paper-with-me

Papers

Learning to refer informatively by amortizing pragmatic reasoning

2020-05-31 · Julia White, Jesse Mu, Noah D. Goodman

A hallmark of human language is the ability to effectively and efficiently convey contextually relevant information. One theory for how humans reason about language is presented in the Rational Speech Acts (RSA) framework, which captures pragmatic phenomena via a process of recursive social reasoning (Goodman & Frank, 2016). However, RSA represents ideal reasoning in an unconstrained setting. We explore the idea that speakers might learn to amortize the cost of RSA computation over time by directly optimizing for successful communication with an internal listener model. In simulations with grounded neural speakers and listeners across two communication game datasets representing synthetic and human-generated data, we find that our amortized model is able to quickly generate language that is effective and concise across a range of contexts, without the need for explicit pragmatic reasoning.

📄 PDF Abstract BibTeX arXiv:2006.00418

Code (1)

juliaiwhite/amortized-rsa 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Amortizing Pragmatic Program Synthesis with Rankings

2023-09-01 · Yewen Pu, Saujas Vaduguru, Priyan Vaithilingam, Elena Glassman 외

In program synthesis, an intelligent system takes in a set of user-generated examples and returns a program that is logically consistent with these examples. The usage of Rational Speech Acts (RSA) framework has been suc…

Program Synthesis

Amortizing Pragmatic Program Synthesis with Rankings

2024-06-01 · Yewen Pu, Saujas Vaduguru, Priyan Vaithilingam, Elena Glassman 외

The usage of Rational Speech Acts (RSA) framework has been successful in building \emph{pragmatic} program synthesizers that return programs which, in addition to being logically consistent with user-generated examples, …

Program Synthesis

Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding

2017-03-29 · TACL 2017 1 · Will Monroe, Robert X. D. Hawkins, Noah D. Goodman, Christopher Potts

We present a model of pragmatic referring expression interpretation in a grounded communication task (identifying colors from descriptions) that draws upon predictions from two recurrent neural network classifiers, a spe…

Referring Expression

Learning from Omission

2019-07-01 · ACL 2019 7 · Bill McDowell, Noah Goodman

Pragmatic reasoning allows humans to go beyond the literal meaning when interpret- ing language in context. Previous work has shown that such reasoning can improve the performance of already-trained language understandin…

Understand the Implication: Learning to Think for Pragmatic Understanding

2025-06-16 · Settaluri Lakshmi Sravanthi, Kishan Maharaj, Sravani Gunnu, Abhijit Mishra 외

Pragmatics, the ability to infer meaning beyond literal interpretation, is crucial for social cognition and communication. While LLMs have been benchmarked for their pragmatic understanding, improving their performance r…

Transfer Learning