Recursive Rules with Aggregation: A Simple Unified Semantics
- URL: http://arxiv.org/abs/2007.13053v3
- Date: Wed, 21 Sep 2022 13:39:44 GMT
- Title: Recursive Rules with Aggregation: A Simple Unified Semantics
- Authors: Yanhong A. Liu and Scott D. Stoller
- Abstract summary: This paper describes a unified semantics for recursion with aggregation.
We present a formal definition of the semantics, prove important properties of the semantics, and compare with prior semantics.
We show that our semantics is simple and matches the desired results in all cases.
- Score: 0.6662800021628273
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Complex reasoning problems are most clearly and easily specified using
logical rules, but require recursive rules with aggregation such as count and
sum for practical applications. Unfortunately, the meaning of such rules has
been a significant challenge, leading to many disagreeing semantics.
This paper describes a unified semantics for recursive rules with
aggregation, extending the unified founded semantics and constraint semantics
for recursive rules with negation. The key idea is to support simple expression
of the different assumptions underlying different semantics, and orthogonally
interpret aggregation operations using their simple usual meaning. We present a
formal definition of the semantics, prove important properties of the
semantics, and compare with prior semantics. In particular, we present an
efficient inference over aggregation that gives precise answers to all examples
we have studied from the literature. We also apply our semantics to a wide
range of challenging examples, and show that our semantics is simple and
matches the desired results in all cases. Finally, we describe experiments on
the most challenging examples, exhibiting unexpectedly superior performance
over well-known systems when they can compute correct answers.
Related papers
- Revisiting Vacuous Reduct Semantics for Abstract Argumentation (Extended Version) [8.010966370223985]
We consider the notion of a vacuous reduct semantics for abstract argumentation frameworks.
We give a systematic overview on vacuous reduct semantics resulting from combining different admissibility-based and conflict-free semantics.
arXiv Detail & Related papers (2024-08-26T07:50:49Z) - SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding [52.98133831401225]
Temporal grounding, also known as video moment retrieval, aims at locating video segments corresponding to a given query sentence.
We propose a large language model-driven method for negative query construction, utilizing GPT-3.5-Turbo.
We introduce a coarse-to-fine saliency ranking strategy, which encourages the model to learn the multi-granularity semantic relationships between videos and hierarchical negative queries.
arXiv Detail & Related papers (2024-07-06T16:08:17Z) - Superlatives in Context: Modeling the Implicit Semantics of Superlatives [31.063753498947346]
Superlatives are used to single out elements with a maximal/minimal property.
Superlatives provide an ideal phenomenon for studying implicit phenomena and discourse restrictions.
We show that the fine-grained semantics of superlatives in context can be challenging for contemporary models.
arXiv Detail & Related papers (2024-05-31T16:14:06Z) - A Unified View on Forgetting and Strong Equivalence Notions in Answer
Set Programming [14.342696862884704]
We introduce a novel relativized equivalence notion, which is able to capture all related notions from the literature.
We then introduce an operator that combines projection and a relaxation of (SP)-forgetting to obtain the relativized simplifications.
arXiv Detail & Related papers (2023-12-13T09:05:48Z) - A Hybrid System for Systematic Generalization in Simple Arithmetic
Problems [70.91780996370326]
We propose a hybrid system capable of solving arithmetic problems that require compositional and systematic reasoning over sequences of symbols.
We show that the proposed system can accurately solve nested arithmetical expressions even when trained only on a subset including the simplest cases.
arXiv Detail & Related papers (2023-06-29T18:35:41Z) - Semantic-aware Contrastive Learning for More Accurate Semantic Parsing [32.74456368167872]
We propose a semantic-aware contrastive learning algorithm, which can learn to distinguish fine-grained meaning representations.
Experiments on two standard datasets show that our approach achieves significant improvements over MLE baselines.
arXiv Detail & Related papers (2023-01-19T07:04:32Z) - On the Complexity of Representation Learning in Contextual Linear
Bandits [110.84649234726442]
We show that representation learning is fundamentally more complex than linear bandits.
In particular, learning with a given set of representations is never simpler than learning with the worst realizable representation in the set.
arXiv Detail & Related papers (2022-12-19T13:08:58Z) - Synergies between Disentanglement and Sparsity: Generalization and
Identifiability in Multi-Task Learning [79.83792914684985]
We prove a new identifiability result that provides conditions under which maximally sparse base-predictors yield disentangled representations.
Motivated by this theoretical result, we propose a practical approach to learn disentangled representations based on a sparsity-promoting bi-level optimization problem.
arXiv Detail & Related papers (2022-11-26T21:02:09Z) - On graded semantics of abstract argumentation: Extension-based case [0.0]
This paper considers some issues on extension-based semantics for abstract argumentation framework (AAF)
An alternative fundamental lemma is given, which generalizes the corresponding result obtained in [1].
A number of fundamental semantics for AAF, including conflict-free, admissible, complete and stable semantics, are shown to be closed under reduced meet modulo an ultrafilter.
arXiv Detail & Related papers (2020-12-19T04:32:19Z) - Compositional Generalization via Semantic Tagging [81.24269148865555]
We propose a new decoding framework that preserves the expressivity and generality of sequence-to-sequence models.
We show that the proposed approach consistently improves compositional generalization across model architectures, domains, and semantic formalisms.
arXiv Detail & Related papers (2020-10-22T15:55:15Z) - Syn-QG: Syntactic and Shallow Semantic Rules for Question Generation [49.671882751569534]
We develop SynQG, a set of transparent syntactic rules which transform declarative sentences into question-answer pairs.
We utilize PropBank argument descriptions and VerbNet state predicates to incorporate shallow semantic content.
In order to improve syntactic fluency and eliminate grammatically incorrect questions, we employ back-translation over the output of these syntactic rules.
arXiv Detail & Related papers (2020-04-18T19:57:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.