Ravi Shekhar

I am a Post-Doctoral fellow in the Computational Linguistics Lab at the Queen Mary University of London working with Matthew Purver. I am working on the EMBEDDIA project.

In 2019, I obtained a Ph.D. at DISI, the University of Trento. I was supervised by Raffaella Bernardi, University of Trento and co-supervised by Raquel Fernández, University of Amsterdam. I was also associated with CLIC Lab, CiMeC. During my Ph.D., I had an amazing collaboration with Dialogue Modelling Group, University of Amsterdam. I also collaborated with Barbara Plank, IT University of Copenhagen, Aurelie Herbelot, University of Trento and the MHUG group, University of Trento.

Prior to my Ph.D., I spent one year as a research assistant at the University of Malaya under C. S. Chan. I received my M.S. (by Research) Degree with a focus on Computer Vision from CVIT, IIIT Hyderabad under the supervision of C. V. Jawahar. Before that, I worked as a Software Engineer for Accenture Services Pvt. Limited.

Email  /  CV  /  Google Scholar  /  LinkedIn

Research

My research lies at the intersection of machine learning, computer vision, and natural language processing with an emphasis on learning Deep Neural Networks form the multi-modal data.
I am always looking for collaborations, including mentoring of Ph.D. and Master thesis.

News

[Sep, 2019] One paper accepted at CLiC-it 2019.

[July, 2019] One paper accepted at SemDial 2019.

[Jun, 2019] Joined Matthew Purver as Post-doc researcher

[May, 2019] Ph.D. Done !!!

[Mar, 2019] One paper accepted at IWCS 2019.

[Feb, 2019] One paper accepted at NAACL 2019.

[May, 2018] One paper accepted at COLING 2018.

[April, 2017 ] The FOIL paper accepted at ACL 2017.

Publications and Preprints
Image

Jointly learning to see, ask, decide when to stop, and then GuessWhat
Ravi Shekhar, A. Testoni, R. Fernández and R. Bernardi
23rd Italian Conference on Computational Linguistics (CLiC-it), 2019  
Paper / Slide / Project


Image

The Devil is in the Detail: A Magnifying Glass for the GuessWhich Visual Dialogue Game
A. Testoni, Ravi Shekhar, R. Fernández and R. Bernardi
23rd Workshop on the Semantics and Pragmatics of Dialogue (SemDial), 2019  
Paper / Slide / Project


Image

Evaluating the Representational Hub of Language and Vision Models
Ravi Shekhar, E. Takmaz, R. Fernández and R. Bernardi
13th International Conference on Computational Semantics (IWCS), 2019   (Long-Oral)
Paper / Slide / Project


Image

Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat
Ravi Shekhar*, A. Venkatesh*, T. Baumgärtner, E. Bruni, B. Plank, R. Bernardi, and R. Fernández
[* : Equal Contribution]
17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), 2019   (Long-Oral)
Paper / Slide / Project


Image

Ask No More: Deciding when to guess in referential visual dialogue
Ravi Shekhar, T. Baumgärtner, A. Venkatesh, E. Bruni, R. Bernardi, and R. Fernández
27th International Conference on Computational Linguistics (COLING), 2018   (Oral)
Paper / Slide / Project


Image

Vision and Language Integration: Moving beyond Objects
Ravi Shekhar, S. Pezzelle, A. Herbelot, M. Nabi, E. Sangineto and R. Bernardi
12th International Conference on Computational Semantics (IWCS), 2017  
Paper / Slide / Project


Image

FOIL it! Find One mismatch between Image and Language caption
Ravi Shekhar, S. Pezzelle, Y. Klimovich, A. Herbelot, M. Nabi, E. Sangineto and R. Bernardi
55th Association for Computational Linguistics (ACL), 2017   (Long-Oral)
Paper / Slide / Project


Image

Building a bagpipe with a bag and a pipe: Exploring conceptual combination in Vision
S. Pezzelle, Ravi Shekhar, and R. Bernardi
5th Workshop on Vision and Language @ACL, 2016  
Paper / Slide / Dataset


Image

Document Specific Sparse Coding for Word Retrieval
Ravi Shekhar, and C. V. Jawahar
12th International Conf. on Document Analysis and Recognition (ICDAR), 2013  
Paper / Project /


Image

Content Level Access to Digital Library of India Pages
P. Krishnan*, Ravi Shekhar*, and C. V. Jawahar [* : Equal Contribution]
8th Indian Conf. on Vision, Graphics and Image Processing (ICVGIP), 2012  
Paper / Project /


Image

Word Image Retrieval Using Bag of Visual Words
Ravi Shekhar, and C. V. Jawahar
10th IAPR International Workshop on Document Analysis Systems (DAS), 2012  
Paper / Project /


Miscellaneous
Image

Learning to see from experience: But which experience is more propaedeutic?
Ravi Shekhar, E. Takmaz, N. Kondylidis, C. Greco, A. Venkatesh, R. Bernardi, and R. Fernández
Workshop on Shortcomings in Vision and Language (SiVL) @ECCV, 2018  
Paper / Slide / Project


Image

Vision and Language Integration: Objects and beyond
Ravi Shekhar, S. Pezzelle, A. Herbelot, M. Nabi, E. Sangineto and R. Bernardi
2nd Workshop on Closing the Loop Between Vision and Language @ICCV, 2017  
Paper / Slide / Project

Thanks Jon!