Papers by Ankit Chadha
Controlled Text Generation with Hidden Representation Transformations (2023.findings-acl)
Copied to clipboard
| Challenge: | Using a con-trolled language model, we gain attribute control by modifying the hidden representation of thebase model through learning transformations. |
| Approach: | They propose a con-trolled language generation framework that gains attribute control bymodifying the hidden representation of thebase model through learned transformations. |
| Outcome: | The proposed framework outperforms all thebaselines in detoxification, positivesentiment steering, and text simplification while minimizing the loss in linguistic qualities. |
Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource Languages (2023.findings-acl)
Copied to clipboard
| Challenge: | Cross-Lingual Knowledge Distillation (CLKD) is a method to train AS2 models for low-resource languages without labeled data. |
| Approach: | They propose a method to train AS2 models for low-resource languages without labeled data . they use a translation-based WikiQA dataset and a multilingual AS2 dataset . |
| Outcome: | The proposed method outperforms or rivals fine-tuning with labeled data and machine translation and the teacher model. |
APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models struggle with reliable long-term conversational memory . enlarging context windows or applying nave retrieval often introduces noise . |
| Approach: | They propose a conversational memory system that uses domain-agnostic ontology to structure conversations as temporally grounded events in an entity-centric framework. |
| Outcome: | APEX-MEM outperforms state-of-the-art retrieval methods in accuracy and time resolution. |
Training Mixed-Domain Translation Models via Federated Learning (2022.naacl-main)
Copied to clipboard
| Challenge: | Experimental results show that neural machine translation engines built via FL can be easily adapted when an FL-based aggregation is applied to fuse different domains. |
| Approach: | They propose to use federated learning to fuse mixed-domain translation models with a centralized aggregation to improve their performance. |
| Outcome: | The proposed model can be easily adapted to a mixed-domain translation model with slight modifications in the training process and perform on par with state-of-the-art training models. |