1 code implementation • 28 Nov 2022 • Brendon Boldt, David Mortensen
We formulate a stochastic process, FiLex, as a mathematical model of lexicon entropy in deep learning-based emergent language systems.
1 code implementation • 22 Jun 2022 • Brendon Boldt, David Mortensen
We introduce FiLex, a self-reinforcing stochastic process which models finite lexicons in emergent language experiments.
no code implementations • 22 Jun 2022 • Brendon Boldt, David Mortensen
Emergent language is unique among fields within the discipline of machine learning for its open-endedness, not obviously presenting well-defined problems to be solved.
no code implementations • 29 Sep 2021 • Brendon Boldt, Yonatan Bisk, David R Mortensen
The second is shaped rewards which are designed specifically to make the task easier to learn by introducing biases in the learning process.
no code implementations • NAACL 2021 • Shrimai Prabhumoye, Brendon Boldt, Ruslan Salakhutdinov, Alan W Black
Recent work in natural language processing (NLP) has focused on ethical challenges such as understanding and mitigating bias in data and algorithms; identifying objectionable content like hate speech, stereotypes and offensive language; and building frameworks for better system design and data handling practices.
no code implementations • 3 Sep 2019 • Brendon Boldt, Zack While, Eric Breimer
An implicit association test is a human psychological test used to measure subconscious associations.
no code implementations • 26 Aug 2019 • Brendon Boldt
Recurrent neural networks (RNNs), specifically long-short term memory networks (LSTMs), can model natural language effectively.
no code implementations • 6 Mar 2018 • Ivan Gavran, Brendon Boldt, Eva Darulova, Rupak Majumdar
We present Flipper, a natural language interface for describing high-level task specifications for robots that are compiled into robot actions.