1 code implementation • 11 Nov 2021 • Fatih Cagatay Akyon, Devrim Cavusoglu, Cemil Cengiz, Sinan Onur Altinuc, Alptekin Temizel
In this work, we fine-tune a multilingual T5 (mT5) transformer in a multi-task setting for QA, QG and answer extraction tasks using Turkish QA datasets.
no code implementations • WS 2020 • Cemil Cengiz, Deniz Yuret
End-to-end models trained on natural language inference (NLI) datasets show low generalization on out-of-distribution evaluation sets.
Natural Language Inference Out-of-Distribution Generalization +2
no code implementations • 7 Nov 2019 • Yusuf Yigit Pilavci, Eylem Tugce Guneyi, Cemil Cengiz, Elif Vural
We estimate the unknown target labels by solving an optimization problem where the label information is transferred from the source graph to the target graph based on the prior that the projections of the label functions onto localized graph bases be similar between the source and the target graphs.
no code implementations • WS 2019 • Cemil Cengiz, Ula{\c{s}} Sert, Deniz Yuret
In this paper, we describe our system and results submitted for the Natural Language Inference (NLI) track of the MEDIQA 2019 Shared Task.