Publications

Yuchen Zhang, Haralambos Mouratidis, Ravi Shekhar (2026). Preserve to Expand: Source-Aware Adaptation and Model Merging for Multilingual LLM-Based ASR. arXiv preprint arXiv:2610.35846.

PDF DOI

Ashley E. Bravo-Bravo, Yuchen Zhang, Haralambos Mouratidis, Ravi Shekhar, Monorama Swain (2026). InterCorrect: Intersection-Aware Correction of Demographic Model Merging for Fair ASR. arXiv preprint arXiv:2610.08604.

PDF DOI

Ganesh Pavan Kartikeya Bharadwaj Kolluri, Michael Kampouridis, Ravi Shekhar (2026). Pruning for Efficiency, Paying in Fairness: Demographic Disparities in Pruned Speech-LLMs. Proceedings of the IMPACT-SPEECH Workshop: Identifying, Measuring, Preventing, and Assessing Consequences of Bias in Speech LLMs.

PDF DOI

Yuchen Zhang, Shuang Dai, Zeyu Fu, Yunfei Long, Ravi Shekhar, Haralambos Mouratidis (2026). CLARA: Clip-Level Multimodal Alignment with VLM-Derived Rationales for Hateful Video Detection. Proceedings of the 34th ACM International Conference on Multimedia (ACM MM 2026).

PDF Code DOI

Ganesh Pavan Kartikeya Bharadwaj Kolluri, Yuchen Zhang, Michael Kampouridis, Ravi Shekhar (2026). CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning. IEEE Spoken Language Technology Workshop (SLT 2026).

PDF

Ganesh Pavan Kartikeya Bharadwaj Kolluri, Michael Kampouridis, Ravi Shekhar (2026). On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR. Proceedings of the Speakable:Speech Language Models in Low-Resource Settings:Performance, Evaluation, and Bias Analysis (LREC Workshop), 2026.

Code Project

Yuchen Zhang, Haralambos Mouratidis, Ravi Shekhar (2026). Speak in Context: Multilingual ASR with Speech–Context Alignment via Contrastive Learning. The Fifteenth biennial Language Resources and Evaluation Conference (LREC 2026).

Code Project

Hannah Liu, Muxin Tian, Iqra Ali, Haonan Gao, Qiaoyiwen Wu, Blair Yang, Uthayasanker Thayasivam, En-Shiun Annie Lee, Pakawat Nakwijit, Surangika Ranathunga, Ravi Shekhar (2026). OasisSimp: An Open-source Asian-English Sentence Simplification Dataset. The Fifteenth biennial Language Resources and Evaluation Conference (LREC 2026).

Project

Yuchen Zhang, Ravi Shekhar, Haralambos Mouratidis (2026). Language Family Matters: Evaluating LLM-Based ASR Across Linguistic Boundaries. 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026).

PDF Project

Olga Loginova, Oleksandr Bezrukov, Ravi Shekhar, Alexey Kravets (2025). Addressing Blind Guessing: Calibration of Selection Bias in Multiple-Choice Question Answering by Video Language Models. Association for Computational Linguistics: ACL 2025.

PDF Code

Surangika Ranathunga, Rumesh Sirithunga, Himashi Rathnayake, Lahiru de Silva, Thamindu Aluthwala, Saman Peramuna, Ravi Shekhar (2025). SiTSE: Sinhala Text Simplification Dataset and Evaluation. ACM Transactions on Asian and Low-Resource Language Information Processing.

PDF Project DOI

Raneem Alharthi, Rajwa Alharthi, Ravi Shekhar, Aiqi Jiang, Arkaitz Zubiaga (2025). Will I Get Hate Speech Predicting the Volume of Abusive Replies before Posting in Social Media. arXiv preprint arXiv:2503.03005.

PDF DOI

Pasindu Udawatta, Indunil Udayangana, Chathulanka Gamage, Ravi Shekhar, Surangika Ranathunga (2024). Use of prompt-based learning for code-mixed and code-switched text classification. World Wide Web.

PDF DOI

Andraž Pelicon, Vanja M Karan, Ravi Shekhar, Matthew Purver, Senja Pollak (2024). Denoising Labeled Data for Comment Moderation Using Active Learning. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING).

Dataset

Patrick Healey, Prashant Khare, Ignacio Castro, Gareth Tyson, Vanja M Karan, Ravi Shekhar, Stephen McQuistin, Colin Perkins, Matthew Purver (2024). Power and Vulnerability: Managing Sensitive Language in Organisational Communication. Frontiers in Psychology.

Project

Yupeng He, Yimeng Gu, Ravi Shekhar, Ignacio Castro, Gareth Tyson (2024). Making the Pick: Understanding Professional Editor Comment Curation in Online News. 18th International AAAI Conference on Web and Social Media (ICWSM), 2024.

Project

Prashant Khare, Ravi Shekhar, Vanja M Karan, Stephen McQuistin, Colin Perkins, Ignacio Castro, Gareth Tyson, Patrick Healey, Matthew Purver (2023). Tracing Linguistic Markers of Influence in a Large Online Organisation. Association for Computational Linguistics: ACL 2023.

PDF Code Project

Vanja M Karan, Prashant Khare, Ravi Shekhar, Stephen McQuistin, Ignacio Castro, Gareth Tyson, Colin Perkins, Patrick Healey, Matthew Purver (2023). LEDA: a Large-Organization Email-Based Decision-Dialogue-Act Analysis Dataset. Findings of the Association for Computational Linguistics: ACL 2023.

PDF Code Project

Raneem Alharthi, Rajwa Alharthi, Ravi Shekhar, Arkaitz Zubiaga (2023). Target-Oriented Investigation of Online Abusive Attacks: A Dataset and Analysis. IEEE Access ( Volume: 11).

PDF Code DOI

Patrick Healey, Prashant Khare, Ignacio Castro, Gareth Tyson, Vanja M Karan, Ravi Shekhar, Stephen McQuistin, Colin Perkins, Matthew Purver (2023). Power and Vulnerability: Managing Sensitive Language in Organisational Communication. 33rd Annual Meeting of the Society for Text and Discourse (ST&D 2023).

Project

Surangika Ranathunga, En-Shiun Annie Lee, Marjana Prifti Skenduli, Ravi Shekhar, Mehreen Alam, Rishemjit Kaur (2023). Neural Machine Translation for Low-resource Languages: A Survey. ACM Computing Surveys.

PDF DOI

Ravi Shekhar, Vanja M Karan, Matthew Purver (2022). CoRAL: a Context-aware Croatian Abusive Language Dataset. Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022.

PDF Code Project

Gayatri Venugopal, Dhanya Pramod, Ravi Shekhar (2022). CWID-hi: A Dataset for Complex Word Identification in Hindi Text. Proceedings of the Thirteenth Language Resources and Evaluation Conference.

PDF Project

Elaine Zosa, Ravi Shekhar, Vanja M Karan, Matthew Purver (2021). Not All Comments are Equal: Insights into Comment Moderation from a Topic-Aware Model. 13th biennial International Conference Recent Advances in Natural Language Processing (RANLP).

Project

Andraž Pelicon, Ravi Shekhar, Blaž Škrlj, Matthew Purver, Senja Pollak (2021). Investigating cross-lingual training for offensive language detection. PeerJ Computer Science.

PDF Code Project DOI

Andraž Pelicon, Ravi Shekhar, Matej Martinc, Blaž Škrlj, Matthew Purver, Senja Pollak (2021). Zero-shot Cross-lingual Content Filtering: Offensive Language and Hate Speech Detection. Proceedings of the Hackashop on News Media Content Analysis and Automated Report Generation (EACL).

PDF Project

Senja Pollak, Marko Robnik-Šikonja, Matthew Purver, Michele Boggia, Ravi Shekhar, Marko Pranjić, Salla Salmela, Ivar Krustok, Tarmo Paju, Carl-Gustav Linden, Leo Leppänen, Elaine Zosa, Matej Ulčar, Linda Freiental, Silver Traat, Luis Adrián Cabrera-Diego, Matej Martinc, Nada Lavrač, Blaž Škrlj, Martin Žnidaršič, Andraž Pelicon, Boshko Koloski, Vid Podečan, Janez Kranjc, Shane Sheehan, Emanuela Boros, Jose Moreno, Antoine Doucet, Hannu Toivonen (2021). EMBEDDIA Tools, Datasets and Challenges: Resources and Hackathon Contributions. Proceedings of the Hackashop on News Media Content Analysis and Automated Report Generation (EACL).

PDF Project

Ravi Shekhar, Marko Pranjić, Senja Pollak, Andraž Pelicon, Matthew Purver (2020). Automating News Comment Moderation with Limited Resources: Benchmarking in Croatian and Estonian. Journal for Language Technology and Computational Linguistics (JLCL).

PDF Project

Ravi Shekhar, Alberto Testoni, Raquel Fernández, Raffaella Bernardi (2019). Jointly Learning to See, Ask, Decide when to Stop, and then GuessWhat. 23rd Italian Conference on Computational Linguistics (CLiC-it), 2019.

PDF Code Project

Alberto Testoni, Ravi Shekhar, Raquel Fernández, Raffaella Bernardi (2019). The Devil is in the Detail: A Magnifying Glass for the GuessWhich Visual Dialogue Game. Proceedings of the 23rd Workshop on the Semantics and Pragmatics of Dialogue (SemDial), - Full Papers.

PDF Code Project

Ravi Shekhar, Ece Takmaz, Raquel Fernández, Raffaella Bernardi (2019). Evaluating the Representational Hub of Language and Vision Models. Proceedings of the 13th International Conference on Computational Semantics (IWCS) - Long Papers.

PDF Project DOI

Ravi Shekhar(?), Aashish Venkatesh(?), Tim Baumgärtner, Elia Bruni, Barbara Plank, Raffaella Bernardi, Raquel Fernández (2019). Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), Volume 1 (Long and Short Papers).

PDF Code Project DOI

Ravi Shekhar, Tim Baumgärtner, Aashish Venkatesh, Elia Bruni, Raffaella Bernardi, Raquel Fernández (2018). Ask No More: Deciding when to guess in referential visual dialogue. Proceedings of the 27th International Conference on Computational Linguistics (COLING).

PDF Code Project

Ravi Shekhar, Ece Takmaz, Nikos Kondylidis, Claudio Greco, Raffaella Bernardi, Raquel Fernández (2018). Learning to see from experience: But which experience is more propaedeutic?. In Shortcomings in Vision and Language, ECCV (SiVL@ECCV).

Project

Ravi Shekhar, Sandro Pezzelle, Aurélie Herbelot, Moin Nabi, Enver Sangineto, Raffaella Bernardi (2017). Vision and Language Integration: Moving beyond Objects. In 2nd Workshop on Closing the Loop Between Vision and Language (ICCV).

Project

Ravi Shekhar, Sandro Pezzelle, Aurélie Herbelot, Moin Nabi, Enver Sangineto, Raffaella Bernardi (2017). Vision and Language Integration: Moving beyond Objects. 12th International Conference on Computational Semantics (IWCS) — Short papers.

PDF Project

Ravi Shekhar, Sandro Pezzelle, Yauhen Klimovich, Aurélie Herbelot, Moin Nabi, Enver Sangineto, Raffaella Bernardi (2017). FOIL it! Find One mismatch between Image and Language caption. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL) (Volume 1: Long Papers).

PDF Project DOI

Sandro Pezzelle, Ravi Shekhar, Raffaella Bernardi (2016). Building a Bagpipe with a Bag and a Pipe: Exploring Conceptual Combination in Vision. Proceedings of the 5th Workshop on Vision and Language (VL@ACL).

PDF DOI

Ravi Shekhar, CV Jawahar (2013). Document specific sparse coding for word retrieval. 12th International Conference on Document Analysis and Recognition (ICDAR).

PDF Project DOI

Praveen Krishnan(?), Ravi Shekhar(?), CV Jawahar (2012). Content level access to digital library of india pages. Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP).

PDF Project

Ravi Shekhar, CV Jawahar (2012). Word image retrieval using bag of visual words. 10th IAPR International Workshop on Document Analysis Systems (DAS).

PDF Project DOI