Many open-domain question answering problems can be cast as a textual entailment task, where a question and candidate answers are concatenated to form hypotheses. A QA system then determines if the supporting knowledge bases, regarded as potential pr
emises, entail the hypotheses. In this paper, we investigate a neural-symbolic QA approach that integrates natural logic reasoning within deep learning architectures, towards developing effective and yet explainable question answering models. The proposed model gradually bridges a hypothesis and candidate premises following natural logic inference steps to build proof paths. Entailment scores between the acquired intermediate hypotheses and candidate premises are measured to determine if a premise entails the hypothesis. As the natural logic reasoning process forms a tree-like, hierarchical structure, we embed hypotheses and premises in a Hyperbolic space rather than Euclidean space to acquire more precise representations. Empirically, our method outperforms prior work on answering multiple-choice science questions, achieving the best results on two publicly available datasets. The natural logic inference process inherently provides evidence to help explain the prediction process.
Document-level relation extraction aims to identify relations between entities in a whole document. Prior efforts to capture long-range dependencies have relied heavily on implicitly powerful representations learned through (graph) neural networks, w
hich makes the model less transparent. To tackle this challenge, in this paper, we propose LogiRE, a novel probabilistic model for document-level relation extraction by learning logic rules. LogiRE treats logic rules as latent variables and consists of two modules: a rule generator and a relation extractor. The rule generator is to generate logic rules potentially contributing to final predictions, and the relation extractor outputs final predictions based on the generated logic rules. Those two modules can be efficiently optimized with the expectation-maximization (EM) algorithm. By introducing logic rules into neural networks, LogiRE can explicitly capture long-range dependencies as well as enjoy better interpretation. Empirical results show that significantly outperforms several strong baselines in terms of relation performance and logical consistency. Our code is available at https://github.com/rudongyu/LogiRE.
Knowledge graphs (KG) have become increasingly important to endow modern recommender systems with the ability to generate traceable reasoning paths to explain the recommendation process. However, prior research rarely considers the faithfulness of th
e derived explanations to justify the decision-making process. To the best of our knowledge, this is the first work that models and evaluates faithfully explainable recommendation under the framework of KG reasoning. Specifically, we propose neural logic reasoning for explainable recommendation (LOGER) by drawing on interpretable logical rules to guide the path-reasoning process for explanation generation. We experiment on three large-scale datasets in the e-commerce domain, demonstrating the effectiveness of our method in delivering high-quality recommendations as well as ascertaining the faithfulness of the derived explanation.
We present a system for learning generalized, stereotypical patterns of events---or schemas''---from natural language stories, and applying them to make predictions about other stories. Our schemas are represented with Episodic Logic, a logical form
that closely mirrors natural language. By beginning with a head start'' set of protoschemas--- schemas that a 1- or 2-year-old child would likely know---we can obtain useful, general world knowledge with very few story examples---often only one or two. Learned schemas can be combined into more complex, composite schemas, and used to make predictions in other stories where only partial information is available.
This paper offer a designed module for buck-boost DC-DC converter, able to solve
unsteady charging voltage problem, due to constant decreasing scale of transformers and
grid or solar panel voltage drop, this module has been designed using fuzzy log
ic in PWM
control and simulated in matlab and all test and its results illustrated the suitable figure.
We present in this paper the neutrosophic exponential distribution,
which is an extension of the classical exponential distribution
according to the neutrosophic logic (a new non-classical logic which
was founded by the American philosopher and ma
thematical
Florentin Smarandache, which he introduced as a generalization of
fuzzy logic especially the intuitionistic fuzzy logic), so that it can
handle all the data that it is not precisely defined.
We present in this paper the neutrosophic randomized variables,
which are a generalization of the classical random variables
obtained from the application of the neutrosophic logic (a new nonclassical
logic which was founded by the American philos
opher and
mathematical Florentin Smarandache, which he introduced as a
generalization of fuzzy logic especially the intuitionistic fuzzy logic )
on classical random variables.
This paper represents a study of all the major and sub influential
factors that affect the process of placing concrete which has
arbitrary nature and has not been stated clearly before; and the
impact of these factors on the cost of a cubic meter of placed
concrete.
In this paper, we will design a Fuzzy Smith Predictor (FSP),
then we will model, simulate and analyze it using colored Fuzzy Petri
networks, then we will compare it with a conventional proportional
integral controller.
The main objective of this
research is to reduce the delay time
of the wind turbine system and to increase its reliability, in the other
side, to improve the response and stability of the operating point of
the mechanical energy and reduce vibration caused by the delay time
in the system.
In the following study we make a simulation of an independent
photovoltaic system connected to an (ohm
- unit of electrical resistance) load which consists of the following
parts:
(Photovoltaic Module - Converter dc- dc - Control system to
track
ing the maximum power point via MATLAB & Simulink
program)
Taking advantage of equations of Photovoltaic Module we chart
the graph and simulate curves of the Module.
We also simulate the converter –type Cuk- which gives higher or
lower voltage than input voltage but with reversed polarity.
We also make a comparison between the two systems tracking:
the first tracker is a traditional one and the second one is a system
in which it uses a fuzzy logic tracker.
The results of the comparison shows different capacities taking into
consideration the varieties of weather conditions of regular solar
radiation as well as the partial shadow.
Such results showed that fuzzy logic has got more capability to
harmonize with all conditions especially in cases of low solar
radiation and partial shadow.
