We invite the submission of papers on all aspects of computational approaches to natural language learning, including, but not limited to:
- Development and empirical evaluation of machine learning methods applied to any natural language or speech processing task in supervised, semi-supervised or unsupervised settings (e.g. structured prediction, graphical models, deep learning, relational learning, reinforcement learning, etc.).
- Theoretical analyses of learning-based approaches to natural language processing.
- Computational models of human language acquisition and processing, models of language evolution and change, and simulation and analysis of psycholinguistic findings.
With the recent growing interest in statistical approaches to natural language learning that go beyond linear models and convex optimization, e.g. latent variable models or deep learning approaches, including recurrent and recursive networks, we are especially interested in papers dealing with theoretical or empirical analyses and of such models and their learning algorithms. This includes analysis of non-convex learning in the context of language processing, as well as theoretical or empirical results on phenomena that can and cannot be learned well with a given approach.
We are delighted to announce two invited speakers for CoNLL 2016:
- Jürgen Schmidhuber, Institute for Artificial Intelligence (IDSIA), Lugano, Switzerland
- Fernanda Ferreira, Department of Psychology, UC Davis, CA, USA
- Paper submission: May 6, 2016, 23:59 CEST (UTC/GMT+2)
- Notification: June 10, 2016
- Conference: August 11-12, 2016 (after ACL 2016)
Submissions to CoNLL-2016 must describe original, unpublished work in 8 pages of content plus maximum 2 additional pages of references. Final versions will be given one additional page of content (up to 9 pages) so that reviewers' comments can be taken into account. Papers will be presented orally, or as posters with a five minute oral presentation (poster booster). All papers will be published in the conference proceedings. There will be no distinction in the proceedings between long papers presented orally and as posters. All accepted papers must be presented at the conference to appear in the proceedings. At least one author of each accepted paper must register for CoNLL 2016 by the early registration deadline.
Papers should be submitted using the ACL 2016 styles. Authors who are unable to use these style files or submit a PDF file electronically should contact the program co-chairs. Authors may also optionally submit a second document containing supporting information such as proofs or algorithmic details. Reviewers will have access to the supporting information and may refer to it at their discretion. Any information that is critical to understanding the paper should be included within the paper itself.
Since reviewing will be blind, the paper should not include the authors' names and affiliations, and there should be no self-references that reveal the authors' identity. Papers that do not conform to these requirements will be rejected without review. Papers that have been or will be submitted to other meetings or publications must indicate this at submission time (by emailing the program chairs), and must be withdrawn from the other venues if accepted by CoNLL 2016. We will not accept for publication or presentation papers that overlap significantly in content or results with papers that hve been or will be published elsewhere. It is acceptable to submit work that has been made available as a technical report (or similar, e.g. in arXiv) without citing it.
Help in Improving Scientific Reviews
A subset of the paper submissions and reviews in CoNLL 2016 will be included in a dataset of peer reviews for research purposes as part of the semantic scholar project at AI2. By default, submissions and reviews will not be included in the dataset, but one can opt-in to include them via the submission and reviewing forms. The dataset will be released to the public domain twelve months after the final accept/reject decisions are made. This is part of a long-term effort to improve the peer-reviewing process.
Best Paper Award
As in recent CoNLL conferences, a Best Paper Award will be given to the authors of the highest quality paper. The most important aspects in judging the quality of a paper will be: originality, innovativeness, relevance, and impact of the presented research.
The 2016 CoNLL Shared Task will be a follow-on to the 2015 Shared Task on Shallow Discourse Parsing (SDP). This 2nd edition will be multilingual. In addition to English, which will be a repeat of the 2015 Shared Task, it will also include Chinese. Registration will start in mid-January, 2016, when the training data and scorer will also be available. The evaluation window will be in late April. Shared task ! results w i ll be presented at the CoNLL conference in Berlin.
For more information and important dates of the shared task competition see http://www.cs.brandeis.edu/~clp/conll16st/