About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Peter Clark
- sl:arxiv_num : 2002.05867
- sl:arxiv_published : 2020-02-14T04:23:28Z
- sl:arxiv_summary : AI has long pursued the goal of having systems reason over *explicitly
provided* knowledge, but building suitable representations has proved
challenging. Here we explore whether transformers can similarly learn to reason
(or emulate reasoning), but using rules expressed in language, thus bypassing a
formal representation. We provide the first demonstration that this is
possible, and characterize the extent of this capability. To do this, we use a
collection of synthetic datasets that test increasing levels of reasoning
complexity (number of rules, presence of negation, and depth of chaining). We
find transformers appear to learn rule-based reasoning with high (99%) accuracy
on these datasets, and in a way that generalizes to test data requiring
substantially deeper chaining than in the training data (95%+ scores). We also
demonstrate that the models transfer well to two hand-authored rulebases, and
to rulebases paraphrased into more natural language. These findings are
significant as it suggests a new role for transformers, namely as a limited
\"soft theorem prover\" operating over explicit theories in language. This in
turn suggests new possibilities for explainability, correctability, and
counterfactual reasoning in question-answering. All datasets and a live demo
are available at http://rule-reasoning.apps.allenai.org/@en
- sl:arxiv_title : Transformers as Soft Reasoners over Language@en
- sl:arxiv_updated : 2020-02-14T04:23:28Z
- sl:bookmarkOf : https://arxiv.org/abs/2002.05867
- sl:creationDate : 2020-02-17
- sl:creationTime : 2020-02-17T09:06:44Z
Documents with similar tags (experimental)