activity
20172021
most citedMSVD-Turkish: A Comprehensive Multimodal Dataset for Integrated Vision and Language Research in Turkish

3 citations · 6 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

14 papers · 1 filter

cs.CL2021

BERTGEN: Multi-task Generation through BERT

Faidon Mitzalis, Ozan Caglayan, Pranava Madhyastha +1

We present BERTGEN, a novel generative, decoder-only model which extends BERT by fusing multimodal and multilingual pretrained models VL-BERT and M-BERT, respectively. BERTGEN is a…

cs.CL2021

Exploiting Multimodal Reinforcement Learning for Simultaneous Machine Translation

Julia Ive, Andy Mingren Li, Yishu Miao +3

This paper addresses the problem of simultaneous machine translation (SiMT) by exploring two main concepts: (a) adaptive policies to learn a good trade-off between high translation…

cs.CL2021

Cross-lingual Visual Pre-training for Multimodal Machine Translation

Ozan Caglayan, Menekse Kuyu, Mustafa Sercan Amac +4

Pre-trained language models have been shown to improve performance in many natural language tasks substantially. Although the early focus of such models was single language pre-tra…

cs.CL20201 cited

Curious Case of Language Generation Evaluation Metrics: A Cautionary Tale

Ozan Caglayan, Pranava Madhyastha, Lucia Specia

Automatic evaluation of language generation systems is a well-studied problem in Natural Language Processing. While novel metrics are proposed every year, a few popular metrics rem…

cs.CL2020

Simultaneous Machine Translation with Visual Context

Ozan Caglayan, Julia Ive, Veneta Haralampieva +3

Simultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. The translation…

cs.CL2019

Multimodal Machine Translation through Visuals and Speech

Umut Sulubacak, Ozan Caglayan, Stig-Arne Grönroos +4

Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative view…