Filters








54,581 Hits in 10.1 sec

Representation and Inference for Natural Language: A First Course in Computational Semantics

Francis Jeffry Pelletier
2006 Computational Linguistics  
For the authors of this textbook, this study includes the representation of the meaning of natural language in logic formalisms, the recognition of certain relations that hold within this formalization  ...  The introduction of this book traces the history of computational semantics, with a goal of justifying the enterprise in the face of the modern emphasis on statistical natural language processing.  ...  Chapters 4 and 5 bring in a consideration not normally contemplated in computational linguistic courses: inference.  ... 
doi:10.1162/coli.2006.32.2.283 fatcat:x5lzseuu4zdi7nfgjthpb6ya2a

Language (Re)modelling: Towards Embodied Language Understanding [article]

Ronen Tamari, Chen Shani, Tom Hope, Miriam R. L. Petruck, Omri Abend, Dafna Shahaf
2020 arXiv   pre-print
While natural language understanding (NLU) is advancing rapidly, today's technology differs from human-like language understanding in fundamental ways, notably in its inferior efficiency, interpretability  ...  This position paper argues that the use of grounding by metaphoric inference and simulation will greatly benefit NLU systems, and proposes a system architecture along with a roadmap towards realizing this  ...  We further thank Ari Rappoport, the Hyadata Lab at HUJI, Yoav Goldberg, Ido Dagan, Jonathan Berant, and the BIU & TAU NLP seminar audiences for interesting discussion and thoughtful remarks.  ... 
arXiv:2005.00311v2 fatcat:giwy3vxpazd73m5nmvj7lwo32e

Applying automated deduction to natural language understanding

Johan Bos
2009 Journal of Applied Logic  
The first is a text understanding system building semantic representations of texts, developed in the late 1990s.  ...  We run a robust parser producing semantic representations for both texts, and use the theorem prover VAMPIRE to check whether one text entails the other.  ...  The use of off-the-shelf first-order reasoning tools also shed a whole new light on research in computational semantics-one could not just build a semantic representation for a given natural language expression  ... 
doi:10.1016/j.jal.2007.07.008 fatcat:ex764s3wu5aspcwddr53o424pu

Logic, Language, and Calculus [article]

Florian Richter
2020 arXiv   pre-print
Several approaches in the field of Natural Language Understanding (NLU) and Natural Language Inference (NLI) take this insight in account, but do not consider, how an inference can be assessed as a good  ...  The difference between object-language and metalanguage is crucial for logical analysis, but has yet not been examined for the field of computer science.  ...  Natural Language Inference In 2006 Dagan et. al wrote one of the first papers in the field of Natural Language Inference (NLI).  ... 
arXiv:2007.02484v1 fatcat:dlrgzclhbfa5fkfyqqiknnu4tm

Bootstrapping language acquisition

Omri Abend, Tom Kwiatkowski, Nathaniel J. Smith, Sharon Goldwater, Mark Steedman
2017 Cognition  
Starting from these assumptions, we develop a Bayesian probabilistic account of semantically bootstrapped first-language acquisition in the child, based on techniques from computational parsing and interpretation  ...  The learner thus demonstrates how statistical learning over structured representations can provide a unified account for these seemingly disparate phenomena.  ...  We thank Julia Hockenmaier and Luke Zettlemoyer for guidance in the early stages of this research, and Inbal Arnon, Jennifer Culbertson, and Ida Szubert for their feedback on a draft of this article.  ... 
doi:10.1016/j.cognition.2017.02.009 pmid:28412593 fatcat:3k3o4o2hw5cuddvqp7pfxzxsgy

Commonsense Reasoning in and Over Natural Language [chapter]

Hugo Liu, Push Singh
2004 Lecture Notes in Computer Science  
We conclude that the flexibility of natural language makes it a highly suitable representation for achieving practical inferences over text, such as context finding, inference chaining, and conceptual  ...  In this paper, we present a methodology for reasoning flexibly about these semi-structured natural language fragments.  ...  Acknowledgements We extend our thanks to the many people at the Media Lab who have used Con-ceptNet in their projects, especially Barbara Barry, Nathan Eagle, Henry Lieberman, and Austin Wang, and especially  ... 
doi:10.1007/978-3-540-30134-9_40 fatcat:tz5zh7tohbgbjlyyk4jyveyq3q

Database semantics for natural language

Roland Hausser
2001 Artificial Intelligence  
Because metalanguage definitions are not designed for procedural implementation, neither truth-1 nor use-conditional semantics are suitable for a computational model of natural language communication.  ...  It is called a SLIM machine and functionally integrates the procedures of natural language interpretation, conceptualization, and production as well as query and inference.  ...  In the course of evolution, contextual cognition came first and comprised non-language-based recognition and action, both external and internal.  ... 
doi:10.1016/s0004-3702(01)00083-2 fatcat:yc6ds2qp4nfnzp7uri74q53wwi

The Semantic Web Languages [chapter]

Fausto Giunchiglia, Feroz Farazi, Letizia Tanca, Roberto De Virgilio
2009 Semantic Web Information Management  
The Semantic Web is basically an extension of the Web and of the Web-enabling database and Internet technology, and, as a consequence, the Semantic Web methodologies, representation mechanisms and logics  ...  This article comes second in this book, after an article on data management, in order to first complete the picture with the description of the languages that can be used to represent information on the  ...  To provide a few examples of the meaning of the constructs above, owl:Class can be used to represent a concept, owl:equivalentClass to state that a concept is equivalent to another, owl:Thing to represent  ... 
doi:10.1007/978-3-642-04329-1_3 fatcat:nzifw26awbcflp4hi75ygv4hw4

Complexity in Language Acquisition

Alexander Clark, Shalom Lappin
2013 Topics in Cognitive Science  
Second, we claim that the real problem for language learning is the computational complexity of constructing a hypothesis from input data.  ...  Such arguments typically neglect the probabilistic nature of cognition and learning in general.  ...  Acknowledgments We thank the participants in our the 2007 and 2011 Linguistics Summer Institute courses, and in our NASSLLI 2010 course, as well as the audiences who attended numerous talks in which we  ... 
doi:10.1111/tops.12001 pmid:23335575 fatcat:dzq6bckz6rfofek6bio5aifbxe

Approaches to natural language discourse processing

Paul Mc Kevitt, Derek Partridge, Yorick Wilks
1992 Artificial Intelligence Review  
The problem is important because, to properly understand natural language, a computer should have some sense of what it means for a discourse to be coherent and rational.  ...  Theories, models and implementations of natural-language processing argue for a measure of coherence based on three themes: meaning, structure, and intention.  ...  Definite Clause Grammars (DCG's) were first developed by Pereira and Warren (1980) as a tool to be used in Prolog for natural-language processing.  ... 
doi:10.1007/bf00123689 fatcat:orfwdvt2vnhavoeu2o5fs5vyai

Language Learning and Language Universals

Jeffrey Lidz
2010 Biolinguistics  
This paper explores the role of learning in generative grammar, highlighting interactions between distributional patterns in the environment and the innate structure of the language faculty.  ...  Reviewing three case studies, it is shown how learners use their language faculties to leverage the environment, making inferences from distributions to grammars that would not be licensed in the absence  ...  the child's antecedent knowledge about the nature of movement rules in natural language.  ... 
doaj:ed2a8525d85f453f9d41921812ec7e77 fatcat:i3y6lwxjxrejtmhjv367kkeetu

Language [chapter]

2016 Principles of Semiotic  
Logical representation is not a means of specifying the meaning of an isolated sentence, but instead a device for evaluating a specific inference in which the sentence may occur.  ...  king of France and bald Its representation in symbolic notation becomes finally (3) 3x[Kx & Vy(Ky => y=x) & Bx] with 'K' for 'is a king of France' and 'B' for 'is bald'.  ...  Why has language been analyzed and described in isolation from comparisons to non-linguistic signs?  ... 
doi:10.4324/9781315533773-13 fatcat:rqyg7q3banfujnevzp6vymnkf4

Language Models are not Models of Language [article]

Csaba Veres
2021 arXiv   pre-print
We argue that this creates a conundrum for claims that neural models provide an alternative theory to generative phrase structure grammars in explaining how language works.  ...  Interestingly, when the models are trained with data that includes software code, they demonstrate remarkable abilities in generating functioning computer code from natural language specifications.  ...  natural and computer languages.  ... 
arXiv:2112.07055v1 fatcat:prrps24glzei5igmmzlra7g3mq

Natural Language Question Answering Systems: 1969 [chapter]

Robert F. Simmons
1970 Theoretical Approaches to Non-Numerical Problem Solving  
Recent experiments in programming natural language question-answering systems are reviewed to summarize the methods that have been developed for syntactic, semantic, and logical analysis of English strings  ...  It is concluded that at least minimalty effective techniques have been devised for answering questions from natural language subsets in small scale experimental systems and that a useful paradigm has evolved  ...  The first of these is a merger of Raphael's earlier line of thought, first with formal theorem-proving techniques (Green and Raphael 1968) , then with a natural language semantic system developed by  ... 
doi:10.1007/978-3-642-99976-5_4 fatcat:ub37dbx4ufb53hadyrqhtmf53u

Natural language question-answering systems: 1969

Robert F. Simmons
1970 Communications of the ACM  
Recent experiments in programming natural language question-answering systems are reviewed to summarize the methods that have been developed for syntactic, semantic, and logical analysis of English strings  ...  It is concluded that at least minimalty effective techniques have been devised for answering questions from natural language subsets in small scale experimental systems and that a useful paradigm has evolved  ...  The first of these is a merger of Raphael's earlier line of thought, first with formal theorem-proving techniques (Green and Raphael 1968) , then with a natural language semantic system developed by  ... 
doi:10.1145/361953.361963 fatcat:kgqm763zqfhl5ke33ymhcpadnq
« Previous Showing results 1 — 15 out of 54,581 results