Filters








2,682 Hits in 3.1 sec

Careful Selection of Knowledge to Solve Open Book Question Answering

Pratyay Banerjee, Kuntal Kumar Pal, Arindam Mitra, Chitta Baral
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
In this paper we address QA with respect to the OpenBookQA dataset and combine state of the art language models with abductive information retrieval (IR), information gain based re-ranking, passage selection  ...  and weighted scoring to achieve 72.0% accuracy, an 11.6% improvement over the current state of the art.  ...  Approach Our approach involves six main modules: Hypothesis Generation, OpenBook Knowledge Extraction, Abductive Information Retrieval, Information Gain based Re-ranking, Passage Selection and Question  ... 
doi:10.18653/v1/p19-1615 dblp:conf/acl/BanerjeePMB19 fatcat:knzbjyynrjhvrgp7ggwfltqcee

語の活性度に基づくキーワード抽出法
Automatic Indexing Based on Term Activity

Naohiro Matsumura, Yukio Ohsawa, Mitsuru Ishizuka
2002 Transactions of the Japanese society for artificial intelligence  
With the increasing number of electronic documents, automatic indexing from a document is an essential approach in information retrieval systems, such as search engines.  ...  Our approach employs a spreading activation model to extract keywords based on the activity of terms without using corpus, thesaurus, syntactic analysis, dependency relations between terms, and the other  ...  Summary With the increasing number of electronic documents, automatic indexing from a document is an essential approach in information retrieval systems, such as search engines.  ... 
doi:10.1527/tjsai.17.398 fatcat:ezrvtvuuarb6zlrpkp64m7owka

Page 170 of Linguistics and Language Behavior Abstracts: LLBA Vol. 28, Issue 1 [page]

1994 Linguistics and Language Behavior Abstracts: LLBA  
The TACITUS project has developed an approach to abductive inference, weighted abduction, that has resulted in a significant simplification of how the problem of interpreting texts is conceptualized.  ...  Interpreta- tion as abduction can be combined with “parsing as deduction” to pro- duce an elegant & thorough integration of syntax, semantics, & pragmatics, spanning the range of linguistic phenomena from  ... 

Magnani's Abduction, Reason, and Science: Processes of Discovery and Explanation

James Guarini
2003 Informal Logic  
But in the end, this is a book that needed to be written. We need more books of this kind that attempt to show how to be more effective critical thinkers in a given area of professional practice.  ...  In sum, this reviewer says thumbs-up to this book. It is a first attempt, and a rme one.  ...  Chapter five has two themes-visual abduction and temporal abduction. Magnani takes an image to be a kind of "internal representation used by humans to retrieve information from memory" (p. 97).  ... 
doi:10.22329/il.v23i3.2178 fatcat:r2lnbaxudzdercdesl6yi5lg74

Recently-Published-Book Precis

2002 Artificial Intelligence  
The goal in machine learning is to extract useful information from a body of data by building good probabilistic models-and to automate the process as much as possible.  ...  Machine learning approaches (e.g., neural networks, hidden Markov models, and belief networks) are ideally suited for areas in which there is a lot of data but little theory, as in molecular biology.  ...  Jacquemin provides an account of the method and implementation of this innovative retrieval technique for text processing.  ... 
doi:10.1016/s0004-3702(02)00188-1 fatcat:xwd5jexdg5gnrmugs4ufuqayva

Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference

Masashi Yoshikawa, Koji Mineshima, Hiroshi Noji, Daisuke Bekki
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In logic-based approaches to reasoning tasks such as Recognizing Textual Entailment (RTE), it is important for a system to have a large amount of knowledge data.  ...  However, there is a tradeoff between adding more knowledge data for improved RTE performance and maintaining an efficient RTE system, as such a big database is problematic in terms of the memory usage  ...  We are also grateful to Bevan Johns for proofreading examples in LexSICK dataset and Hitoshi Manabe for his public codebase from which we learned many about the KBC techniques.  ... 
doi:10.1609/aaai.v33i01.33017410 fatcat:3aic4w6zpffe5h65bjiadqvq2q

Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference [article]

Masashi Yoshikawa, Koji Mineshima, Hiroshi Noji, Daisuke Bekki
2018 arXiv   pre-print
In logic-based approaches to reasoning tasks such as Recognizing Textual Entailment (RTE), it is important for a system to have a large amount of knowledge data.  ...  However, there is a tradeoff between adding more knowledge data for improved RTE performance and maintaining an efficient RTE system, as such a big database is problematic in terms of the memory usage  ...  We are also grateful to Bevan Johns for proofreading examples in LexSICK dataset and Hitoshi Manabe for his public codebase from which we learned many about the KBC techniques.  ... 
arXiv:1811.06203v1 fatcat:kacd6r7cangtfelnvkowt5g5ai

Peircean Semiotics and Subject Indexing: Contributions of Speculative Grammar and Pure Logic

Carlos Cândido de Almeida, Mariângela Spotti Lopes Fujita, Daniela Marjorie dos Reis
2013 Knowledge organization  
Secondly, and aiming to raise the level of interlocution between the areas, we intend to argue that subject indexing is an inferential process, as explained by the second branch of semiotics.  ...  We believe that the main difficulty in the proposals to understand the process of subject indexing based on Peircean semiotics stems from an incomplete interpretation of his semiotic system.  ...  The arguments are the linguistic expression that demonstrates the reasons that led us to conclude. For Salmon (1969, 22) , an argument is a linguistic entity and is not an inference.  ... 
doi:10.5771/0943-7444-2013-4-225 fatcat:dls6xmpw5ncmdhbl6ahooxaz2q

Page 180 of Computational Linguistics Vol. 24, Issue 1 [page]

1998 Computational Linguistics  
and Several Retrieval Languages Crist-Jan Doedens (Utrecht University) Editions Rodopi (Language and Computers: Studies in Practical Linguistics, edited by Jan Aarts and Willem Meijs, volume 14), 1994  ...  Authors and publishers who wish their pub- lications to be considered for review in Com- putational Linguistics should send a copy to the book review editor, Graeme Hirst, De- partment of Computer Science  ... 

USE: A Concept-Based Recommendation System to Support Creative Search

J. Sousa Lopes, S. Alvarez-Napagao, J. Vazquez-Salceda
2009 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology  
The system, driven by user feedback, executes an abductive reasoning (based on WordNet synset semantic relations) that is able to iteratively lead to new concepts which progressively represent the cognitive  ...  Vázquez-Salceda would like to acknowledge support from European funded CONTRACT Project (IST-034418). J. Sousa Lopes work has been funded by FCT-Portugal, scholarship SFRH/BD/38767/2007. J.  ...  We use tags related to pictures because they represent a description based on a perceived linguistic interpretation, meaning that this metadata associated with each image is already itself an abductive  ... 
doi:10.1109/wi-iat.2009.220 dblp:conf/iat/LopesAV09 fatcat:r2ajwiuyajesxizqgthubguewi

∂-Explainer: Abductive Natural Language Inference via Differentiable Convex Optimization [article]

Mokanarangan Thayaparan, Marco Valentino, Deborah Ferreira, Julia Rozanova, André Freitas
2021 arXiv   pre-print
ILP based approaches provide a way to encode explicit and controllable assumptions casting natural language inference as an abductive reasoning problem, where the solver constructs a plausible explanation  ...  In contrast, state-of-the-art transformer-based models can learn from data and implicitly encode complex constraints. However, these models are intrinsically black boxes.  ...  linguistic and semantic information to downstream tasks.  ... 
arXiv:2105.03417v1 fatcat:dxj3htriafarta36kddfj3dzva

Page 1950 of Psychological Abstracts Vol. 80, Issue 5 [page]

1993 Psychological Abstracts  
Following a summary of previous approaches to creativity, the authors present a theoretical model of the creative pro- cess.  ...  knowledge © biological variation in modes of abduction © spatial learning: two ways to get there from here © the relation between abduction and spatial mechanisms 16310.  ... 

Multimedia Interpretation for Dynamic Ontology Evolution

S. Castano, I. S. E. Peraldi, A. Ferrara, V. Karkaletsis, A. Kaya, R. Moller, S. Montanelli, G. Petasis, M. Wessel
2008 Journal of Logic and Computation  
In this article, we present an ontology evolution approach in the context of multimedia interpretation.  ...  Ontology evolution is generally defined as the timely adaptation of an ontology to changing requirements and the consistent propagation of changes to dependent artifacts.  ...  The abductive retrieval service discards inconsistent explanations.  ... 
doi:10.1093/logcom/exn049 fatcat:ltj45v3tlzer7hqexgysrcfa2q

A Multi-agent Approach to Question Answering [chapter]

Cássia Trojahn dos Santos, Paulo Quaresma, Irene Rodrigues, Renata Vieira
2006 Lecture Notes in Computer Science  
In this paper we present a multi-agent approach to question answering for the Portuguese language.  ...  This approach allows the use of different strategies and the reduction of errors introduced by individual methods.  ...  for concept Y, while the algorithm B constructs an accurate model for concept Y and a weak model for concept X.  ... 
doi:10.1007/11751984_14 fatcat:vqyy2thbsjgszfqnbjplpd3wvu

Page 1407 of Psychological Abstracts Vol. 80, Issue 3 [page]

1993 Psychological Abstracts  
Chater A PDP approach to processing center-embedded sentences - J. Weckerly and J. Elman Forced simple recurrent neural networks and grammatical in- ference - A. Maskara and A.  ...  Wharton A model of the role of expertise in analog retrieval - L. Branting The story with reminding: Memory retrieval is influenced by analogical similarity - C. Wharton, K. Holyoak, P. Downing, T.  ... 
« Previous Showing results 1 — 15 out of 2,682 results