Dr Ravi Shekhar
-
Email
r.shekhar@essex.ac.uk -
Location
5B.528, Colchester Campus
-
Academic support hours
Wednesday, 11:00 - 12:00 (In person) Thursday, 16:00 - 17:00 (On Zoon)
Profile
Biography
I am a Lecturer at the University of Essex. Before that, I was a post-doctoral researcher at the Queen Mary University of London, working with Professor Matthew Purver on the EMBEDDIA and SoDeStream projects. I obtained a Ph.D. at DISI, the University of Trento. I was supervised by Dr. Raffaella Bernardi, University of Trento, and co-supervised by Prof. Raquel Fernández, University of Amsterdam. My research interests include Natural Language Processing, Cross-Lingual Representation, Language and Vision Interaction, and Social Media Analysis.
Qualifications
-
Ph.D. University of Trento, (2019)
Appointments
University of Essex
-
Lecturer in Natural Language Processing, School of Computer Science and Electronic Engineering, University of Essex (1/2023 - present)
Other academic
-
Post-Doctoral Researcher, School of Electronic Engineering and Computer Science, Queen Mary University of London (6/2019 - 1/2023)
Research and professional activities
Research interests
Multi-model NLP
Conversation AI
Social Media Analysis
Cross-Lingual Representation
Social Media Analysis
Assessing and mitigating online harms
NLP for social media
Abusive language detection
Large Language Models
Teaching and supervision
Current teaching responsibilities
-
Text Analytics (CE807)
Publications
Journal articles (6)
Shekhar, R., Pranjić, M., Pollak, S., Pelicon, A. and Purver, M., Automating News Comment Moderation with Limited Resources: Benchmarking in Croatian and Estonian. Journal for Language Technology and Computational Linguistics. 34 (1), 49-79
Healey, PGT., Khare, P., Castro, I., Tyson, G., Karan, M., Shekhar, R., McQuistin, S., Perkins, C. and Purver, M., (2024). Power and vulnerability: managing sensitive language in organizational communication. Frontiers in Psychology. 14
Udawatta, P., Udayangana, I., Gamage, C., Shekhar, R. and Ranathunga, S., (2024). Use of prompt-based learning for code-mixed and code-switched text classification. World Wide Web. 27 (5)
Alharthi, R., Alharthi, R., Shekhar, R. and Zubiaga, A., (2023). Target-Oriented Investigation of Online Abusive Attacks: A Dataset and Analysis. IEEE Access. 11, 64114-64127
Ranathunga, S., Lee, E-SA., Prifti Skenduli, M., Shekhar, R., Alam, M. and Kaur, R., (2023). Neural Machine Translation for Low-resource Languages: A Survey. ACM Computing Surveys. 55 (11), 1-37
Pelicon, A., Shekhar, R., Škrlj, B., Purver, M. and Pollak, S., (2021). Investigating cross-lingual training for offensive language detection.. PeerJ Computer Science. 7, e559-e559
Conferences (20)
He, Y., Gu, Y., Shekhar, R., Castro, I. and Tyson, G., Making the Pick: Understanding Professional Editor Comment Curation in Online News
Pelicon, A., Karan, M., Shekhar, R., Purver, M. and Pollak, S., (2024). Denoising Labeled Data for Comment Moderation Using Active Learning
Healey, P., Khare, P., Castro, I., Tyson, G., Karan, M., Shekhar, R., McQuistin, S., Perkins, C. and Purver, M., (2023). Power and Vulnerability: Managing Sensitive Language in Organisational Communication
Khare, P., Shekhar, R., Karan, M., McQuistin, S., Perkins, C., Castro, I., Tyson, G., Healey, PGT. and Purver, M., (2023). Tracing Linguistic Markers of Influence in a Large Online Organisation
Karan, M., Khare, P., Shekhar, R., McQuistin, S., Castro, I., Tyson, G., Perkins, C., Healey, PGT. and Purver, M., (2023). LEDA: a Large-Organization Email-Based Decision-Dialogue-Act Analysis Dataset
Venugopal, G., Pramod, D. and Shekhar, R., (2022). CWID-hi: A Dataset for Complex Word Identification in Hindi Text
Shekhar, R., Karan, M. and Purver, M., (2022). CoRAL: a Context-aware Croatian Abusive Language Dataset
Pelicon, A., Shekhar, R., Martinc, M., Škrlj, B., Purver, M. and Pollak, S., (2021). Zero-shot Cross-lingual Content Filtering: Offensive Language and Hate Speech Detection
Pollak, S., Šikonja, MR., Purver, M., Boggia, M., Shekhar, R., Pranjić, M., Salmela, S., Krustok, I., Paju, T., Linden, CG., Leppänen, L., Zosa, E., Ulčar, M., Freienthal, L., Traat, S., Cabrera-Diego, LA., Martinc, M., Lavrač, N., Škrlj, B., Žnidaršič, M., Pelicon, A., Koloski, B., Podpečan, V., Kranjc, J., Sheehan, S., Boros, E., Moreno, JG., Doucet, A. and Toivonen, H., (2021). EMBEDDIA Tools, Datasets and Challenges: Resources and Hackathon Contributions
Zosa, E., Shekhar, R., Karan, M. and Purver, M., (2021). Not All Comments are Equal: Insights into Comment Moderation from a Topic-Aware Model
Shekhar, R., Takmaz, E., Fernández, R. and Bernardi, R., (2019). Evaluating the Representational Hub of Language and Vision Models
Shekhar, R., Venkatesh, A., Baumgärtner, T., Bruni, E., Plank, B., Bernardi, R. and Fernández, R., (2019). Beyond task success: A closer look at jointly learning to see, ask, and
Shekhar, R., Testoni, A., Fernández, R. and Bernardi, R., (2019). Jointly learning to see, ask, decide when to stop, and then guesswhat
Shekhar, R., Baumgärtner, T., Venkatesh, A., Bruni, E., Bernardi, R. and Fernandez, R., (2018). Ask no more: Deciding when to guess in referential visual dialogue
Shekhar, R., Pezzelle, S., Klimovich, Y., Herbelot, A., Nabi, M., Sangineto, E. and Bernardi, R., (2017). FOIL it! Find One mismatch between Image and Language caption
Shekhar, R., Pezzelle, S., Herbelot, A., Nabi, M., Sangineto, E. and Bernardi, R., (2017). Vision and language integration: Moving beyond objects
Pezzelle, S., Shekhar, R. and Bernardi, R., (2016). Building a Bagpipe with a Bag and a Pipe: Exploring Conceptual Combination in Vision
Shekhar, R. and Jawahar, CV., (2013). Document Specific Sparse Coding for Word Retrieval
Shekhar, R. and Jawahar, CV., (2012). Word Image Retrieval Using Bag of Visual Words
Krishnan, P., Shekhar, R. and Jawahar, CV., (2012). Content level access to digital library of India pages
Grants and funding
2024
To explore and implement applications of natural language processing in commodities trading software, enabling operators to interact with their data in a conversational manner.
Innovate UK (formerly Technology Strategy Board)
2023
Multilingual and Cross-cultural interactions for context-aware, and bias-controlled dialogue systems for safety-critical applications
European Commission
Contact
Academic support hours:
Wednesday, 11:00 - 12:00 (In person) Thursday, 16:00 - 17:00 (On Zoon)
