David Demeter

According to our database, David Demeter authored at least 8 papers between 2018 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Sentiment analysis with adaptive multi-head attention in Transformer.

Fanfei Meng, David Demeter

CoRR, 2023

Summarization from Leaderboards to Practice: Choosing A Representation Backbone and Ensuring Robustness.

David Demeter, Oshin Agarwal, Simon Ben Igeri, Marko Sterbentz, Neil P. Molino, John M. Conroy, Ani Nenkova

CoRR, 2023

2022

Learning to Perform Complex Tasks through Compositional Fine-Tuning of Language Models.

Victor S. Bursztyn, David Demeter, Doug Downey, Larry Birnbaum

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

2021

CODE: Compiler-based Neuron-aware Ensemble training.

Ettore M. G. Trainiti, Thanapon Noraset, David Demeter, Doug Downey, Simone Campanoni

Proceedings of Machine Learning and Systems 2021, 2021

Who's on First?: Probing the Learning and Representation Capabilities of Language Models on Deterministic Closed Domains.

David Demeter, Doug Downey

Proceedings of the 25th Conference on Computational Natural Language Learning, 2021

2020

Stolen Probability: A Structural Weakness of Neural Language Models.

David Demeter, Gregory Kimmel, Doug Downey

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020

Just Add Functions: A Neural-Symbolic Language Model.

David Demeter, Doug Downey

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2018

Controlling Global Statistics in Recurrent Neural Network Text Generation.

Thanapon Noraset, David Demeter, Doug Downey

Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018