Filters








33,310 Hits in 4.4 sec

Learning STRIPS Operators from Noisy and Incomplete Observations [article]

Kira Mourao, Luke S. Zettlemoyer, Ronald P. A. Petrick, Mark Steedman
2012 arXiv   pre-print
deriving explicit STRIPS rules from the classifiers' parameters.  ...  Even in standard STRIPS domains, existing approaches cannot learn from noisy, incomplete observations typical of real-world domains.  ...  Our approach depends on decomposing the learning problem into two stages: learning implicit action models and then deriving explicit rules from the implicit models.  ... 
arXiv:1210.4889v1 fatcat:k66lyi4poff6bhdjbll32sedom

A New Vision About AI and Situation Awareness Model of Auto-driving with Implicit Memory

Hang SONG, Bo-han JIANG, Da-xue LIU
2018 DEStech Transactions on Computer Science and Engineering  
Similarly, some skills and knowledge are acquired by implicit learning and this kind of learning show an enormous migration and analogy ability.  ...  This paper is enlightenment by implicit memory, situation awareness model of Ensley's and the way a very young child watching, touching and knowing the objects of the world.  ...  Acknowledgments This work was supported by the grant from Post-Doctoral Foundation of China (P.PHD. 44919).  ... 
doi:10.12783/dtcse/cnai2018/24168 fatcat:jtxrbgsuw5cptafbkrnpehlswa

Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspective [article]

Wen Zhang, Jiaoyan Chen, Juan Li, Zezhong Xu, Jeff Z. Pan, Huajun Chen
2022 arXiv   pre-print
symbolic logic is deterministic, with reasoning results being explainable, while modern embedding-based reasoning can deal with uncertainty and predict plausible knowledge, often with high efficiency via  ...  We first briefly introduce preliminaries, then systematically categorize and discuss works of logic and embedding-aware KG reasoning from different perspectives, and finally conclude and discuss the challenges  ...  Methods mentioned above inject pre-defined rules via regularizing relation embeddings during training. They are specific to KGE methods.  ... 
arXiv:2202.07412v1 fatcat:ou6ioak6affevo4e6sz2mebbvm

Learning from Explicit and Implicit Supervision Jointly For Algebra Word Problems

Shyam Upadhyay, Ming-Wei Chang, Kai-Wei Chang, Wen-tau Yih
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
To leverage the mined dataset, we propose a novel structured-output learning algorithm that aims to learn from both explicit (e.g., equations) and implicit (e.g., solutions) supervision signals jointly  ...  Existing state-of-the-art approaches mainly rely on learning from human annotated equations.  ...  We allow partial matches so that the model can learn from the incomplete implicit signals as well. Prior work has used only 5 explicit supervision examples when training with solutions.  ... 
doi:10.18653/v1/d16-1029 dblp:conf/emnlp/UpadhyayCCY16 fatcat:l6k4uxyki5amvceffgtuvrp274

Learning from Learning Machines: Optimisation, Rules, and Social Norms [article]

Travis LaCroix, Yoshua Bengio
2019 arXiv   pre-print
If this claim is correct, then the recent successes of deep learning for AI suggest that more implicit specifications work better than explicit ones for solving such problems.  ...  There is an analogy between machine learning systems and economic entities in that they are both adaptive, and their behaviour is specified in a more-or-less explicit way.  ...  Instead, they require implicit human judgement and correspond more to implicit rules or principles. 4.3. Example 3: Rules and Principles.  ... 
arXiv:2001.00006v1 fatcat:joduaaf2ufc45bqlwob4vrgkfy

MULTIPLE SYSTEMS OF PERCEPTUAL CATEGORY LEARNING: THEORY AND COGNITIVE TESTS [chapter]

F. GREGORY ASHBY, VIVIAN V. VALENTIN
2005 Handbook of Categorization in Cognitive Science  
TWO CATEGORY-LEARNING TASKS As mentioned above, rule-based tasks are those in which the categories can be learned via some explicit reasoning process.  ...  COVIS As mentioned earlier, COVIS postulates two systems that compete throughout learning -an explicit system that uses logical reasoning and an implicit system that uses a form of procedural learning.  ... 
doi:10.1016/b978-008044612-7/50080-9 fatcat:acxy7wxugbbwjoo6vj2aopoibq

Knowledge Enhanced Event Causality Identification with Mention Masking Generalizations

Jian Liu, Yubo Chen, Jun Zhao
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
, via a mechanism called event mention masking generalization, which can greatly enhance the ability of our model to handle new, previously unseen cases.  ...  In experiments, we evaluate our model on three benchmark datasets and show our model outperforms previous methods by a significant margin.  ...  The second finding comes from the unexpected drop from implicit(substitution) to explicit(substitution).  ... 
doi:10.24963/ijcai.2020/495 dblp:conf/ijcai/LiuCGLZZ20 fatcat:3rnwk3jh6rhhjevikgmy4ygmaa

Differentiable Reasoning on Large Knowledge Bases and Natural Language

Pasquale Minervini, Matko Bošnjak, Tim Rocktäschel, Sebastian Riedel, Edward Grefenstette
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
General neural architectures that jointly learn representations and transformations of text are very data-inefficient, and it is hard to analyse their reasoning process.  ...  Then, we propose a novel approach for jointly reasoning over KBs and textual mentions, by embedding logic facts and natural language sentences in a shared embedding space.  ...  We can see that, even without providing any rule to the model, GNTPs yields better ranking results in comparison with neural link prediction models-since it is able to learn such rules from data-and it  ... 
doi:10.1609/aaai.v34i04.5962 fatcat:5huq7nj3fnbdla2xdfs7vsiwsq

Ranking of Potential Questions

Luise Schricker, Tatjana Scheffler
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop  
In the present study, a system for ranking explicit and implicit questions by their appropriateness in a dialogue is presented.  ...  One linguistic theory, the Questions Under Discussion model, takes question structures as integral to the functioning of a coherent discourse.  ...  Acknowledgements We would like to thank the participants of the 2018 University of Potsdam class Questions and Models of Discourse for annotating the interview segments that were used as test data.  ... 
doi:10.18653/v1/p19-2019 dblp:conf/acl/SchrickerS19 fatcat:e3ira22qjvgrtoejinnaiibbxi

Learning Embedding Representations for Knowledge Inference on Imperfect and Incomplete Repositories [article]

Miao Fan, Qiang Zhou, Thomas Fang Zheng
2015 arXiv   pre-print
We propose IIKE (Imperfect and Incomplete Knowledge Embedding), a probabilistic model which measures the probability of each belief, i.e. 〈 h,r,t〉, in large-scale knowledge bases such as NELL and Freebase  ...  by machine learning (NELL) or crowdsouring (Freebase), so that we can use || h + r - t|| to assess the plausibility of a belief when conducting inference.  ...  N-FOIL [Quinlan and Cameron-Jones, 1993] learns first order Horn clause rules to infer new beliefs from the known ones. So far, it has helped to learn approximately 600 such rules.  ... 
arXiv:1503.08155v1 fatcat:3lxeq6n2rva7tgyrkdc2siz3gq

Psychologically realistic cognitive agents: taking human cognition seriously

Ron Sun, Sébastien Hélie
2013 Journal of experimental and theoretical artificial intelligence (Print)  
In cognitive architectures, this can result not only from the number of modules (as explained above), but also from the complexity of within-module processing.  ...  CLARION assumes the distinction between explicit and implicit knowledge, as well as the distinction of actioncentered and non-action-centered knowledge.  ...  Acknowledgments This research was supported in part by the Army Research Institute grant W74V8H-05-K-0002 and the Office of Naval Research grant N00014-08-1-0068, as well as by a postdoctoral research fellowship from  ... 
doi:10.1080/0952813x.2012.661236 fatcat:x5dsbwnfnffi7ifbv2naxxq664

Differentiable Reasoning on Large Knowledge Bases and Natural Language [article]

Pasquale Minervini, Matko Bošnjak, Tim Rocktäschel, Sebastian Riedel, Edward Grefenstette
2019 arXiv   pre-print
General neural architectures that jointly learn representations and transformations of text are very data-inefficient, and it is hard to analyse their reasoning process.  ...  Then, we propose a novel approach for jointly reasoning over KBs and textual mentions, by embedding logic facts and natural language sentences in a shared embedding space.  ...  We can see that, even without providing any rule to the model, GNTPs yields better ranking results in comparison with neural link prediction models-since it is able to learn such rules from data-and it  ... 
arXiv:1912.10824v1 fatcat:cttiq66w7jdzln6d7kakx7vdlm

Complex Cognitive Systems and Their Unconscious. Related Inspired Conjectures for Artificial Intelligence

Gianfranco Minati
2020 Future Internet  
Examples of expected features are the ability to combine current and unconscious links to perform cognitive processing such as representing, deciding, memorizing, and solving equivalencies, and also learning  ...  We elaborate on the artificial unconscious as an implicit, usage-dependent, self-profiling, and emergent process.  ...  Ruled activities do not fully use cognitive resources and support implicit, parasitic, i.e., not explicitly allowed activities.  ... 
doi:10.3390/fi12120213 fatcat:nigflctj5fa75ho7rqikyujgeq

The Interaction of the Explicit and the Implicit in Skill Learning: A Dual-Process Approach

Ron Sun, Paul Slusarz, Chris Terry
2005 Psychological review  
The authors argue for an integrated model of skill learning that takes into account both implicit and explicit processes.  ...  Moreover, they argue for a bottom-up approach (first learning implicit knowledge and then explicit knowledge) in the integrated model.  ...  Nonconnectionist Modeling of Skill Learning Tasks As mentioned before, Ling and Marinov (1994) simulated the data from Lewicki et al. (1987) , using a decision tree learning algorithm (i.e., C4.5).  ... 
doi:10.1037/0033-295x.112.1.159 pmid:15631592 fatcat:3plqlscbvfhi7mt24rhkqxzeoi

How Far are We from Effective Context Modeling? An Exploratory Study on Semantic Parsing in Context [article]

Qian Liu, Bei Chen, Jiaqi Guo, Jian-Guang Lou, Bin Zhou, Dongmei Zhang
2020 arXiv   pre-print
We evaluate 13 context modeling methods on two large complex cross-domain datasets, and our best model achieves state-of-the-art performances on both datasets with significant improvements.  ...  We present a grammar-based decoding semantic parser and adapt typical context modeling methods on top of it.  ...  For each schema-agnostic grammar rule, φ y returns a learned embedding.  ... 
arXiv:2002.00652v2 fatcat:6fpcduylvvhtfbinjwhsnqsylu
« Previous Showing results 1 — 15 out of 33,310 results