Barlas Oğuz

RESEARCH SCIENTIST | MENLO PARK, UNITED STATES

Barlas is a research scientist at Facebook AI, working on question answering and information retrieval. Previously, he was an applied researcher at Microsoft, Sunnyvale, working on language modeling. He received his Ph.D degree at University of California, Berkeley in information theory, and a BS degree in Electrical Engineering from Bilkent University in Ankara, Turkey.

Barlas's Publications

June 14, 2024

NLP

How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval

Sheng-Chieh Lin, Akari Asai, Minghan Li, Barlas Oguz, Jimmy Lin, Scott Yih, Xilun Chen

June 14, 2024

September 27, 2023

NLP

Effective Long-Context Scaling of Foundation Models

Wenhan Xiong, Igor Molybog, Hejia Zhang, Praj Bhargava, Rui Hou, Louis Martin, Rashi Rungta, Karthik Abinav Sankararaman, Barlas Oguz, Madian Khabsa, Han Fang, Yashar Mehdad, Sharan Narang, Kshitiz Malik, Angela Fan, Shruti Bhosale, Sergey Edunov, Mike Lewis, Sinong Wang, Hao Ma, Jingyu Liu

September 27, 2023

June 20, 2023

NLP

CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval

Minghan Li, Jack Lin, Barlas Oguz, Asish Ghoshal, Jimmy Lin, Yashar Mehdad, Scott Yih, Xilun Chen

June 20, 2023

July 07, 2022

NLP

CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training

Xilun Chen, Armen Aghajanyan, Barlas Oguz, Scott Yih, Sonal Gupta, Patrick Huber

July 07, 2022

May 06, 2022

Domain-matched Pre-training Tasks for Dense Retrieval

Barlas Oguz, Aleksandra Piktus, Anchit Gupta, Kushal Lakhotia, Patrick Lewis, Scott Yih, Sebastian Riedel, Sonal Gupta, Vladimir Karpukhin, Xilun Chen, Yashar Mehdad

May 06, 2022

May 02, 2020

MLQA: Evaluating Cross-lingual Extractive Question Answering

Patrick Lewis, Barlas Oguz, Holger Schwenk, Ruty Rinott, Sebastian Riedel

May 02, 2020

July 20, 2018

RESEARCH

SPEECH & AUDIO

Multilingual seq2seq training with similarity loss for cross-lingual document classification

Katherin Yu, Barlas Oguz, Haoran Li

July 20, 2018