Pragmatic language interpretation as probabilistic inference
Understanding language requires more than the use of fixed conventions and more than
decoding combinatorial structure. Instead, comprehenders make exquisitely sensitive …
decoding combinatorial structure. Instead, comprehenders make exquisitely sensitive …
The pervasive role of pragmatics in early language
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 …
listeners use social reasoning to go beyond the literal meanings of words to interpret …
In situ bidirectional human-robot value alignment
A prerequisite for social coordination is bidirectional communication between teammates,
each playing two roles simultaneously: as receptive listeners and expressive speakers. For …
each playing two roles simultaneously: as receptive listeners and expressive speakers. For …
Speaker-follower models for vision-and-language navigation
Navigation guided by natural language instructions presents a challenging reasoning
problem for instruction followers. Natural language instructions typically identify only a few …
problem for instruction followers. Natural language instructions typically identify only a few …
Inherent disagreements in human textual inferences
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 …
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
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 …
humans unless they can ask questions. In this work, we build a neural network model for the …
Learning language games through interaction
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 …
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 …
results from a combination of inference-driven pragmatics and learned semantics. Like …
Adjectival vagueness in a Bayesian model of interpretation
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 …
adjectives from a Bayesian approach to communication and interpretation. We describe an …
Colors in context: A pragmatic neural model for grounded language understanding
We present a model of pragmatic referring expression interpretation in a grounded
communication task (identifying colors from descriptions) that draws upon predictions from …
communication task (identifying colors from descriptions) that draws upon predictions from …