Papers by Rajkumar Pujari
TAIGR: Towards Modeling Influencer Content on Social Media via Structured, Pragmatic Inference (2026.acl-long)
Copied to clipboard
| Challenge: | Health influencers are often conveyed through conversational narratives and rhetorical strategies rather than explicit factual claims. |
| Approach: | They propose a framework to analyze influencer discourse using takeaway argumentation inference with Grounded References. |
| Outcome: | The proposed framework is based on a content validation task over influencer video transcripts on health, showing that accurate validation requires modeling the discourse’s pragmatic and argumentative structure rather than treating transcripts as flat collections of claims. |
“We Demand Justice!”: Towards Social Context Grounding of Political Texts (2024.emnlp-main)
Copied to clipboard
| Challenge: | Political discourse on social media often contains similar language with opposing intended meanings. |
| Approach: | They propose to characterize the social context required to fully understand political discourse . structured models outperform larger models on both tasks, but still lag behind human performance . |
| Outcome: | The proposed models outperform larger models on both tasks but lag behind human performance. |
Understanding Politics via Contextualized Discourse Processing (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in pretrained language models do not capture nuanced biases in political discourse . a new approach to represent political content is to use contextualized embeddings to create effective representations . |
| Approach: | They propose a model that captures and leverages political content to generate more effective representations . they use tweets, press releases, issues, news articles and participating entities to generate composed representations. |
| Outcome: | The proposed model generates representations for political entities over multiple issues or events . qualitative and quantitative analysis shows that the model is meaningful and effective . |
Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection (2022.acl-long)
Copied to clipboard
| Challenge: | Existing ‘Stereotype Detection’ datasets adopt a diagnostic approach toward large PLMs. |
| Approach: | They propose a multi-task model that leverages the abundance of data-rich neighboring tasks such as hate speech detection, offensive language detection, misogyny detection, etc., to improve the empirical performance. |
| Outcome: | The proposed model achieves significant gains over baselines on hate speech detection, offensive language detection, misogyny detection, etc. |
LLM-Human Pipeline for Cultural Grounding of Conversations (2025.naacl-long)
Copied to clipboard
| Challenge: | addressing parents by name is commonplace in the West, but it is rare in most Asian cultures. |
| Approach: | They propose a Cultural Context Schema for conversations that incorporates conversational information and cultural information such as social norms, violations, etc. |
| Outcome: | The proposed model significantly improves the empirical performance of a Chinese conversational norm and violation description using an interactive human-in-loop framework. |
Using Natural Language Relations between Answer Choices for Machine Comprehension (N19-1)
Copied to clipboard
| Challenge: | Current approaches to the reading comprehension task quantify the relationship between each question and answer choice independently and pick the highest scoring option. |
| Approach: | They propose a method to leverage natural language relations between answer choices to improve machine comprehension. |
| Outcome: | The proposed model improves the performance of a reading comprehension task by leveraging natural language relations between answer choices. |
Can Taxonomy Help? Improving Semantic Question Matching using Question Taxonomy (C18-1)
Copied to clipboard
Deepak Gupta, Rajkumar Pujari, Asif Ekbal, Pushpak Bhattacharyya, Anutosh Maitra, Tom Jain, Shubhashis Sengupta
| Challenge: | Existing QA systems that answer factual questions with short answers are rare in practice. |
| Approach: | They propose a proposed two-layered taxonomy technique for semantic question matching . they augment state-of-the-art deep learning models with question classes from a deep learning based question classifier . |
| Outcome: | The proposed technique achieves state-of-the-art on an open-domain dataset. |