Many prediction tasks in NLP involve assigning values to mutually dependent variables. For example, when designing a model to automatically perform linguistic analysis of a sentence or a document (e.g., parsing, semantic role labeling, or discourse analysis), it is crucial to model the correlations between labels. Many other NLP tasks, such as machine translation, textual entailment, and information extraction, can be also modeled as structured prediction problems.
In order to tackle such problems, various structured prediction approaches have been proposed, and their effectiveness has been demonstrated. Studying structured prediction is interesting from both NLP and machine learning (ML) perspectives. From the NLP perspective, syntax and semantics of natural language are clearly structured and advances in this area will enable researchers to understand the linguistic structure of data. From the ML perspective, the large amount of available text data and complex linguistic structures bring challenges to the learning community. Designing expressive yet tractable models and studying efficient learning and inference algorithms become important issues.
Recently, there has been significant interest in non-standard structured prediction approaches that take advantage of non-linearity, latent components, and/or approximate inference in both the NLP and ML communities. Researchers have also been discussing the intersection between deep learning and structured prediction through the DeepStructure reading group. This workshop intends to bring together NLP and ML researchers working on diverse aspects of structured prediction and expose the participants to recent progress in this area. Topics of interest include, but are not limited to, the following:
- Efficient learning and inference algorithms.
- Joint inference and learning approaches.
- Learning to search for NLP.
- Latent variable models.
- Integer linear programming and other modeling techniques.
- Structured training for non-linear models.
- Deep learning and neural network approaches for structured prediction.
- Structured prediction software.
- Structured prediction applications in NLP.
- Approximate inference for structured prediction.
We invite the following two types of papers:
- Paper describing original, solid, and scientific research work related to structured learning in NLP.
- Tutorial paper on structure prediction methods and/or applications.
All submissions must follow EMNLP 2016 formatting requirements, and they must be in PDF. Papers should be less than 8 pages in length. References do not count against this limit. The page limit serves as a guideline and will not be strictly enforced. We will also accept short papers. The official style files are available at EMNLP16 Instructions for Submission
Reviewing will be double-blind, and thus no author information should be included in the papers; self-reference should be avoided as well.
Submission is electronic and is managed by the START conference management system at https://www.softconf.com/emnlp2016/SPNLP/
Each submission will be reviewed by at least 2 program committee members.
- Aug 27: (DEADLINE EXTENDED) submission deadline
- Sep 12: acceptance notification
- Sep 26: camera ready
- Nov 05: Workshop at EMNLP 2016
Time is in GMT-12. Deadline is 11:59pm of the date indicated.