Filters








63,921 Hits in 4.2 sec

Answer Validation Through Robust Logical Inference [chapter]

Ingo Glöckner
2007 Lecture Notes in Computer Science  
The paper features MAVE, a knowledge-based system for answer validation through deep linguistic processing and logical inference.  ...  A relaxation loop is used to determine a robust indicator of logical entailment.  ...  The goal was that of showing that deep NLP and logical inference (plus relaxation) are robust enough to handle the validation task successfully. 2 System description 2.1 Overview of MAVE A validation candidate  ... 
doi:10.1007/978-3-540-74999-8_62 fatcat:7aozhdcjgravplrnrkbqp22rh4

Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations [article]

Jaehun Jung, Lianhui Qin, Sean Welleck, Faeze Brahman, Chandra Bhagavatula, Ronan Le Bras, Yejin Choi
2022 arXiv   pre-print
We also show that Maieutic Prompting improves robustness in inference while providing interpretable rationales.  ...  In this work, we develop Maieutic Prompting, which infers a correct answer to a question even from the noisy and inconsistent generations of LM.  ...  Given Q, we first generate E T and E F , then validate whether each of these explanations is logically integral.  ... 
arXiv:2205.11822v1 fatcat:2l5fyuuukrhsfib7cjmzuubgru

Flexible Generation of Natural Language Deductions [article]

Kaj Bostrom, Xinyu Zhao, Swarat Chaudhuri, Greg Durrett
2021 arXiv   pre-print
., 2020) to generate the result of applying a particular logical operation to one or more premise statements.  ...  In this paper, we describe ParaPattern, a method for building models to generate deductive inferences from diverse natural language inputs without direct human supervision.  ...  Through experiments on manually-constructed English perturbation sets, as well as on the English Question Answering via Sentence Composition (QASC) and EntailmentBank datasets (Khot et al., 2020; , we  ... 
arXiv:2104.08825v2 fatcat:b4dy552stja33pqqcpahxmkokq

Conflict Detection and Logical Complexity

Janie Brisson, Walter Schaeken, Henry Markovits, Wim De Neys
2018 Psychologica Belgica  
In two studies, we investigate the boundary conditions of these logical intuitions by manipulating the logical complexity of problems where logical validity and conclusion believability conflict or not  ...  The boundaries of logical intuition might thus reside in problems of greater complexity than these inferences.  ...  Valid inferences.  ... 
doi:10.5334/pb.448 pmid:30524748 pmcid:PMC6266877 fatcat:kbiwjvwijvc53gh6f4dhetha6u

From LSAT: The Progress and Challenges of Complex Reasoning [article]

Siyuan Wang, Zhongkun Liu, Wanjun Zhong, Ming Zhou, Zhongyu Wei, Zhumin Chen, Nan Duan
2021 arXiv   pre-print
Complex reasoning aims to draw a correct inference based on complex rules.  ...  As a hallmark of human intelligence, it involves a degree of explicit reading comprehension, interpretation of logical knowledge and complex rule application.  ...  to encode the inferred logic for answer prediction.  ... 
arXiv:2108.00648v1 fatcat:q6oy5rzbs5dcfc2cdkrslhmmpi

GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering

Drew A. Hudson, Christopher D. Manning
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
We use the programs to gain tight control over the answer distribution and present a new tunable smoothing technique to mitigate question biases.  ...  We introduce GQA, a new dataset for real-world visual reasoning and compositional question answering, seeking to address key shortcomings of previous VQA datasets.  ...  ; (4) logical which involve logical inference, and (5) compare for comparison questions between two or more objects.  ... 
doi:10.1109/cvpr.2019.00686 dblp:conf/cvpr/HudsonM19 fatcat:qvdofh4xijcmtpw3rmiajoq3m4

VQA-LOL: Visual Question Answering under the Lens of Logic [article]

Tejas Gokhale, Pratyay Banerjee, Chitta Baral, Yezhou Yang
2020 arXiv   pre-print
the answers of the component questions and the composed question are consistent with the inferred logical operation.  ...  We suggest this work as a move towards robustness by embedding logical connectives in visual understanding.  ...  Acknowledgments Support from NSF Robust Intelligence Program (1816039 and 1750082), DARPA (W911NF2020006) and ONR (N00014-20-1-2332) is gratefully acknowledged.  ... 
arXiv:2002.08325v2 fatcat:dft3d4x7cjccdk4luspbcuf7ga

Keystones

Andres Molina-Markham, Joseph J. Rushanan
2020 Notices of the American Mathematical Society  
Answering these questions requires logic, statistical methods, theory of algorithms, and advanced programming language concepts.  ...  behavior of a system to designing robust protection mechanisms and Bayesian inference engines needed to estimate trust.  ...  This rate is available for five continuous years as you transition through your early career.  ... 
doi:10.1090/noti2081 fatcat:3gtyctc7mvcylikzpx2koxtiqy

Low-Latency Asynchronous Logic Design for Inference at the Edge [article]

Adrian Wheeldon, Alex Yakovlev, Rishad Shafik, Jordan Morris
2020 arXiv   pre-print
Robustness of the proposed circuit is proven through post-synthesis simulation with 0.25 V to 1.2 V supply.  ...  Commonly known as inference at-the-edge, this gives many benefits to the users, including personalization and security. However, such applications demand high energy efficiency and robustness.  ...  If e 2m (resp. e 2m+1 ) is logic-0 (ie. the feature input should be included in the clause calculation), the value of f m (resp. f m ) is passed through to the AND gate to be evaluated.  ... 
arXiv:2012.03402v1 fatcat:cbwqyaya4rhoriaimxeepsavja

Fuzzy Control of a Servomechanism: Practical Approach using Mamdani and Takagi- Sugeno Controllers

Renato Aguiar, Izabella Sirqueira
2021 International Journal of Fuzzy Logic Systems  
The main objective of this work is to propose two fuzzy controllers: one based on the Mamdani inference method and another controller based on the Takagi- Sugeno inference method, both will be designed  ...  has more robustness and precision when compared to the Mamdani inference method.  ...  with Mamdani inference method Here, the control based on Takagi-Sugeno inference method shown more robustness and better relative stability.  ... 
doi:10.5121/ijfls.2021.11402 fatcat:ots4gunmkvg33cj7njyj2dkzra

CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text

Koustuv Sinha, Shagun Sodhani, Jin Dong, Joelle Pineau, William L. Hamilton
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
Motivated by classic work on inductive logic programming, CLUTRR requires that an NLU system infer kinship relations between characters in short stories.  ...  Successful performance on this task requires both extracting relationships between entities, as well as inferring the logical rules governing these relationships.  ...  Ideally, we want language understanding systems that can not only answer questions and draw inferences from text, but that can also do so in a systematic, logical, and robust way.  ... 
doi:10.18653/v1/d19-1458 dblp:conf/emnlp/SinhaSDPH19 fatcat:44vymkqd35fzjjeups5hv3liqa

From Conceptual Content in Big Apes and AI, to the Classical Principle of Explosion: An Interview with Robert B. Brandom [Del contenido conceptual en los grandes monos e IA, hasta el principio de explosión clásico: una entrevista con Robert B. Brandom]

María José Frápolli, Kurt Wischin
2019 Zenodo  
Philosophy of Logic.  ...  Brandom answered ten detailed questions about his philosophy of Rational Pragmatism and Semantic Expressivism, grouped into four topics. 1. Metaphysics and Anthropology, 2.  ...  The distinction between logically valid reasoning and reasoning that is not logically valid does not come up for ground level material inferences.  ... 
doi:10.5281/zenodo.2642445 fatcat:dd3cfto4wbb2pbgbefdil7jtgi

From Conceptual Content in Big Apes and AI, to the Classical Principle of Explosion: An Interview with Robert B. Brandom [Del contenido conceptual en los grandes monos e IA, hasta el principio de explosión clásico: una entrevista con Robert B. Brandom]

María José Frápolli, Kurt Wischin
2019 Zenodo  
Philosophy of Logic.  ...  Brandom answered ten detailed questions about his philosophy of Rational Pragmatism and Semantic Expressivism, grouped into four topics. 1. Metaphysics and Anthropology, 2.  ...  The distinction between logically valid reasoning and reasoning that is not logically valid does not come up for ground level material inferences.  ... 
doi:10.5281/zenodo.4615726 fatcat:wymmj755lzfoxnd46gwgggdhn4

ExtrAns: Extracting answers from technical texts

D. Molla, R. Schwitter, F. Rinaldi, J. Dowdall, M. Hess
2003 IEEE Intelligent Systems  
ExtrAns uses robust natural language processing technology and a semantic representation for information's propositional content.  ...  Answer extraction is a new technology that helps users find precise answers to their questions in technical documents.  ...  Inferences Extracting answers sometimes requires that a system make inferences.  ... 
doi:10.1109/mis.2003.1217623 fatcat:ccdxqp7vfbbobm6haefpwvw4vq

Increased scientific rigor will improve reliability of research and effectiveness of management

Sarah N. Sells, Sarah B. Bassing, Kristin J. Barker, Shannon C. Forshee, Allison C. Keever, James W. Goerz, Michael S. Mitchell
2018 Journal of Wildlife Management  
Such research also draws inferences that are robust to idiosyncratic observations and unavoidable human biases.  ...  To evaluate the prevalence of scientific rigor in wildlife research, we examined 24 issues of the Journal of Wildlife Management from August 2013 through July 2016.  ...  Conclusions reached through inductive logic represent generalizations inferred from specific observations, whereas those reached through deductive logic represent specific predictions derived from general  ... 
doi:10.1002/jwmg.21413 fatcat:ekmjzhoetvhfpkafaspffavfpy
« Previous Showing results 1 — 15 out of 63,921 results