Papers by Devang Kulshreshtha
How emotional are you? Neural Architectures for Emotion Intensity Prediction in Microblogs (C18-1)
Copied to clipboard
| Challenge: | Social media based micro-blogging sites like Twitter are used for expressing emotions and opinions. |
| Approach: | They propose to combine convolutional and fully connected layers in a non-sequential manner to train deep multi-task learning models trained for all emotions at once in unified architecture. |
| Outcome: | The proposed model outperforms the previous system by 0.044 or 4.4% on the WASSA’17 EmoInt shared task dataset. |
Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval (2021.emnlp-main)
Copied to clipboard
| Challenge: | Using self-training to train unsupervised domains can be expensive, resulting in poor generalization due to distributional shift. |
| Approach: | They propose to use unaligned data to train unsupervised domain adaptation models using cheap synthetically generated labeled data. |
| Outcome: | The proposed method significantly outperforms self-training on question generation and passage retrieval domains and on MLQuestions and PubMedQA. |
The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems (2026.eacl-industry)
Copied to clipboard
| Challenge: | Existing literature on uncooperative behavior degrades collective outcomes and requires more resilient multi-agent systems. |
| Approach: | They propose a game theory-based taxonomy of uncooperative agent behaviors and a structured, multi-stage simulation pipeline that dynamically generates and refines uncooperation behaviors as agents’ states evolve. |
| Outcome: | The proposed framework achieves 96.7% accuracy in generating realistic uncooperative behaviors, validated by human evaluations. |
Retrieve and Copy: Scaling ASR Personalization to Large Catalogs (2023.emnlp-industry)
Copied to clipboard
| Challenge: | End-to-end ASR models struggle to recognize uncommon domain-specific words due to limited audio context. |
| Approach: | They propose a "Retrieve and Copy" mechanism to improve latency while retaining the accuracy even when scaled to a large catalog. |
| Outcome: | The proposed method achieves 6% more word error rate reduction and 3.6% improvement in F1 when scaled to a large catalog size while retaining the accuracy. |