Filters








87,190 Hits in 5.8 sec

Models of natural language understanding

M. Bates
1995 Proceedings of the National Academy of Sciences of the United States of America  
This paper surveys some of the fundamental problems in natural language (NL) understanding (syntax, semantics, pragmatics, and discourse) and the current approaches to solving them.  ...  Critical areas for the future include grammars that are appropriate to processing large amounts of real language; automatic (or at least semiautomatic) methods for deriving models of syntax, semantics,  ...  But it is important to distinguish "language understanding" from "recognizing speech," so it is natural to ask, why the same path has not been followed in natural language understanding.  ... 
doi:10.1073/pnas.92.22.9977 pmid:7479812 pmcid:PMC40721 fatcat:cv3rnjtgcreodmkjvzdx2rbyfi

Natural language understanding for logical games [article]

Adrian Groza, Cristian Nitu
2021 arXiv   pre-print
We developed a system able to automatically solve logical puzzles in natural language. Our solution is composed by a parser and an inference module.  ...  The advantage of using reasoning for Natural Language Understanding (NLU) instead of Machine learning is that the user can obtain an explanation of the reasoning chain.  ...  ACKNOWLEDGMENTS We thank the anonymous reviewers for their valuable comments.  ... 
arXiv:2110.00558v1 fatcat:3nu6yri5hbbnfgmeyf2ppupb2q

Query Understanding for Natural Language Enterprise Search [article]

Francisco Borges, Georgios Balikas, Marc Brette, Guillaume Kempf, Arvind Srikantan, Matthieu Landos, Darya Brazouskaya, Qianqian Shi
2020 arXiv   pre-print
Natural Language Search (NLS) extends the capabilities of search engines that perform keyword search allowing users to issue queries in a more "natural" language.  ...  We present an NLS system we implemented as part of the Search service of a major CRM platform. The system is currently in production serving thousands of customers.  ...  ACKNOWLEDGEMENTS We would like to thank Ahmet Bugdayci, Anmol Bhasin, Christian Posse, Dylan Hingey, Ghislain Brun, Mario Rodriguez, Paulo Gomes, Rohit Kapoor and Sam Edwards for their support, help and  ... 
arXiv:2012.06238v1 fatcat:t5ck2jmaqngexgmgoylpoqt3ua

Modelling for natural language understanding

R Baud, C Lovis, L Alpay, A M Rassinoux, J R Scherrer, A Nowlan, A Rector
1993 Proceedings. Symposium on Computer Applications in Medical Care  
Natural Language Understanding (NLU) is a rapidly growing field in medical informatics. Its potential for tomorrow's applications is important.  ...  This article aims at describing the current development of a multilingual natural language system, strongly oriented towards the semantics of the domain.  ...  The GRAIL language and the modelling methodology have been developed within the framework of the GALEN project, at the University of Manchester.  ... 
pmid:8130480 pmcid:PMC2248520 fatcat:j2jwcujuybfk5nrfqr2nqim2ay

Exploring natural language understanding in robotic interfaces

Ioannis Giachos, Evangelos C. Papakitsos, Georgios Chorozoglou
2017 IJAIN (International Journal of Advances in Intelligent Informatics)  
Natural Language Understanding is a major aspect of the intelligence of robotic systems.  ...  These enhanced communicational abilities can be based on the voids of an output data structure that corresponds to a systemic-semantic model of language communication, as grammar formalism.  ...  So the easiest way is to construct a new language that addresses the associated problems of speech that the usage of a natural language introduces.  ... 
doi:10.26555/ijain.v3i1.81 fatcat:pzlg2peh5jfs3l55ivdoewv67y

Toward understanding natural language directions

Thomas Kollar, Stefanie Tellex, Deb Roy, Nicholas Roy
2010 2010 5th ACM/IEEE International Conference on Human-Robot Interaction (HRI)  
Speaking using unconstrained natural language is an intuitive and flexible way for humans to interact with robots.  ...  We present a system that follows natural language directions by extracting a sequence of spatial description clauses from the linguistic input and then infers the most probable path through the environment  ...  Understanding language from an untrained user is challenging because we are not asking the human to adapt to the limitations of the system, i.e., to limit their instructions to a small vocabulary or grammar  ... 
doi:10.1109/hri.2010.5453186 fatcat:7adbzjrpkfdotgak3wos36u3ci

Toward understanding natural language directions

Thomas Kollar, Stefanie Tellex, Deb Roy, Nicholas Roy
2010 Proceeding of the 5th ACM/IEEE international conference on Human-robot interaction - HRI '10  
Speaking using unconstrained natural language is an intuitive and flexible way for humans to interact with robots.  ...  We present a system that follows natural language directions by extracting a sequence of spatial description clauses from the linguistic input and then infers the most probable path through the environment  ...  Understanding language from an untrained user is challenging because we are not asking the human to adapt to the limitations of the system, i.e., to limit their instructions to a small vocabulary or grammar  ... 
doi:10.1145/1734454.1734553 dblp:conf/hri/KollarTRR10 fatcat:gmxy4kwog5aller5t7ks6c4jxe

Learning Executable Semantic Parsers for Natural Language Understanding [article]

Percy Liang
2016 arXiv   pre-print
We will see that semantic parsing is a rich fusion of the logical and the statistical world, and that this fusion will play an integral role in the future of natural language understanding systems.  ...  For building question answering systems and natural language interfaces, semantic parsing has emerged as an important and powerful paradigm.  ...  Logical forms have played a foundational role in natural language understanding systems since their genesis in the 1960s.  ... 
arXiv:1603.06677v1 fatcat:p4dwgeh5onfr7kd6mk53mls7au

Integration of speech with natural language understanding

R. C. Moore
1995 Proceedings of the National Academy of Sciences of the United States of America  
The integration of speech recognition with natural language understanding raises issues of how to adapt natural language processing to the characteristics of spoken language; how to cope with errorful  ...  I then look at how systems cope with errors in speech recognition and at attempts to use natural language information to reduce recognition errors.  ...  major challenges for correctly interpreting spoken language.  ... 
doi:10.1073/pnas.92.22.9983 pmid:7479813 pmcid:PMC40722 fatcat:iyynjeqinjeyxjbnj2siqfjft4

Learning executable semantic parsers for natural language understanding

Percy Liang
2016 Communications of the ACM  
We will see that semantic parsing is a rich fusion of the logical and the statistical world, and that this fusion will play an integral role in the future of natural language understanding systems.  ...  For building question answering systems and natural language interfaces, semantic parsing has emerged as an important and powerful paradigm.  ...  Logical forms have played a foundational role in natural language understanding systems since their genesis in the 1960s.  ... 
doi:10.1145/2866568 fatcat:lcl6pogzmfazdma4wmt5rnebai

Applying automated deduction to natural language understanding

Johan Bos
2009 Journal of Applied Logic  
1 The concept natural language understanding is not easy to define.  ...  Moreover, abduction rather than deduction is generally viewed as a promising way to apply reasoning in natural language understanding.  ...  to natural language understanding and push its potential forward.  ... 
doi:10.1016/j.jal.2007.07.008 fatcat:ex764s3wu5aspcwddr53o424pu

An approach to program understanding by natural language understanding

LETHA H. ETZKORN, LISA L. BOWEN, CARL G. DAVIS
1999 Natural Language Engineering  
A system, called the PATRicia system (Program Analysis Tool for Reuse) that implements the approach is examined.  ...  A knowledge-based, natural language processing approach to the automated understanding of object-oriented code as an aid to the reuse of object-oriented code is described.  ...  The Sleator and Temperley natural language parser is a word-based, link grammar parser, which has a power similar to that of a context-free grammar.  ... 
doi:10.1017/s1351324999002120 fatcat:2n4axwcacncm7bwopvuaqmtnka

Understanding visual scenes

CARINA SILBERER, JASPER UIJLINGS, MIRELLA LAPATA
2018 Natural Language Engineering  
AbstractA growing body of recent work focuses on the challenging problem of scene understanding using a variety of cross-modal methods which fuse techniques from image and text processing.  ...  In this paper, we develop representations for the semantics of scenes by explicitly encoding the objects detected in them and their spatial relations.  ...  Efforts to advance scene understanding have seen the emergence of new tasks such as visual question answering (VQA; Antol et al., 2015) , where the aim is to provide an accurate natural language answer  ... 
doi:10.1017/s1351324918000104 fatcat:ly2tgzxwmjbkbofurydmn2odna

Natural Language Understanding with Distributed Representation [article]

Kyunghyun Cho
2015 arXiv   pre-print
This is a lecture note for the course DS-GA 3001 at the Center for Data Science , New York University in Fall, 2015.  ...  As the name of the course suggests, this lecture note introduces readers to a neural network based approach to natural language understanding/processing.  ...  I will leave these questions for you to figure out. Chapter 5 Neural Language Models Language Modeling: First Step What does it mean for a machine to understand natural language?  ... 
arXiv:1511.07916v1 fatcat:jfa2ab5byfavheibaxfohaf2ui

Active Learning for New Domains in Natural Language Understanding [article]

Stanislav Peshterliev, John Kearney, Abhyuday Jagannatha, Imre Kiss, Spyros Matsoukas
2019 arXiv   pre-print
We explore active learning (AL) for improving the accuracy of new domains in a natural language understanding (NLU) system.  ...  Additionally, case studies with human-in-the-loop AL on six new domains show 4.6%-9% improvement on an existing NLU system.  ...  Conclusions In this work, we focused on AL methods designed to select live data for manual annotation. The difference with prior work on AL is that we specifically target new domains in NLU.  ... 
arXiv:1810.03450v2 fatcat:advsnoleczbwzaws3i5x3scvw4
« Previous Showing results 1 — 15 out of 87,190 results