Papers by Vivek Iyer
XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Cross-lingual open-ended generation is an important yet understudied problem. |
| Approach: | They propose XL-Instruct, a novel technique for generating high-quality synthetic data, and introduce Xl-AlpacaEval, evaluating cross-lingual generation capabilities of large language models. |
| Outcome: | The proposed technique improves model performance by fine tuning with just 8K instructions generated using XL-Instruct, and also by improving on several fine-grained quality metrics. |
Towards Automatic Evaluation for Image Transcreation (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for evaluating image transcreation have relied on human evaluation. |
| Approach: | They propose a suite of automatic evaluation metrics inspired by machine translation metrics . they identify cultural relevance, semantic equivalence and visual similarity as critical dimensions of image transcreation . |
| Outcome: | The proposed evaluation metrics agree with human ratings across 7 countries. |
Code-Switching with Word Senses for Pretraining in Neural Machine Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Lexical ambiguity is a significant and pervasive challenge in Neural Machine Translation (NMT) many state-of-the-art (SOTA) NMT systems struggle to handle polysemous words . |
| Approach: | They propose an end-to-end approach for pretraining multilingual NMT models leveraging word sense-specific information from Knowledge Bases. |
| Outcome: | The proposed approach improves translation quality and scales to various data and resource-strapped scenarios. |
Exploring Enhanced Code-Switched Noising for Pretraining in Neural Machine Translation (2023.findings-eacl)
Copied to clipboard
| Challenge: | Multilingual pretraining approaches to denoise synthetic code-switched data have shown that they generate the noise using non-contextual, one-to-one word translations obtained from lexicons. |
| Approach: | They propose an approach where contextual, many-to-many word translations are generated using a ‘base’ NMT model. |
| Outcome: | The proposed approach improves on 3 different language families and shows that small models can perform better than massive models like mBART50 and mRASP2 . |
VeeAlign: Multifaceted Context Representation Using Dual Attention for Ontology Alignment (2021.emnlp-main)
Copied to clipboard
| Challenge: | State-of-the-art Ontology Alignment systems are based on domain-dependent approaches with handcrafted rules or domain-specific architectures, making them unscalable and inefficient. |
| Approach: | They propose a Deep Learning based model that exploits syntactic and semantic information encoded in ontologies by using a dual-attention mechanism. |
| Outcome: | The proposed model exploits syntactic and semantic information encoded in ontologies and is flexible and scalable to different domains with minimal effort. |