Knowledge Bases and Multiple Modalities

About

Recently, there has been growing interest in combining knowledge bases and multiple modalities such as NLP, vision and speech. These combinations have resulted in improvements to various downstream tasks including question answering, image classification, object detection, and link prediction. The objectives of the KBMM workshop is to bring together researchers interested in (a) combining knowledge bases with other modalities to showcase more effective downstream tasks, (b) improving completion and construction of knowledge bases from multiple modalities, and in general, to share state-of-the-art approaches, best practices, and future directions.

Speakers


Xinlei Chen, Facebook Title: Learning and Reasoning with Visual Knowledge	Jared Dunnmon, Stanford Title: Cross-Modal Data Programming: Leveraging Multimodality in Weakly Supervised Machine Learning	Xiang Ren, USC Title: From Data to Model Programming: Injecting Structured Priors for Knowledge Extraction

Schedule

8:30 AM - 8:35 AM : Opening Remarks

8:35 AM - 9:15 AM : Invited talk: Xinlei Chen, Learning and Reasoning with Visual Knowledge

9:15 AM - 9:55 AM : Invited talk: Xiang Ren, From Data to Model Programming: Injecting Structured Priors for Knowledge Extraction

9:55 AM - 10:10AM : Daniel Oñoro-Rubio, MMKG: Multi-Modal Knowledge Graphs

10:10 AM - 10:30 AM : Break

10:30 AM - 11:10 AM : Invited talk: Jared Dunnmon, Cross-Modal Data Programming: Leveraging Multimodality in Weakly Supervised Machine Learning

11:10 AM - 11:25 AM : Bhushan Kotnis, Harnessing Numerical Information in Multi-Modal Knowledge Bases

11:25 AM - 11:40 AM : Kartik Talamadupula, Interactive Question Answering in Multimodal Environments Using External Knowledge

11:40 AM - 11:55 AM : Anonymous, KnowledgeNet: A Dataset for End-to-end Knowledge Graph Population

11:55 AM - 12:00 Noon : Closing Remarks

CALL FOR PAPERS

Scope

The workshop on Knowledge Bases and Multiple Modalities (KBMM) will consist of contributed posters, and invited talks on a wide variety of methods and problems in this area. We invite extended abstract submissions in the following categories to present at the workshop:

Knowledge base completion using multiple modalities

Using knowledge bases in NLP tasks

Vision and knowledge bases

Information extraction

Optimization challenges in multimodal scenarios

Benchmark datasets and evaluation methods

Call for extended abstract

We invite submission of extended abstracts related to Knowledge Bases and Multiple Modalities (KBMM). Since the workshop is not intended to have a proceedings comprising full versions of the papers, concurrent submissions to other venues, as well accepted work, are allowed provided that concurrent submissions or intention to submit to other venues is declared to all venues including KBMM. Accepted work will be presented as posters during the workshop and listed on this website.

Reviewing Policy:

Submissions shall be refereed on the basis of technical quality, potential impact, and clarity. A fraction of the submitted extended abstract shall be accepted for poster presentation at the workshop. Atleast one of the authors of each accepted submission will be required to attend the workshop to present the work.

Submission instructions

1). Prepare 1-page abstract.
2). Please upload your submission in the following Google form (only PDF accepted):
https://goo.gl/USTuYe.
3). In case of any queries, please drop an email to anand_mishra@iisc.ac.in (remove underscore).

Important dates

Abstract submission: April 17, 2019, 11:59pm PST.
Acceptance/rejection notification: April 25, 2019.
Workshop: May 22, 2019.