Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Nancy Fulda
Agent Decompositions in Reinforcement Learning Architectures
Keywords agent decompositions, reinforcement learning architectures, learning speed College Physical and Mathematical Sciences Department Computer Science Abstract Reinforcement learning is a sub-discipline of machine learning in which an autonomous program, called an agent, learns to behave appropriately in its environment. Appropriate behavior is described in terms of numerical reinforcements which the agent receives for appropriate or inappropriate actions.
Out of One, Many: Using Language Models to Simulate Human Samples
Hostname: page-component-b7cdf9bb7-7m8tn Total loading time: 0 Render date: 2023-04-05T09:06:24.535Z Has data issue: false Feature Flags: { "useRatesEcommerce": false } hasContentIssue false Published online by Cambridge University Press: 21 February 2023 Lisa P. Argyle [Opens in a new window] , Joshua R.
Out of One, Many: Using Language Models to Simulate Human Samples
References Adiwardana, D., et al. 2020. “Towards a Human-Like Open-Domain Chatbot.” Preprint, arXiv:2001.09977.Google Scholar ANES. 2021. “American National Election Studies.” https://electionstudies.org/about-us/.Google Scholar Argyle, L. P., Busby, E. C., Fulda, N., Gubler, J. R., Rytting, C., and Wingate, D.. 2022. “Replication Data for: ‘Out of One, Many: Using Language Models to Simulate Human Samples’.” https://doi.org/10.7910/DVN/JPV20K CrossRefGoogle Scholar Barberá, P., Boydstun, A.
Out of One, Many: Using Language Models to Simulate Human Samples
Do you navigate arXiv using a screen reader or other assistive technology? Are you a professor who helps students do so? We want to hear from you. Please consider signing up to share your insights as we work to make arXiv even more open.
Semantically Aligned Sentence-Level Embeddings for Agent Autonomy and Natural Language Understanding
Abstract Many applications of neural linguistic models rely on their use as pre-trained features for downstream tasks such as dialog modeling, machine translation, and question answering. This work presents an alternate paradigm: Rather than treating linguistic embeddings as input features, we treat them as common sense knowledge repositories that can be queried using simple mathematical operations within the embedding space, without the need for additional training.
Humor as a Plot Adhesive
by Nancy Fulda As fiction writers, we talk a lot about humor. We talk about what’s funny. We talk about what isn’t. We talk about appropriate moments for humor, the types of audience best suited to it, and the consequences of attempted humor gone horribly wrong. Today, I’d like to ignore all that and focus, instead, on one specific aspect of humor that often gets overlooked: its effectiveness as a plot-patch. I know, I know! Nobody wants to patch their plot.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Nancy
Contact Nancy, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack