A Generative Symbolic Model for More General Natural Language Understanding and Reasoning
release_ydjc4rzzkbbhlnnrod2obqzqdq
by
Abulhair Saparov, Tom M. Mitchell
2021
Abstract
We present a new fully-symbolic Bayesian model of semantic parsing and
reasoning which we hope to be the first step in a research program toward more
domain- and task-general NLU and AI. Humans create internal mental models of
their observations which greatly aid in their ability to understand and reason
about a large variety of problems. We aim to capture this in our model, which
is fully interpretable and Bayesian, designed specifically with generality in
mind, and therefore provides a clearer path for future research to expand its
capabilities. We derive and implement an inference algorithm, and evaluate it
on an out-of-domain ProofWriter question-answering/reasoning task, achieving
zero-shot accuracies of 100% and 93.43%, depending on the experimental setting,
thereby demonstrating its value as a proof-of-concept.
In text/plain
format
Archived Files and Locations
application/pdf 511.6 kB
file_wkirgvi7jfbpbj3hxyoxifvqyi
|
arxiv.org (repository) web.archive.org (webarchive) |
2105.02486v1
access all versions, variants, and formats of this works (eg, pre-prints)