Filters








1,998 Hits in 5.7 sec

Automated Word Puzzle Generation via Topic Dictionaries [article]

Balazs Pinter, Gyula Voros, Zoltan Szabo, Andras Lorincz
2012 arXiv   pre-print
We propose a general method for automated word puzzle generation.  ...  Our method can (i) generate automatically a large number of proper word puzzles of different types, including the odd one out, choose the related word and separate the topics puzzle.  ...  Our goal is to develop a general automated word puzzle generation method from 1. an unstructured and unannotated document collection, i.e., a simple corpus, 2. a topic model 1 , which induces a topic dictionary  ... 
arXiv:1206.0377v1 fatcat:4yxyxjokrfe5bagmvbnfyisohu

Automated Crossword Solving [article]

Eric Wallace, Nicholas Tomlin, Albert Xu, Kevin Yang, Eshaan Pathak, Matthew Ginsberg, Dan Klein
2022 arXiv   pre-print
Our system works by generating answer candidates for each crossword clue using neural question answering models and then combines loopy belief propagation with local search to find full puzzle solutions  ...  Compared to existing approaches, our system improves exact puzzle accuracy from 71% to 82% on crosswords from The New York Times and obtains 99.9% letter accuracy on themeless puzzles.  ...  We are also grateful to Will Shortz and the organizers of the American Crossword Puzzle Tournament for allowing us to participate in the event.  ... 
arXiv:2205.09665v2 fatcat:mvpqt77uc5hgrgytib4osdx6by

Cronus: An Automated Feedback Tool for Concept Maps

Masrik A. Dahir, Syed Ali Qasim, Irfan Ahmed
2021 IEEE Access  
The feedback includes identifying misconceptions, finding concepts, links, and branches that are (partially) matched or missed from a student concept map, generating summary statistics based on the feedback  ...  The finding establishes that an automated concept map evaluation system is a catalyst for higher-order thinking and understanding the hierarchical composition of a topic.  ...  The student has to construct the concept map in a jigsaw puzzle [20] manner. Jigsaw Puzzle invoke to think logically and improve students' problemsolving skills.  ... 
doi:10.1109/access.2021.3106509 fatcat:36h6s4p4mffobnmjf2linyxy4e

Combining Computational Analyses and Interactive Visualization for Document Exploration and Sensemaking in Jigsaw

C. Gorg, Zhicheng Liu, Jaeyeon Kihm, Jaegul Choo, Haesun Park, J. Stasko
2013 IEEE Transactions on Visualization and Computer Graphics  
Our particular focus is on the process of integrating automated analyses with interactive visualizations in a smooth and fluid manner.  ...  ACKNOWLEDGMENTS This research is based upon work supported in part by the National Science Foundation via Awards IIS-0915788 and CCF-0808863, and by the U.S.  ...  Surprisingly, the two author lists have many different names, which puzzles Bill since the two topics seem to be closely related.  ... 
doi:10.1109/tvcg.2012.324 pmid:23267206 fatcat:hjhelczb2bektfft4q4azva6b4

The Conceptual Foundations of National Terminological Information System

Rasim M. Alguliyev, Afruz M. Gurbanova
2018 International Journal of Education and Management Engineering  
Index Terms: Lexicography, terminology dictionary, computational terminology, terminology database, terminology registry.  ...  via Internet, in other words, the formation of Citizen Terminology will be supported.  ...  Some of those conceptual approaches are presented below: Automation of Term Generation Process 1) Traditionally, terms are selected from texts and systemized by scientists and experts (terminologists  ... 
doi:10.5815/ijeme.2018.04.03 fatcat:aka53c3in5cxxminbqdfrry6ei

Mitigating Dictionary Attacks on Password-Protected Local Storage [chapter]

Ran Canetti, Shai Halevi, Michael Steiner
2006 Lecture Notes in Computer Science  
from the password and the solutions of the specified puzzles.  ...  We propose an approach for limiting off-line dictionary attacks in this setting without relying on secret storage or secure hardware.  ...  This is a topic for future research. Computational Hardness of Puzzles.  ... 
doi:10.1007/11818175_10 fatcat:hu4oyxnftncnzn6jzhn5o4i6aa

Weighted Joint Sentiment-Topic Model for Sentiment Analysis Compared to ALGA: Adaptive Lexicon Learning Using Genetic Algorithm

Amjad Osmani, Jamshid Bagherzadeh Mohasefi, Mohamed Abdelaziz
2022 Computational Intelligence and Neuroscience  
generate a sentiment dictionary.  ...  As an LDA-based model, Joint Sentiment-Topic (JST) examines the impact of topics and emotions on words.  ...  ALGA generates a sentiment dictionary using the genetic algorithm, but proposed methods generate a sentiment dictionary using topic modeling.  ... 
doi:10.1155/2022/7612276 fatcat:otxnnqac4vcfbocxj4s2uhrnim

Learning to Understand Phrases by Embedding the Dictionary [article]

Felix Hill, Kyunghyun Cho, Anna Korhonen, Yoshua Bengio
2016 arXiv   pre-print
We present two applications of these architectures: "reverse dictionaries" that return the name of a concept given a definition or description and general-knowledge crossword question answerers.  ...  Neural language embedding models can be effectively trained to map dictionary definitions (phrases) to (lexical) representations of the words defined by those definitions.  ...  Our long question set consists of the first 150 questions (starting from puzzle #1) from his general-knowledge crosswords, excluding clues of fewer than four words and those whose answer was not a single  ... 
arXiv:1504.00548v4 fatcat:d442yvgz5vbdpe3laxtfg2jb2u

Learning to Understand Phrases by Embedding the Dictionary

Felix Hill, Kyunghyun Cho, Anna Korhonen, Yoshua Bengio
2016 Transactions of the Association for Computational Linguistics  
We present two applications of these architectures: reverse dictionaries that return the name of a concept given a definition or description and general-knowledge crossword question answerers.  ...  Neural language embedding models can be effectively trained to map dictionary definitions (phrases) to (lexical) representations of the words defined by those definitions.  ...  Our long question set consists of the first 150 questions (starting from puzzle #1) from his general-knowledge crosswords, excluding clues of fewer than four words and those whose answer was not a single  ... 
doi:10.1162/tacl_a_00080 fatcat:wmemcopd6fcrpdgni4ygsvcxju

Learning Language from a Large (Unannotated) Corpus [article]

Linas Vepstas, Ben Goertzel
2014 arXiv   pre-print
A novel approach to the fully automated, unsupervised extraction of dependency grammars and associated syntax-to-semantic-relationship mappings from large text corpora is described.  ...  If successful, this approach would enable the mining of all the information needed to power a natural language comprehension and generation system, directly from a large, unannotated corpus.  ...  A disjunct can be thought of as a jig-saw puzzle-piece; valid syntactic word orders are those for which the puzzle-pieces can be validly connected.  ... 
arXiv:1401.3372v1 fatcat:cl7huumnvbfppottck6jldcyji

Using Aesthetic Judgements to Distinguish between Humans and Computers [article]

Nasser Mohammed Al-Fannah
2019 arXiv   pre-print
More generally, using human aesthetic judgement adds a possible new dimension to the future design of Turing tests.  ...  At the present time, no AI can simulate general intelligence and so cannot pass a general Turing test (i.e. on an unlimited range of topics) [6] .  ...  Ease for Humans: the puzzle should be easy for humans to solve. 3. Ease of Generation: the generation of puzzles in software should be straightforward. 4.  ... 
arXiv:1704.02972v2 fatcat:msdsylg4f5bndm2fu3be6liuh4

Validating automated integrative complexity: Natural language processing and the Donald Trump Test

Lucian Gideon Conway, Kathrene R. Conway, Shannon C. Houck
2020 Journal of Social and Political Psychology  
We first review the growing body of evidence for the validity of the Automated Integrative Complexity (AutoIC) method for computer-scoring integrative complexity.  ...  Supplementary materials to "Validating Automated Integrative Complexity: Natural language processing and the Donald Trump Test" [Additional tests, information, and examples].  ...  Consider that, in contrast to V+POStags -which spent more time on machine learning and thus developed a human dictionary that had 312 base words -AutoIC has thousands of complexity-related words and phrases  ... 
doi:10.5964/jspp.v8i2.1307 fatcat:jcan4u3otrbfxpffxxfmpnxd3y

People Still Care About Facts: Twitter Users Engage More with Factual Discourse than Misinformation–A Comparison Between COVID and General Narratives on Twitter [article]

Mirela Silva, Fabrício Ceschin, Prakash Shrestha, Christopher Brant, Shlok Gilda, Juliana Fernandes, Catia S. Silva, André Grégio, Daniela Oliveira, Luiz Giovanini
2021 arXiv   pre-print
Misinformation entails the dissemination of falsehoods that leads to the slow fracturing of society via decreased trust in democratic processes, institutions, and science.  ...  topics, and (4) factual claims on general topics.  ...  of words per sentence, number of words containing more than six letters, and number of words found in the LIWC dictionary. • Eighty-five dimensions, including function words (e.g., pronouns, articles,  ... 
arXiv:2012.02164v3 fatcat:fxitpvvpkvb2xnykxlcqu47f5a

Using games with a purpose and bootstrapping to create domain-specific sentiment lexicons

Albert Weichselbraun, Stefan Gindl, Arno Scharl
2011 Proceedings of the 20th ACM international conference on Information and knowledge management - CIKM '11  
This process considers sentiment terms as well as sentiment indicators occurring in the discourse surrounding a particular topic.  ...  Automatically created lexicons yield a performance comparable to professionally created language resources such as the General Inquirer.  ...  20 most frequent words and the averages scores for all verbs, nouns and adjectives are based on SentiWordNet [5] ; (iii) the frequency of positive and negative words according to the General Inquirer;  ... 
doi:10.1145/2063576.2063729 dblp:conf/cikm/WeichselbraunGS11 fatcat:v6lomgzulvd4zbunqbzp3vjzw4

A probabilistic approach to solving crossword puzzles

Michael L. Littman, Greg A. Keim, Noam Shazeer
2002 Artificial Intelligence  
PROVERB, the complete system, averages 95.3% words correct and 98.1% letters correct in under 15 minutes per puzzle on a sample of 370 puzzles taken from the New York Times and several other puzzle sources  ...  We attacked the problem of solving crossword puzzles by computer: given a set of clues and a crossword grid, try to maximize the number of words correctly filled in.  ...  These modules ignore their clues and return all words of the correct length from several dictionaries.  ... 
doi:10.1016/s0004-3702(01)00114-x fatcat:33ybo4rqhrd6notyp7jwfj3yqu
« Previous Showing results 1 — 15 out of 1,998 results