Computational Models of Language (at UC Irvine)

I love how this work uses state-of-the-art “AI” models (i.e., neural networks with distributed representations) to concretely explore ideas ...

The utility of incorporating human-like biases into LLMs trying to learn language is that language is a human construct, transmitted by huma...

I really feel for the goal of investigating what general-purpose learners can extract from an input signal, with the aim of identifying when...

I really appreciate trying to leverage a sophisticated language modeling tool (neural networks = NNs) to help us understand child language a...

Before I read a single word of this paper, I already loved the idea of this: encoding useful symbolic knowledge into a distributed represent...

I’m definitely on board with the spirit of these papers. My position: I would love to understand more about how children do what they do whe...

To me, th is is a beautifully accessible review article for the probabilistic pragmatics approach, as implemented in RSA. (Figure 1 in parti...

I really appreciated the leisurely pace and accessible tone of this writing, especially for someone who’s not super-familiar with the nuts a...

I love the way Hahn et al. (2022) set up the two approaches they’re combining – it seems like the most natural thing in the world to combine...

I love seeing work that evaluates an idea against naturalistic data. It’s often the exciting next “proof of concept” once you’ve got an impl...

I really like seeing modeling work like this where a more complex, ideal computation (here, EIG) can be well-approximated by a simpler, more...

This paper made me really happy because it involved careful thought about what was being investigated, an accessible intuition about how eac...