FIRE 2022

Call for Papers

FIRE 2022: 14th meeting of the Forum for Information Retrieval Evaluation

9th - 13th December 2022

Hybrid Conference

Submission Deadline: 9th September 2022 (Extended)

Website : fire.irsi.res.in 

Submission Link: https://easychair.org/conferences/?conf=fire22

The 14th meeting of the Forum for Information Retrieval Evaluation 2022 will be a hybrid conference. We are seeking the submission of high-quality and original paper. Submissions will be reviewed by experts on the basis of the originality of the work, the validity of the results, chosen methodology, writing quality and the overall contribution to the field of IR. Authors are encouraged to describe work in progress and late-breaking research results.

Topics of interest include, but are not limited to

1. Search and Ranking: Research on core algorithmic topics in IR:
   • Queries and query analysis (e.g., Query understanding, query reformulation, query representation etc.)
   • Retrieval models and ranking (e.g., Cross lingual IR, ranking algorithms, language models, retrieval algorithms, learning to rank etc)
   • Efficiency and scalability (e.g., distributed search, search engine architecture, indexing, crawling etc)
2. Domain Specific: Research on domain specific IR:
   1. Applications in Social Media (e.g., Hate speech recognition, social network in search etc.)
   2. Applications in Finance (e.g., Stock market prediction, other applications in finance)
   3. Applications in Legal (e.g., Patent discovery, verdict summarization, other applications in law)
   4. Applications in Health (e.g., Biomedical IR, medicine, genomics, other applications in health)
   5. Other applications and domains
3. Recommendation Systems: Research on Recommendation systems, content representation and content analysis:
   1. Recommendation algorithms (e.g., Content based filtering, collaborative filtering etc.)
4. Document representation and analysis (e.g., Summarization, text representation, sentiment analysis etc.)
5. Knowledge acquisition (e.g., Information extraction, event extraction etc.)
6. Multimodal and Crossmodal IR/Recsys model
   1. Visual Question Answering
   2. Image search/recommendation
   3. Multimodal document summarization
7. Bridging the gap between AI and IR:
   1. Supervised/Weakly supervised deep neural networks
   2. Word Embedding Methodologies
   3. Question answering
   4. Conversational systems
   5. Machine Translation
8. Evaluation: Research on evaluation of IR systems:
   1. User centric evaluation (e.g., User experience, user engagement etc)
   2. System centric evaluation (e.g., Evaluation metrics)
9. Explainability, Fairness and Trust of IR/Recsys models
   1. Explainable models for ranking, text classification/clustering, summarization etc.
   2. User studies for explainable AI (XAI) applied to IR/Recsys
   3. Issues related to fairness and trustworthiness of IR/Recsys models

Important dates 

Note: All submission deadlines are 11:59 PM AoE Time Zone (Anywhere on Earth).

Submission Guidelines

Submissions must describe substantial, original and unpublished work. Wherever appropriate, concrete evaluation and analysis must be included. If the paper being submitted is under review at any other venue, the same should be explicitly mentioned when making the submission. Such a paper, if accepted, should be withdrawn from all other places.

The FIRE conference track, this year, is subdivided into 4 different subtracks (described later), each with a different scope and objective, and with different reviewing policy. Please make sure that you are submitting your paper in the correct track. No requests for switching papers across tracks will be entertained after the deadline for paper submission expires. 

The submission link is available here: https://easychair.org/conferences/?conf=fire22. Please select the correct track while submitting  to avoid desk rejection.

Paper Template and Submission

The submitted papers must follow ACM SIG's template available on https://www.acm.org/publications/taps/word-template-workflow . The only accepted format of submissions is PDF. Papers which do not conform to the requirements may get rejected without review. Please note that it is the responsibility of the authors to ensure that the PDF submission has been uploaded successfully (we suggest that you try downloading your paper again yourself, to check).  Authors are invited to submit in any of the following tracks:

• Regular paper

Similar to last year, this year also we don’t make any explicit distinction between long and short papers. More time will be allocated for longer papers during the presentation. Submitted papers can be of variable length ranging from a minimum of 2 pages to a maximum of 9 pages of content (excluding references).

Reviewing policy: Double-blind. 

• Reproducibility Track

In addition to papers that describe original contributions, this year we are also encouraging researchers to submit extensions of papers describing work that was conducted as a part of their submission to a shared task either in FIRE itself (current or previous years) or other evaluation forums. In such a case, the paper submitted at this venue must be associated with a cover letter (limited to at most one page) that explicitly mentions the shared task paper (already published or to be published) and clearly explains the difference between the submitted version and the one that already exists. We encourage submissions that are associated with at least 40% new content. Without associated cover letters such papers will be rejected.

In addition to extensions of authors’ own papers, we also invite papers that seek to reproduce results from a number of other different papers (may be of different authors). Such papers don’t need the cover letter.

Reviewing policy: Single-blind.

Number of pages: Variable - min: 4, max 9 pages of content (excluding references).

• Resource and Demo paper

The papers submitted at this track should describe data or software resources towards a research problem that will be helpful to the IR/NLP/AI community. Such resources should ideally be made publicly available for reviewers to judge the merit of the resources. The demo papers should contain a link to a working software that demonstrates the application of existing research methods as a proof-of-the-concept.

Reviewing policy: Single-blind.

Number of pages: Max 4 pages of content (excluding references).

• Extended Abstract

This track invites submissions of extended abstracts of papers that have been published elsewhere (e.g., at flagship IR/NLP conferences). Ideally, the extended abstract should summarize the existing paper and contain a perspective on new ideas towards further extending that work or present a bigger picture on how that work fits in a much broader context of existing research. The submitted paper must cite the paper on which further perspective is provided.

Reviewing policy: Single-blind.

Number of pages: Max 4 pages of content (excluding references).

Double-blind Reviewing Policy

All submissions to the regular track of FIRE conference 2022 will be reviewed on the basis of originality, relevance, importance and clarity. For papers submitted to the regular track, the authors must not mention their names or institutional details anywhere in the paper. Authors should refer to themselves in third person when citing their own work. Expressions like "In our earlier work..." or "We previously showed that..." must be avoided.

Presentation Requirements

If accepted, at least one author will have to register for the conference and present their work either in-person or online. For the online mode, the authors would need to pre-record their presentation but are also required to be available during the QA session at the end of the presentation.

Overall co-ordinators

• Prasenjit Majumder (DA-IICT) 
• Mandar Mitra (ISI Kolkata) 

Conference Track Chairs

• Debasis Ganguly
• Surupendu Gangopadhyay

For queries related to conference please email us at [ clia@isical.ac.in ]
For latest updates subscribe the FIRE mailing List [ https://groups.google.com/forum/#!forum/fire-list ]