Papers by Deniz Yuret

4 papers
Neurocache: Efficient Vector Retrieval for Long-range Language Modeling (2024.naacl-long)

Copied to clipboard

Challenge: Recent research shows that retrieval-augmented models with shorter contexts (4K tokens) can match the performance of models with longer contexts (16K/32K token)
Approach: They introduce an approach to extend the effective context size of large language models by using an external vector cache to store past states.
Outcome: The proposed method improves on models trained from scratch and pre-trained models.
CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions (2022.findings-acl)

Copied to clipboard

Challenge: Existing models with similar physical and causal understanding capabilities are still underdeveloped.
Approach: They propose a video question answering dataset that requires causal reasoning about physical forces and object interactions.
Outcome: The proposed dataset requires causal reasoning about physical forces and object interactions.
Mukayese: Turkish NLP Strikes Back (2022.findings-acl)

Copied to clipboard

Challenge: Having sufficient resources for language X lifts it from the under-resourced languages class, but not necessarily from the researched class.
Approach: They propose a set of NLP benchmarks for the Turkish language that contains several NLP tasks.
Outcome: The proposed benchmarks outperform previous work significantly in the Turkish language.
Sequential Compositional Generalization in Multimodal Models (2024.naacl-long)

Copied to clipboard

Challenge: a growing number of multimodal models have a limited capacity for generalization . however, prior studies into compositionality have focused on visual grounding and downstream tasks like image captioning.
Approach: They examine compositional generalization using egocentric kitchen activity videos . they find bi-modal and tri-modal models exhibit a clear edge over their text-only counterparts .
Outcome: The proposed model outperforms text-only models in a multimodal setting.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations