629,338 Hits in 4.4 sec


2006 Mathematical Logic in Asia  
We primarily concentrate on learning using (1) carefully chosen finite negative data (2) negative counterexamples provided when conjectures contain data not in the target language (3) negative counterexamples  ...  obtained from a teacher (formally, oracle), when a learner queries the oracle if an hypothesis is contained in the target language.  ...  Some Notions from Language Learning We now consider some basic notions in language learning. Following definition gives the concepts of data that is presented to a learner.  ... 
doi:10.1142/9789812772749_0008 fatcat:vmp4mijsnjd2lkjhwij26iimfm

Inductive Logic Programming: Issues, results and the challenge of Learning Language in Logic

Stephen Muggleton
1999 Artificial Intelligence  
The area of Learning Language in Logic (LLL) is producing a number of challenges to existing ILP theory and implementations.  ...  In the natural language area ILP has not only been shown to have higher accuracies than various other ML approaches in learning the past tense of English but also shown to be capable of learning accurate  ...  Acknowledgements The author would like to thank the following people who collaborated on research described in this paper: Mike Sternberg, Steve Pulman, Donald Michie, David Haussler, Ross King, David  ... 
doi:10.1016/s0004-3702(99)00067-3 fatcat:6fbihina7zba3neogm7knq45qe

KILLE: learning grounded language through interaction

Simon Dobnik, Erik de Graaf
2017 European Summer School in Logic, Language and Information  
We present our system called KILLE and provide a proof-ofconcept evaluation of interactive situated learning of object categories and spatial relations.  ...  Processing language in interaction also presents challenges from the computational perspective as it is often not trivial to employ existing language technology tools and (machine learning) algorithms,  ...  To address both issues we have developed a framework for situated agents that learn grounded language incrementally and online with a help of human tutor called KILLE 3 (Kinect Is Learning LanguagE).  ... 
dblp:conf/esslli/DobnikG17 fatcat:v4ylijqaaffppcqtojwduy4enu

A Declarative Modeling Language for Concept Learning in Description Logics [chapter]

Francesca Alessandra Lisi
2013 Lecture Notes in Computer Science  
Learning in Description Logics (DLs) has been paid increasing attention over the last decade.  ...  In this paper we present a declarative modeling language for Concept Learning in DLs which relies on recent results in the fields of Knowledge Representation and Machine Learning.  ...  Acknowledgements The author would like to thank Luc De Raedt for the fruitful discussion on the open issues of declarative modeling for ML/DM, not only in general but also in the specific case of interest  ... 
doi:10.1007/978-3-642-38812-5_11 fatcat:lzctzmztybch3bopzrxhrlqp4y

Modality: logic, semantics, annotation and machine learning

Annie Zaenen
2016 Linguistic Issues in Language Technology  
Up to rather recently Natural Language Processing has not given much attention to modality.  ...  As long as the main task was to determined what a text was about (Information Retrieval) or who the participants in an eventuality were (Information Extraction), this neglect was understandable.  ...  This makes it possible to exploit translations as a means to disambiguate modal verbs in one language via the sense of a modal expression in another language for which there are parallel corpora.  ... 
doi:10.33011/lilt.v14i.1393 fatcat:2cse6e5qejah3od4adrjqltcua

Feature economy vs. logical complexity in phonological pattern learning

Klaas T. Seinhorst
2017 Language Sciences  
In a learning experiment, participants acquired data sets that varied in feature economy and logical complexity.  ...  inventories in spoken language.  ...  Conclusion and discussion In a learning experiment, the roles of two measures of complexity in language acquisition were probed: feature economy and logical complexity.  ... 
doi:10.1016/j.langsci.2016.10.002 fatcat:udyl4vc5bjdzzikru5wrio4y74

Learning Regular Languages over Large Ordered Alphabets

Irini-Eleftheria Mens, Oded Maler, Erika Abraham
2015 Logical Methods in Computer Science  
We then extend Angluin's L* algorithm for learning regular languages from examples for such automata.  ...  We sketch the extension of the algorithm to a class of languages over partially ordered alphabets.  ...  Learning Languages over Ordered Alphabets In this section we present a symbolic learning algorithm starting with an intuitive verbal description.  ... 
doi:10.2168/lmcs-11(3:13)2015 fatcat:ttup7brkczfafku3ptwvjuxiju

The Effectiveness of Language Used in E-Learning Courses

Agnieszka Przygoda
2017 Studies in Logic, Grammar and Rhetoric  
The notion of language in e-Learning is still not very clear from a technical as well as semantic point of view.  ...  With a laptop, a mobile device and Wi-Fi, you can manage your own e-Learning course, and take courses yourself, at any time and place, in any language.  ...  This stage of "learning by doing" was described by Castells (2003) . Castells shows that the Internet is a communication medium with its own logic and its own language.  ... 
doi:10.1515/slgr-2017-0051 fatcat:onv2syo5hjej5aafcfoiclcra4

Fuzzy Logic Based Teaching/Learning of a Foreign Language in Multilingual Situations

2017 Acta Linguistica Asiatica  
A multilingual situation poses a similar challenge for a language teacher/learner where languages exist in continuum.  ...  The concept of Fuzzy Logic (FL) has gained momentum in areas of artificial intelligence and allied researches because of its absolute ability to present efficient solutions to real life problems.  ...  This paper tries to advocate the adoption of a very revolutionary approach of Fuzzy Logic in the teaching/ learning of languages.  ... 
doi:10.4312/ala.7.2.71-84 fatcat:e7qcsziupje53gfa3etq3emax4

Bidirectional Optimization from Reasoning and Learning in Games

Michael Franke, Gerhard Jäger
2011 Journal of Logic, Language and Information  
reasoning and once in a model of reinforcement learning.  ...  sufficient conditions for equivalence of bidirectional optimality and the former, and show based on numerical simulations that bidirectional optimization may be thought of as a process of reinforcement learning  ...  The cumulative definition of biot has in fact a strong affinity to the ibr logic.  ... 
doi:10.1007/s10849-011-9151-z fatcat:wj7neeboijbhpgsudtbexfluda


Ljubica Kordić, Vesna Cigan
2013 Studies in Logic, Grammar and Rhetoric  
In accordance with the Bologna Declaration, modern languages and communication skills have a growing importance in all professions.  ...  First, the status of foreign languages for specific purposes (FLSP) in the Higher Education System of the Republic of Croatia in general is analyzed.  ...  By this approach, Content and Language Integrated Learning (CLIL) in the field of law represents a way of learning which "is improved through increased motivation and the study of natural language seen  ... 
doi:10.2478/slgr-2013-0019 fatcat:dlxrxqdxmzcz5hbaequxv3kshi

A First-Order-Logic Based Model for Grounded Language Learning [chapter]

Leonor Becerra-Bonache, Hendrik Blockeel, María Galván, François Jacquenet
2015 Lecture Notes in Computer Science  
Much is still unknown about how children learn language, but it is clear that they perform "grounded" language learning: they learn the grammar and vocabulary not just from examples of sentences, but from  ...  We propose a simple model for this task that uses first-order logic representations for contexts and meanings, including a simple incremental learning algorithm.  ...  In this paper, we propose a model for grounded language learning that uses a first-order logic representation of contexts and meanings.  ... 
doi:10.1007/978-3-319-24465-5_5 fatcat:wmf5ooj5m5echi3sg7hhzzzkka

Learning to Automatically Solve Logic Grid Puzzles

Arindam Mitra, Chitta Baral
2015 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing  
This is the first learning system that can solve logic grid puzzles described in natural language in a fully automated manner.  ...  Logic grid puzzle is a genre of logic puzzles in which we are given (in a natural language) a scenario, the object to be deduced and certain clues.  ...  for learning to automatically translate a logic problem described in natural language to its ASP counterpart.  ... 
doi:10.18653/v1/d15-1118 dblp:conf/emnlp/MitraB15 fatcat:irnjau44xrhg3mezm4vprghzky

Learning Distributions over Logical Forms for Referring Expression Generation

Nicholas FitzGerald, Yoav Artzi, Luke S. Zettlemoyer
2013 Conference on Empirical Methods in Natural Language Processing  
We present a new approach to referring expression generation, casting it as a density estimation problem where the goal is to learn distributions over logical expressions identifying sets of objects in  ...  This learning is enabled by a new, multi-stage approximate inference technique that uses a pruning model to construct only the most likely logical forms.  ...  Acknowledgements This research was supported in part by the Intel Science and Technology Center for Pervasive Computing, by DARPA under the DEFT program through the AFRL (FA8750-13-2-0019) and the CSSG  ... 
dblp:conf/emnlp/FitzGeraldAZ13 fatcat:hwhz32k7a5b5xjbqdgcam4cjnq

Learning Logical Structures of Paragraphs in Legal Articles

Ngo Xuan Bach, Minh Le Nguyen, Oanh Thi Tran, Akira Shimazu
2011 International Joint Conference on Natural Language Processing  
We present a two-phase framework to learn logical structures of paragraphs in legal articles.  ...  This paper presents a new task, learning logical structures of paragraphs in legal articles, which is studied in research on Legal Engineering (Katayama, 2007).  ...  An example in natural language 4 is presented in Figure 2 .  ... 
dblp:conf/ijcnlp/BachNTS11 fatcat:rpy4ta6rejhtlkkgly7jioymoa
« Previous Showing results 1 — 15 out of 629,338 results