Search Results for author: Robert D. Hawkins

Found 22 papers, 16 papers with code

Learning a Hierarchical Planner from Humans in Multiple Generations

no code implementations17 Oct 2023 Leonardo Hernandez Cano, Yewen Pu, Robert D. Hawkins, Josh Tenenbaum, Armando Solar-Lezama

Compared to learning from demonstrations or experiences, programmatic learning allows the machine to acquire a novel skill as soon as the program is written, and, by building a library of programs, a machine can quickly learn how to perform complex tasks.

Causal interventions expose implicit situation models for commonsense language understanding

1 code implementation6 Jun 2023 Takateru Yamakoshi, James L. McClelland, Adele E. Goldberg, Robert D. Hawkins

Accounts of human language processing have long appealed to implicit ``situation models'' that enrich comprehension with relevant but unstated world knowledge.

World Knowledge

Semantic uncertainty guides the extension of conventions to new referents

no code implementations11 May 2023 Ron Eliav, Anya Ji, Yoav Artzi, Robert D. Hawkins

A long tradition of studies in psycholinguistics has examined the formation and generalization of ad hoc conventions in reference games, showing how newly acquired conventions for a given target transfer to new referential contexts.

Overinformative Question Answering by Humans and Machines

no code implementations11 May 2023 Polina Tsvilodub, Michael Franke, Robert D. Hawkins, Noah D. Goodman

When faced with a polar question, speakers often provide overinformative answers going beyond a simple "yes" or "no".

Question Answering

Abstract Visual Reasoning with Tangram Shapes

no code implementations29 Nov 2022 Anya Ji, Noriyuki Kojima, Noah Rush, Alane Suhr, Wai Keen Vong, Robert D. Hawkins, Yoav Artzi

We introduce KiloGram, a resource for studying abstract visual reasoning in humans and machines.

Visual Reasoning

Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines

1 code implementation23 May 2022 Sreejan Kumar, Carlos G. Correa, Ishita Dasgupta, Raja Marjieh, Michael Y. Hu, Robert D. Hawkins, Nathaniel D. Daw, Jonathan D. Cohen, Karthik Narasimhan, Thomas L. Griffiths

Co-training on these representations result in more human-like behavior in downstream meta-reinforcement learning agents than less abstract controls (synthetic language descriptions, program induction without learned primitives), suggesting that the abstraction supported by these representations is key.

Meta-Learning Meta Reinforcement Learning +2

Identifying concept libraries from language about object structure

1 code implementation11 May 2022 Catherine Wong, William P. McCarthy, Gabriel Grand, Yoni Friedman, Joshua B. Tenenbaum, Jacob Andreas, Robert D. Hawkins, Judith E. Fan

Our understanding of the visual world goes beyond naming objects, encompassing our ability to parse objects into meaningful parts, attributes, and relations.

2k Machine Translation +2

Linguistic communication as (inverse) reward design

no code implementations11 Apr 2022 Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho, Thomas L. Griffiths, Dylan Hadfield-Menell

We then define a pragmatic listener which performs inverse reward design by jointly inferring the speaker's latent horizon and rewards.

Probing BERT's priors with serial reproduction chains

1 code implementation24 Feb 2022 Takateru Yamakoshi, Thomas L. Griffiths, Robert D. Hawkins

Sampling is a promising bottom-up method for exposing what generative models have learned about language, but it remains unclear how to generate representative samples from popular masked language models (MLMs) like BERT.

Language Modelling Masked Language Modeling

A pragmatic account of the weak evidence effect

1 code implementation7 Dec 2021 Samuel A. Barnett, Thomas L. Griffiths, Robert D. Hawkins

Here, we extend recent probabilistic models of recursive social reasoning to allow for persuasive goals and show that our model provides a pragmatic account for why weakly favorable arguments may backfire, a phenomenon known as the weak evidence effect.

Decision Making

Visual resemblance and communicative context constrain the emergence of graphical conventions

1 code implementation17 Sep 2021 Robert D. Hawkins, Megumi Sano, Noah D. Goodman, Judith E. Fan

From photorealistic sketches to schematic diagrams, drawing provides a versatile medium for communicating about the visual world.

Learning to communicate about shared procedural abstractions

1 code implementation30 Jun 2021 William P. McCarthy, Robert D. Hawkins, Haoliang Wang, Cameron Holdaway, Judith E. Fan

Many real-world tasks require agents to coordinate their behavior to achieve shared goals.

Extending rational models of communication from beliefs to actions

1 code implementation25 May 2021 Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho, Thomas L. Griffiths

Speakers communicate to influence their partner's beliefs and shape their actions.

Shades of confusion: Lexical uncertainty modulates ad hoc coordination in an interactive communication task

no code implementations13 May 2021 Sonia K. Murthy, Thomas L. Griffiths, Robert D. Hawkins

There is substantial variability in the expectations that communication partners bring into interactions, creating the potential for misunderstandings.

From partners to populations: A hierarchical Bayesian account of coordination and convention

1 code implementation12 Apr 2021 Robert D. Hawkins, Michael Franke, Michael C. Frank, Adele E. Goldberg, Kenny Smith, Thomas L. Griffiths, Noah D. Goodman

Languages are powerful solutions to coordination problems: they provide stable, shared expectations about how the words we say correspond to the beliefs and intentions in our heads.

Continual Learning

Generalizing meanings from partners to populations: Hierarchical inference supports convention formation on networks

1 code implementation4 Feb 2020 Robert D. Hawkins, Noah D. Goodman, Adele E. Goldberg, Thomas L. Griffiths

A key property of linguistic conventions is that they hold over an entire community of speakers, allowing us to communicate efficiently even with people we have never met before.


Characterizing the dynamics of learning in repeated reference games

1 code implementation16 Dec 2019 Robert D. Hawkins, Michael C. Frank, Noah D. Goodman

The language we use over the course of conversation changes as we establish common ground and learn what our partner finds meaningful.

When redundancy is useful: A Bayesian approach to 'overinformative' referring expressions

1 code implementation19 Mar 2019 Judith Degen, Robert D. Hawkins, Caroline Graf, Elisa Kreiss, Noah D. Goodman

Crucially, we relax the assumption that informativeness is computed with respect to a deterministic Boolean semantics, in favor of a non-deterministic continuous semantics.

Informativeness Specificity

The division of labor in communication: Speakers help listeners account for asymmetries in visual perspective

1 code implementation24 Jul 2018 Robert D. Hawkins, Hyowon Gweon, Noah D. Goodman

In Experiment 1, we manipulated the presence or absence of occlusions in a director-matcher task and found that speakers spontaneously produced more informative descriptions to account for "known unknowns" in their partner's private view.

Known Unknowns Navigate

Cannot find the paper you are looking for? You can Submit a new open access paper.