[Corpora-List] Call for Abstracts - Twenty Years of Bitext (at EMNLP 2013)

Chris Dyer cdyer at cs.cmu.edu
Thu Aug 22 02:30:05 CEST 2013

Twenty Years of Bitext (at EMNLP 2013) https://sites.google.com/site/20yearsofbitext/ Friday, October 18, 2013 Seattle, WA

1993 was a watershed year in the development of empirical methods for processing parallel corpora. Seminal publications by Gale and Church at Bell Labs (CL, 1993) and Brown and colleagues at IBM (CL, 1993) established the methodology, models, and algorithms that form the basis of modern statistical approaches to machine translation and multilingual text processing. In that year the first Workshop on Very Large Corpora (which would ultimately become EMNLP) was held, a sign of the broader sea change that transformed how problems in natural language processing are approached.

This workshop, collocated with EMNLP 2013 in Seattle, is an opportunity to look back on the 20-year history of statistical models of bitext processing and to ask where the field will be in another 20 years.

We invite 2-page (including references) extended abstracts for poster presentations on the use of bitext in NLP, including: * Representations: morphology, syntax, semantics, words, phrases; * Models: generative, discriminative, Bayesian, hybrid, neural; * Speculation: e.g., will we still be using Model 4 in 2033?; * Applications of bitext models: machine translation, syntax, semantics, object recognition, topic modeling, paraphrase, textual entailment, question answering; * Learning: latent variables, non-convex optimization, semi-supervision, spectral methods, information theoretic approaches; * Formalisms: automata, transducers, grammars; * (and of course) Data: parallel corpora and other artifacts of multilinguality.

Each submission must contain: * Author name(s), affiliation(s), and email address(es) (submissions should not be anonymized) * Title * Abstract text

To encourage inclusiveness and the presentation of speculative and recent work, abstracts will not be published in a proceedings, but simply reviewed by the conference organizers and panelists to ensure that they are on topic and reasonably coherent. Abstracts on work published or submitted elsewhere are welcome.

Abstracts, indicating authors and their affiliations, should be submitted as an attachment in PDF format to 20yearsofbitext at googlegroups.com before 11:59PM PDT on Friday, August 30, 2013.

Important Dates * Abstract deadline : Friday, August 30, 2013 * Acceptance notification : Monday, September 9, 2013 * Workshop : Friday, October 18, 2013

Organizers Chris Dyer, Carnegie Mellon University Noah A. Smith, Carnegie Mellon University Phil Blunsom, University of Oxford

More information about the Corpora mailing list