Neuro-symbolic artificial intelligence: The state of the art
Neuro-symbolic AI is an emerging subfield of Artificial Intelligence that brings together two
hitherto distinct approaches.” Neuro” refers to the artificial neural networks prominent in …
hitherto distinct approaches.” Neuro” refers to the artificial neural networks prominent in …
From word models to world models: Translating from natural language to the probabilistic language of thought
How does language inform our downstream thinking? In particular, how do humans make
meaning from language--and how can we leverage a theory of linguistic meaning to build …
meaning from language--and how can we leverage a theory of linguistic meaning to build …
Symbolic logic meets machine learning: A brief survey in infinite domains
V Belle - International conference on scalable uncertainty …, 2020 - Springer
The tension between deduction and induction is perhaps the most fundamental issue in
areas such as philosophy, cognition and artificial intelligence (AI). The deduction camp …
areas such as philosophy, cognition and artificial intelligence (AI). The deduction camp …
The gap of semantic parsing: A survey on automatic math word problem solvers
Solving mathematical word problems (MWPs) automatically is challenging, primarily due to
the semantic gap between human-readable words and machine-understandable logics …
the semantic gap between human-readable words and machine-understandable logics …
Text2math: End-to-end parsing text into math expressions
Y Zou, W Lu - arXiv preprint arXiv:1910.06571, 2019 - arxiv.org
We propose Text2Math, a model for semantically parsing text into math expressions. The
model can be used to solve different math related problems including arithmetic word …
model can be used to solve different math related problems including arithmetic word …
[PDF][PDF] Logic meets Probability: Towards Explainable AI Systems for Uncertain Worlds.
V Belle - IJCAI, 2017 - ijcai.org
Logical AI is concerned with formal languages to represent and reason with qualitative
specifications; statistical AI is concerned with learning quantitative specifications from data …
specifications; statistical AI is concerned with learning quantitative specifications from data …
Semirings for probabilistic and neuro-symbolic logic programming
The field of probabilistic logic programming (PLP) focuses on integrating probabilistic
models into programming languages based on logic. Over the past 30 years, numerous …
models into programming languages based on logic. Over the past 30 years, numerous …
Why are nlp models fumbling at elementary math? a survey of deep learning based word problem solvers
From the latter half of the last decade, there has been a growing interest in developing
algorithms for automatically solving mathematical word problems (MWP). It is a challenging …
algorithms for automatically solving mathematical word problems (MWP). It is a challenging …
SemEval-2019 task 10: math question answering
We report on the SemEval 2019 task on math question answering. We provided a question
set derived from Math SAT practice exams, including 2778 training questions and 1082 test …
set derived from Math SAT practice exams, including 2778 training questions and 1082 test …
Logic meets learning: From aristotle to neural networks
V Belle - Neuro-symbolic artificial intelligence: The state of the …, 2021 - ebooks.iospress.nl
The tension between deduction and induction is perhaps the most fundamental issue in
areas such as philosophy, cognition and artificial intelligence. In this chapter, we survey …
areas such as philosophy, cognition and artificial intelligence. In this chapter, we survey …