Pragmatic language interpretation as probabilistic inference

ND Goodman, MC Frank - Trends in cognitive sciences, 2016 - cell.com
Understanding language requires more than the use of fixed conventions and more than
decoding combinatorial structure. Instead, comprehenders make exquisitely sensitive …

The pervasive role of pragmatics in early language

M Bohn, MC Frank - Annual Review of Developmental …, 2019 - annualreviews.org
Language is a fundamentally social endeavor. Pragmatics is the study of how speakers and
listeners use social reasoning to go beyond the literal meanings of words to interpret …

In situ bidirectional human-robot value alignment

L Yuan, X Gao, Z Zheng, M Edmonds, YN Wu… - Science robotics, 2022 - science.org
A prerequisite for social coordination is bidirectional communication between teammates,
each playing two roles simultaneously: as receptive listeners and expressive speakers. For …

Speaker-follower models for vision-and-language navigation

D Fried, R Hu, V Cirik, A Rohrbach… - Advances in neural …, 2018 - proceedings.neurips.cc
Navigation guided by natural language instructions presents a challenging reasoning
problem for instruction followers. Natural language instructions typically identify only a few …

Inherent disagreements in human textual inferences

E Pavlick, T Kwiatkowski - Transactions of the Association for …, 2019 - direct.mit.edu
We analyze human's disagreements about the validity of natural language inferences. We
show that, very often, disagreements are not dismissible as annotation “noise”, but rather …

Learning to ask good questions: Ranking clarification questions using neural expected value of perfect information

S Rao, H Daumé III - arxiv preprint arxiv:1805.04655, 2018 - arxiv.org
Inquiry is fundamental to communication, and machines cannot effectively collaborate with
humans unless they can ask questions. In this work, we build a neural network model for the …

Learning language games through interaction

SI Wang, P Liang, CD Manning - arxiv preprint arxiv:1606.02447, 2016 - arxiv.org
We introduce a new language learning setting relevant to building adaptive natural
language interfaces. It is inspired by Wittgenstein's language games: a human wishes to …

Reasoning about pragmatics with neural listeners and speakers

J Andreas, D Klein - arxiv preprint arxiv:1604.00562, 2016 - arxiv.org
We present a model for pragmatically describing scenes, in which contrastive behavior
results from a combination of inference-driven pragmatics and learned semantics. Like …

Adjectival vagueness in a Bayesian model of interpretation

D Lassiter, ND Goodman - Synthese, 2017 - Springer
We derive a probabilistic account of the vagueness and context-sensitivity of scalar
adjectives from a Bayesian approach to communication and interpretation. We describe an …

Colors in context: A pragmatic neural model for grounded language understanding

W Monroe, RXD Hawkins, ND Goodman… - Transactions of the …, 2017 - direct.mit.edu
We present a model of pragmatic referring expression interpretation in a grounded
communication task (identifying colors from descriptions) that draws upon predictions from …