CfP: Research Papers at AMTA-2012

21 May 2012

Machine Translation is one of the oldest and most challenging problems in Natural Language Processing. In the last decade, remarkable progress has been achieved through a combination of data-influenced approaches, automatic metrics, and open comparative evaluations. Applications of MT technology, such as post-editing, are becoming increasingly viable. New researchers continue to join the field, in part due to open-source toolkits such as GIZA++ and MOSES, which have lowered the bar for mounting a competitive baseline system.

AMTA-2012 solicits original research papers that will advance the field. We seek submissions across the entire spectrum of MT-related research activity. In particular, we are interested in creative new applications of MT technology, and in new ideas that will allow MT to break free of BLEU incrementalism as it approaches maturity. Submissions must be unpublished, and in English. Important dates:

* Submission deadline: Monday, May 21
* Notifications of acceptance: Monday, July 2
* Final "camera-ready" versions: Monday, August 6

Topics of interest include but are not limited to:

* Advances in various MT paradigms: data-driven, rule-based, and hybrids
* Supervised or unsupervised acquisition of linguistic structure
* MT applications and embedding: translation/localization pipelines,speech-to-speech, speech-to-text, OCR, MT for communication (chats, blogs, social networks)
* Technologies for MT deployment: confidence estimation and domain adaptation
* MT in special settings: low resources, massive resources, high volume, low computing resources (eg, PDAs)
* MT Evaluation