Filters








17,440 Hits in 2.0 sec

Page 414 of Computational Linguistics Vol. 32, Issue 3 [page]

2006 Computational Linguistics  
Learning semantic constraints for the automatic discovery of part-whole relations.  ...  Computational Linguistics by latent semantic analysis. Journal of the American SOC ety tor Information science (JASIS), 41(6):391—407 Dolan, William B. 1995.  ... 

Direct Manipulation: A Step Beyond Programming Languages

Shneiderman
1983 Computer  
Because their fields of action are abstractions of reality, these games are easily understood-learning is by analogy.  ...  The syntax of text editors may vary, but the decomposition from problem domain into low-level semantics is largely the same.  ... 
doi:10.1109/mc.1983.1654471 fatcat:sfmp535lwjby3crouyjbu4rwda

Page 27 of Computational Linguistics Vol. 32, Issue 1 [page]

2006 Computational Linguistics  
Lexical cohesion computed by thesaural relations as an indicator of the structure of text. Computational Linguistics, 17(1):21-48.  ...  Morris, Jane and Graeme Hirst. 2005. 1 he subjectivity of lexical cohesion in text. In James G. Shanahan, Yan Qu, and Janyce Wiebe, editors, Computing Attitude and Affect in Text.  ... 

Generating Sentences by Editing Prototypes [article]

Kelvin Guu, Tatsunori B. Hashimoto, Yonatan Oren, Percy Liang
2018 arXiv   pre-print
Furthermore, the model gives rise to a latent edit vector that captures interpretable semantics such as sentence similarity and sentence-level analogies.  ...  Compared to traditional models that generate from scratch either left-to-right or by first sampling a latent sentence vector, our prototype-then-edit model improves perplexity on language modeling and  ...  We thank the reviewers and editor for their insightful comments. This work was funded by DARPA CwC program under ARO prime contract no. W911NF-15-1-0462.  ... 
arXiv:1709.08878v2 fatcat:s6veavzgvfhs5lb73auynjuqh4

Recent Statistics on the Growth of the KI Journal

Ubbo Visser
2015 Künstliche Intelligenz  
The statistics also show that the full-text download rate nearly doubled from 2011 to 2014. This is an indication for the positive impact of an international publisher like Springer.  ...  Years 2013 and 2014 show an increasing full-text download trend from North-American readers ( 14, 13 %, respectively), which can be interpreted as a growing impact of our journal in that area.  ...  systems can efficiently learn from the interaction with the environment, especially by having an integrated approach to decision making and learning, allowing systems to decide by themselves on actions  ... 
doi:10.1007/s13218-015-0369-9 fatcat:nzpaj64gnzfwdgjybhk7mkp6eq

A conversation with Professor Zhongzhi Shi

Zhongzhi Shi
2012 SIGKDD Explorations  
At that time, the Chinese researchers mainly focused on individual learning algorithms, such as inductive learning, analogical learning, casebased learning, explanation-based learning, genetic learning  ...  About the author: The book "Knowledge Discovery" (First Edition) by Zhongzhi Shi, published by Tsinghua University Press in 2002 gave a summary of the above research areas.Multi-agent system, semantic  ... 
doi:10.1145/2207243.2207263 fatcat:woe3snawrrgbdkck27lwnza2r4

Introduction: Modeling, Learning and Processing of Text-Technological Data Structures [chapter]

Alexander Mehler, Kai-Uwe Kühnberger, Henning Lobin, Harald Lüngen, Angelika Storrer, Andreas Witt
2011 Studies in Computational Intelligence  
In the case of the present volume, this relates to the conference on "Processing Text-Technological Resources", organized by the research group "Text-technological  ...  By analogy to the analysis of sentence structure, it is often called text or discourse parsing.  ...  That is, as instances of webgenres (i.e., types of web documents by analogy to text types), websites usually consist of several pages that are connected by hyperlinks.  ... 
doi:10.1007/978-3-642-22613-7_1 fatcat:4moj7owrc5ec5msnvw5fqyc7sy

CPoint: Dissolving the Author's Dilemma [chapter]

Andrea Kohlhase, Michael Kohlhase
2004 Lecture Notes in Computer Science  
We present the CPoint application, a semantic, invasive editor for Microsoft Pow-erPoint, geared towards the OMDoc MKM format.  ...  Automated knowledge management techniques critically depend on the availability of semantically enhanced documents which are hard to come by in practice.  ...  Acknowledgments The development of the CPoint system has been funded by the National Science Foundation under grant CCF-0113919 and a grant from Carnegie Mellon's Office for Technology in Education.  ... 
doi:10.1007/978-3-540-27818-4_13 fatcat:bbcuuuw57bblnmudzrl744lj7y

Page 347 of Computational Linguistics Vol. 29, Issue 3 [page]

2003 Computational Linguistics  
A framework of a mechanical translation between Japanese and English by analogy principle. In Alick Elithorn and Ranan Banerji, editors, Artificial and Human Intelligence.  ...  Sublanguage: Studies of Language in Restricted Semantic Domains. De Gruyter, Berlin. Korhonen, Anna. 2000. Using semantically motivated estimates to help subcategorization acquisition.  ... 

Not just about size - A Study on the Role of Distributed Word Representations in the Analysis of Scientific Publications [article]

Andres Garcia, Jose Manuel Gomez-Perez
2018 arXiv   pre-print
Embeddings from domain-specific scientific corpora effectively capture the semantics of the domain.  ...  On the other hand, obtaining comparable results through general corpora can also be achieved, but only in the presence of very large corpora of well formed text.  ...  taxonomy categories where articles are placed by authors or editors.  ... 
arXiv:1804.01772v1 fatcat:3fuzesbrsfbdnaeslgbodea4n4

EFFECTIVE KNOWLEDGE MANAGEMENT USING AN ONTOLOGY-BASED APPROACH

2009 Issues in Information Systems  
These are the Military Analogical Reasoning System (MARS) and the Planning for Urban Terrain Operations (PLUTO) system.  ...  Figure 2: Military Analogical Reasoning System MARS operates by comparing many instances of stored tactical stories, determining which include analogous situations and thus related lessons learned, and  ...  This approach integrates heterogeneous distributed knowledge and supports semantic querying based on the meaning of concepts rather than searching for text string matches, i.e., keywords.  ... 
doi:10.48009/2_iis_2009_231-236 fatcat:jssmnqgwzfdgfgme55thbgzrve

Robust Intelligence

Edwina L. Rissland
2018 The AI Magazine  
Understanding text, speech, and other communicative forms, as well as their underlying meaning, intent, and realization, including semantic interpretation, cognitively and neuro-linguistically informed  ...  Generating text, speech or multimodal communication to convey meaning and intent.  ... 
doi:10.1609/aimag.v39i1.2789 fatcat:bsxvf2vdxjclfkijw3hxffwcnq

Not Just About Size - A Study on the Role of Distributed Word Representations in the Analysis of Scientific Publications

Andrés García-Silva, José Manuél Gómez-Pérez
2018 Extended Semantic Web Conference  
Embeddings from domain-specific scientific corpora effectively capture the semantics of the domain.  ...  On the other hand, obtaining comparable results through general corpora can also be achieved, but only in the presence of very large corpora of well formed text.  ...  taxonomy categories where articles are placed by authors or editors.  ... 
dblp:conf/esws/Garcia-SilvaG18 fatcat:v7ttwmblszh4rmkywqu5my37zu

Briefly Noted/Publications Received

2007 Computational Linguistics  
Instead, they are in- terconnected via transfer, the ability to extend what has been learned in one context to new contexts by analogy.  ...  Semantic va- lency (the potential semantic relations of a word with other items) and syntactic valency (the ways to express those relations in sen- tences) are learned for each word separately.  ... 
doi:10.1162/coli.2007.33.4.601 fatcat:rd2fpnshxngvbgokrgx4ub3rt4

Background Knowledge, Indexing and Matching Interdependencies of Document Management and Ontology-Maintenance

Andreas Faatz, Thomas Kamps, Ralf Steinmetz
2000 European Conference on Artificial Intelligence  
learn.  ...  This is shown to be one way of improving the results of the algorithm by improving the background knowledge.  ...  Our goal is to express similarities of text documents detected by an algorithm. Hence a semantic matching problem is to be solved.  ... 
dblp:conf/ecai/FaatzKS00 fatcat:vn4i7soo5rhpnjxrxoh3tz6ugm
« Previous Showing results 1 — 15 out of 17,440 results