Papers by Yannick Versley
Continuous Model Improvement for Language Understanding with Machine Translation (2021.naacl-industry)
Copied to clipboard
Abdalghani Abujabal, Claudio Delli Bovi, Sungho Ryu, Turan Gojayev, Fabian Triefenbach, Yannick Versley
| Challenge: | a simple translation-test approach would fail the latency requirements of a live environment. |
| Approach: | They show that annotating unlabeled utterances offline can improve performance . they demonstrate that an extrinsic evaluation can improve the performance if manual data is available . |
| Outcome: | The proposed method improves performance in an extrinsic evaluation setting with real-world commercial dialog system in german. |
Adapting Vision-Language Models for E-commerce Understanding at Scale (2026.eacl-industry)
Copied to clipboard
Matteo Nulli, Vladimir Orshulevich, Tala Bazazo, Christian Herold, Michael Kozielski, Marcin Mazur, Szymon Tuzel, Cees G. M. Snoek, Seyyed Hadi Hashemi, Omar Javed, Yannick Versley, Shahram Khadivi
| Challenge: | Existing approaches to adapt VLMs to attribute-centric, multi-image, and noisy data are limited. |
| Approach: | They propose a novel evaluation suite that incorporates deep product understanding, strict instruction following, and dynamic attribute extraction. |
| Outcome: | The proposed model improves e-commerce performance while preserving broad multimodal capabilities. |
Domain Adaptation of Foundation LLMs for e-Commerce (2025.acl-industry)
Copied to clipboard
Christian Herold, Michael Kozielski, Tala Bazazo, Pavel Petrushkov, Yannick Versley, Seyyed Hadi Hashemi, Patrycja Cieplicka, Dominika Basaj, Shahram Khadivi
| Challenge: | Large Language Models (LLMs) have greatly improved the performance on most natural language tasks, and often show surprisingly good zero-shot generalization to new domains. |
| Approach: | They propose to continuously pretrain the Llama 3.1 base models on 1 trillion tokens of e-commerce data to introduce domain specific knowledge into the model while at the same time keeping the general capabilities intact. |
| Outcome: | The proposed model can be adapted to the new domain without sacrificing performance on general domain tasks. |
LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging (2022.coling-1)
Copied to clipboard
| Challenge: | LINGUIST generates annotated data for Intent Classification and Slot Tagging (IC+ST) we demonstrate fine-tuning of a large-scale seq2seq model to control outputs of multilingual data generation. |
| Approach: | They propose a method for generating annotated data for Intent Classification and Slot Tagging (IC+ST) they use a 5-billion-parameter multilingual sequence-to-sequence model to fine-tune it on a flexible instruction prompt. |
| Outcome: | The proposed method outperforms state-of-the-art approaches on a SNIPS intent setting and shows significant improvement on IC+ST in a cross-lingual setting. |