Semantic Analysis And Simple Recurrent Networks For The Automatic Acquisition Of Lexical Representations From Unlabeled Corpora

 

Aoife Cahill, Mairead McCarthy, Josef van Genabith, Andy Way

Automatic Annotation Of The Penn-Treebank With LFG F-Structure Information

 

Pavel Kveton, Karel Oliva

Detection Of Errors In Part-Of-Speech Tagged Corpora By Bootstrapping Generalized Negative N-Grams

 

Laura Alonso i Alemany, Irene Castell'on Masalles, Llu'is Padr'o Cirera

X-Tractor: A Tool For Extracting Discourse Markers

 

Maite Melero

Automatic Acquisition Of Selectional Properties Of Adjectives In Ser/Estar Constructions

 

Marisa Jiménez

Using Decision Trees To Predict Human Nouns In Spanish Parsed Text

 

Rebecca Hwa, Philip Resnik, and Amy Weinberg

Breaking The Resource Bottleneck For Multilingual Parsing

 

Adam Lopez, Mike Nossal, Rebecca Hwa, Philip Resnik

Word-Level Alignment For Multilingual Resource Acquisition

 

Rayid Ghani, Rosie Jones

A Comparison Of Efficacy And Assumptions Of Bootstrapping Algorithms For Training Information Extraction Systems

 

Bernd Bohnet, Stefan Klatt, and Leo Wanner

A Bootstrapping Approach To Automatic Annotation Of Functional Information To Adjectives With An Application To German

 

Kiril Simov, Milen Kouylekov, Alexander Simov

Incremental Specialization of an HPSG-Based Annotation Scheme