Neu-IR 2016 - The SIGIR 2016 Workshop on Neural Information Retrieval

The SIGIR 2016 Workshop on Neural Information Retrieval
July 21st, 2016
Pisa, Tuscany, Italy
URL: http://research.microsoft.com/neuir2016
For latest updates and queries, please follow: https://twitter.com/neuir2016
===
Important Dates:
---
Submission Deadline: May 16th, 2016
Acceptance Notifications: June 6th, 2016
Camera-ready Deadline: June 17th, 2016
Overview:
---
In recent years, deep neural networks have yielded significant performance improvements on speech recognition and computer vision tasks, as well as led to exciting breakthroughs in novel application areas such as automatic voice translation, image captioning, and conversational agents. Despite demonstrating good performance on natural language processing (NLP) tasks, the performance of deep neural networks on IR tasks has had relatively less scrutiny.
The lack of many positive results in the area of information retrieval is partially due to the fact that IR tasks such as ranking are fundamentally different from NLP tasks, but also because the IR and neural network communities are only beginning to focus on the application of these techniques to core information retrieval problems. Given that deep learning has made such a big impact, first on speech processing and computer vision and now, increasingly, also on computational linguistics, it seems clear that deep learning will have a major impact on information retrieval and that this is an ideal time for a workshop in this area. Our focus is on the applicability of deep neural networks to information retrieval: demonstrating performance improvements on public or private information retrieval datasets, identifying key modelling challenges and best practices, and thinking about what insights deep neural network architectures give us about information retrieval problems.
Neu-IR 2016 will be a highly interactive full day workshop that will provide a forum for academic and industrial researchers working at the intersection of IR and neural networks. The purpose is to provide an opportunity for people to present new work and early results, compare notes on neural network toolkits, share best practices, and discuss the main challenges facing this line of research.
Call for Papers:
---
We solicit submission of papers of two to six pages, representing reports of original research, preliminary research results, proposals for new work, descriptions of neural network based toolkits tailored for IR, and position papers. Papers presented at the workshop will be required to be uploaded to arXiv.org but will be considered non-archival, and may be submitted elsewhere (modified or not), although the workshop site will maintain a link to the arXiv versions. This makes the workshop a forum for the presentation and discussion of current work, without preventing the work from being published elsewhere.
We are interested in submissions relevant to the following main themes:
(1) The application of neural network models in IR tasks, including but not limited to:
* Full text document retrieval, passage retrieval, question answering
* Web search, searching social media, distributed information retrieval, entity ranking
* Learning to rank combined with neural network based representation learning
* User and task modelling, personalized search, diversity
* Query formulation assistance, query recommendation, conversational search
* Multimedia retrieval
(2) Fundamental modelling challenges faced in such applications, including but not limited to:
* Learning dense representations for long documents
* Dealing with rare queries and rare words
* Modelling text at different granularities (character, word, passage, document)
* Compositionality of vector representations
* Jointly modelling queries, documents, entities and other structured/knowledge data
(3) Best practices for research and development in the area, dealing with concerns such as:
* Finding sufficient publicly-available training data
* Baselines, test data, avoiding overfitting
* Neural network toolkits
* Real-world use cases, deployment at scale
All papers will be peer reviewed (single-blind) by the program committee and judged by their relevance to the workshop, especially to the main themes identified above, and their potential to generate discussion.
Submission Instructions:
---
Page limit: 2 to 6 pages (including references)
Submission url: https://easychair.org/conferences/?conf=neuir2016
Submission Deadline: May 16th, 2016
Acceptance Notifications: June 6th, 2016
All submissions must be formatted according to the ACM SIG proceedings template. Please note that at least one of the authors of each accepted paper must register for the workshop and present the paper in-person.
Program Committee:
---
Carsten Eickhoff, ETH Zurich
Debasis Ganguly, Dublin City University
Katja Hoffman, Microsoft Research
Hang Li, Huawei Technologies
Piotr Mirowski, Google DeepMind
Alessandro Moschitti, University of Trento
Pavel Serdyukov, Yandex
Fabrizio Silvestri, Yahoo Labs
Alessandro Sordoni, Université de Montréal
Organizing Committee:
---
Nick Craswell, Microsoft
W. Bruce Croft, University of Massachusetts, Amherst
Maarten de Rijke, University of Amsterdam
Jiafeng Guo, Chinese Academy of Sciences
Bhaskar Mitra, Microsoft