The ACM SIGIR International Conference on the Theory of Information Retrieval (ICTIR) provides a forum for the presentation and discussion of research related to the foundational aspects of Information Retrieval (IR), including, for example, human search processes, search and recommendation, learning and optimization, language and representations, sensory information, artificial intelligence, ethics and responsibility.
The conference explicitly welcomes papers on core IR and any paper on connections between IR and its neighboring disciplines. To accommodate this multidisciplinary focus, ICTIR 2017 is organized around five tracks:
✖Human information access
✖Natural language processing
Contributions could be (a) conceptual papers that explore key concepts, (b) more theoretical papers that model concepts and/or relations between concepts, or (c) papers that study theory in experimental or industrial settings.
We welcome experimental and industrial papers that validate approaches from the lens of practical applicability. Such papers should, apart from validating the practical applicability of an existing approach, provide a clear message to the community as to which aspects need further (theoretical) investigation, based on the experimental findings.
The topic areas covered by ICTIR include any topic of relevance to core IR and connections between IR and its neighboring disciplines. Examples are:
✖ Information Retrieval track
Queries and query analysis, retrieval models and ranking, search engine architectures and scalability, filtering and recommendation, evaluation, Web and social media search, IR and structured data, search applied to the Internet of Things, IR for social good, ethics and responsibility, other areas of IR including digital libraries, enterprise search, genomics IR, legal IR, patent search, text reuse, new retrieval problems.
✖ Human Information Access track
Understanding humans, interaction techniques, modeling and simulation of information interaction, information seeking, interactive search and recommendation, including task-based and exploratory search, personalized search, social and collaborative search, search interfaces, whole session support, and other new problems and applications of human-centered work.
✖ Machine Learning track
Statistical learning algorithms, online learning, bandit algorithms, kernel methods, graphical models, Gaussian processes, Bayesian methods, neural networks, deep learning, dimensionality reduction and manifold learning, hyper-parameter and model selection, structured learning, Markov decision processes, reinforcement learning, dynamical systems, recurrent networks.
✖ Natural Language Processing track
Text representation, document structure, linguistic analysis, cross- and multi-lingual IR, information extraction, sentiment analysis, clustering, classification, topic models, facets, text streams, generation, semantics, dialog systems.
✖ Perception track
Image search, video search, speech recognition, multimedia content analysis, music and audio analysis
All submissions must describe work that is not previously published, not accepted for publication elsewhere, and not currently under review elsewhere. The same work cannot be submitted as both a long paper and a short paper.
All submissions must be in English, in PDF format, and in two-column format. Long paper submissions should not exceed 8 pages, including references and figures. Short papers should not exceed 4 pages, including references and figures. Suitable LaTeX and Word templates for ICTIR are available from the ACM website.
The algorithms, resources and methods used within a paper should be described as completely as possible. Authors may upload supplementary material, including detailed descriptions, test datasets, or code; however, this information is not part of the submission proper, and will be read only at the discretion of the reviewers.
The review process for all submissions is double-blind, and authors must take all reasonable steps to conceal their identity. Submissions will be rejected without review if they are over the specified page limit, or if they violate the formatting guidelines in other ways (such as the use of too-small fonts, including in graphs and figures), or if they are not anonymous, or if they are incomplete.
Papers must be submitted electronically via the conference submission system. Upon submission, authors have to select a track to which they want to submit their paper. Authors should carefully go through ACM’s authorship policy before submitting a paper.