SIGDAT, the Association for Computational Linguistics' special interest group on linguistic data and corpus-based approaches to NLP, invites submissions to EMNLP 2004. The conference will be held on July 25-26 in Barcelona, Spain, immediately following the 42nd meeting of the ACL (ACL 2004).
We are interested in papers from academia, government, and industry on all areas of traditional interest to the SIGDAT community and aligned fields, including but not limited to:
In addition to providing a general forum, the theme for this year is
"Error Analysis in Empirical NLP"
We encourage papers that apply existing or new methodology for meaningful empirical analysis of errors, independent of the application. The theme emphasizes that learning algorithms are not merely magic "black boxes". Corpus-based NLP has reached a stage of maturity where many competing models have reached comparable plateaus in performance. Merely reporting the aggregate accuracy or coverage percentages typically fails to uncover the model limitations that are fundamentally responsible for the plateaus. While reporting aggregate percentages remains essential, instructive research should also explain a model's limitations in more meaningful ways. This can be as simple as categorizing error statistics by finer-grained types of errors, to reveal specific areas of model limitations. Better yet, we seek deeper insight into the models' inherent representational biases, in the form of qualitative theoretical analyses that can be backed up by comparative quantitative measurements. We especially welcome empirically verifiable implications arising for feature engineering or model selection, whether manual or automatic.
We strongly prefer submissions to be as PS files. Any author who submits in PDF must assume the responsibility for ensuring that fonts are treated properly so that the paper will print (not just view) anywhere. (This may involve reading the manual.) DOC/RTF formats cannot be accepted.
Reviewing will be blind. No information identifying the authors should
be in the paper: this includes not only the authors' names and
affiliations, but also self-references that reveal authors' identities;
for example, "We have previously shown (Smith 1999)" should be changed to
"Smith (1999) has previously shown".
A PostScript file of the paper must be uploaded onto the system by the date of the deadline (12 midnight GMT). In addition, information about each paper must be entered on the website. This information includes:
* Paper title
* Contact author name, affiliation, and email address
* A short list of keywords (selected from a predefined list)
* Abstract (no more than 300 words)
* The conferences that the paper has also been submitted to (if any).
Submission deadline: April 28, 2004
Acceptance notification: May 26, 2004
Camera-ready copy due: June 15, 2004
Conference: July 25-26, 2004
Dekang Lin, University of
Dekai Wu, HKUST, Hong Kong University of Science & Technology (email@example.com)
Antal van den Bosch
Erik Tjong Kim Sang
Franz Josef Och
Ismael Garc¡ía Varea