1 code implementation • 6 Apr 2022 • Sunit Bhattacharya, Věra Kloudová, Vilém Zouhar, Ondřej Bojar
We present the Eyetracked Multi-Modal Translation (EMMT) corpus, a dataset containing monocular eye movement recordings, audio and 4-electrode electroencephalogram (EEG) data of 43 participants.
1 code implementation • 13 Oct 2022 • Sunit Bhattacharya, Vilém Zouhar, Ondřej Bojar
It is unclear whether, how and where large pre-trained language models capture subtle linguistic traits like ambiguity, grammaticality and sentence complexity.
no code implementations • CMCL (ACL) 2022 • Sunit Bhattacharya, Rishu Kumar, Ondrej Bojar
Our submissions achieved an average MAE of 5. 72 and ranked 5th in the shared task.
no code implementations • 20 Mar 2023 • Vilém Zouhar, Sunit Bhattacharya, Ondřej Bojar
To investigate the impact of multimodal information in this game, we use human participants and a language model (LM, GPT-2).
no code implementations • 24 Oct 2023 • Sunit Bhattacharya, Ondrej Bojar
The values then combine the output from the 'memories' of the keys to generate predictions about the next token.