5,666 Hits in 5.7 sec

Answer Validation Through Robust Logical Inference [chapter]

Ingo Glöckner
2007 Lecture Notes in Computer Science  
The paper features MAVE, a knowledge-based system for answer validation through deep linguistic processing and logical inference.  ...  The system not only validates answers directly, but also gathers evidence by proving the original question and comparing results with the answer candidate. This method boosts recall by up to 13%.  ...  Table 1 lists the results of MAVE in the answer validation exercise. 'Accuracy' is ratio of correct decision.  ... 
doi:10.1007/978-3-540-74999-8_62 fatcat:7aozhdcjgravplrnrkbqp22rh4

A Knowledge-Based Sense Disambiguation Method to Semantically Enhanced NL Question for Restricted Domain

Ammar Arbaaeen, Asadullah Shah
2021 Information  
Many studies have achieved encouraging results in lexical semantic resolution on the topic of word sense disambiguation (WSD), and several other works consider these challenges in the context of QA applications  ...  Extracting the lexical semantic of a Natural Language (NL) question presents challenges at syntactic and semantic levels for most QA systems.  ...  A group of features based on semantic, syntactic and lexical of the sentences were defined.  ... 
doi:10.3390/info12110452 fatcat:ynxlsrfstrh77mod64243nxoge

Techniques for Recognizing Textual Entailment and Semantic Equivalence [chapter]

Jesús Herrera, Anselmo Peñas, Felisa Verdejo
2006 Lecture Notes in Computer Science  
After defining what is understood by textual entailment and semantic equivalence, the present state and the desirable future of the systems aimed at recognizing them is shown.  ...  A compilation of the currently implemented techniques in the main Recognizing Textual Entailment and Semantic Equivalence systems is given.  ...  Acknowledgments This work has been partially supported by the Spanish Ministry of Science and Technology. Project TIC-2003-07158-C04-02: R2D2-SyEMBRA.  ... 
doi:10.1007/11881216_44 fatcat:x2jutqmtivfthcrhv6nntu6avi

A Latin Functionalist Dictionary as a Self-Learning Language Device: Previous Experiences to Digitalization

Manuel Márquez, Beatriz Chaves
2016 Education Sciences  
The application of a methodology based on S.C.  ...  Dik's Functionalist Grammar linguistic principles, which is addressed to the teaching of Latin to secondary students, has resulted in a quantitative improvement in students' acquisition process of knowledge  ...  Later on, the student needs to compare the results with his/her group members for ten minutes. Finally, the teacher goes over through the answers of the proposed exercises.  ... 
doi:10.3390/educsci6030023 fatcat:7uxypvdeh5g4li5z57cfvw327q

REAP.PT Serious Games for Learning Portuguese [chapter]

André Silva, Cristiano Marques, Jorge Baptista, Alfredo Ferreira, Nuno Mamede
2012 Lecture Notes in Computer Science  
For text-based exercises, it focus on automatic generation of syntactic and vocabulary questions. These exercises are set in a gaming context, to better motivate students.  ...  Computer-Aided Language Learning (CALL) is an area of research that focuses on developing tools to improve the process of learning a language.  ...  This game consists of cloze questions allowing students to practice reading comprehension while enhancing their syntactic knowledge of the language.  ... 
doi:10.1007/978-3-642-28885-2_29 fatcat:pojfctuma5ghtms7ur5dtyqiwe

Experimenting a "General Purpose" Textual Entailment Learner in AVE [chapter]

Fabio Massimo Zanzotto, Alessandro Moschitti
2007 Lecture Notes in Computer Science  
In this paper we present the use of a "general purpose" textual entailment recognizer in the Answer Validation Exercise (AVE) task.  ...  Its main feature is the use of Support Vector Machines (SVMs) with kernel functions based on cross-pair similarity between entailment pairs.  ...  The Answer Validation Exercise (AVE) instead provides an opportunity to show that such recognizers are useful for Question Answering.  ... 
doi:10.1007/978-3-540-74999-8_61 fatcat:swyhrfm5ljd33buh5fs7yab5bm

Selecting Answers to Questions from Web Documents by a Robust Validation Process

A. Grappy, B. Grau, M-H. Falco, A-L. Ligozat, I. Robba, A. Vilnat
2011 2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology  
It takes into account criteria characterizing both passage and answer relevance at surface, lexical, syntactic and semantic levels to deal with different types of texts.  ...  We developed a QA system based on an answer validation process able to handle Web specificity.  ...  Thus, we regarded answering questions as an answer validation problem on retrieved passages. Answer validation was introduced at CLEF with AVE (Answer Validation Exercise 2 ) in 2006.  ... 
doi:10.1109/wi-iat.2011.210 dblp:conf/webi/GrappyGFLRV11 fatcat:7jdppenkfve6nj3ibua6dqfgtu

Automatic Semantic Analysis for NLP Applications

Ingo Glückner, Sven Hartrumpf, Hermann Helbig, Johannes Leveling, Rainer Osswald
2007 Zeitschrift für Sprachwissenschaft  
We introduce the underlying semantic framework and give an overview of several recent activities and projects covering natural language interfaces to information providers on the web, automatic knowledge  ...  AbstractIn this article, we describe a long-term enterprise at the FernUniversität in Hagen to develop systems for the automatic semantic analysis of natural language.  ...  With this basic approach, MAVE achieved the best answer filtering results for German in the CLEF 2006 answer validation exercise (58.4 % precision, 50.6 % recall, 54.2 % F-score; see AVE06 overview in  ... 
doi:10.1515/zfs.2007.019 fatcat:kkrm6ssqzjbxnbqrr7sggqrdie

Ontology-Based Interpretation of Natural Language

Philipp Cimiano, Christina Unger, John McCrae
2014 Synthesis Lectures on Human Language Technologies  
a fair balance at peril of dissatisfying both sides or nail their colors to the mast and cater mainly to one of two communities.  ...  A book aiming to build a bridge between two fields that share the subject of research but do not share the same views necessarily puts itself in a difficult position: The authors have either to strike  ...  In Chapter 9, the application of question answering over structured data is discussed-not to be confused with question answering from unstructured sources in the flavor of TREC or IBM Watson.  ... 
doi:10.2200/s00561ed1v01y201401hlt024 fatcat:n6jwt7ot25h5los7vojm5d6osm

XTE: Explainable Text Entailment [article]

Vivian S. Silva, André Freitas, Siegfried Handschuh
2020 arXiv   pre-print
Also, if a semantic matching is involved, we make the answer interpretable, using external knowledge bases composed of structured lexical definitions to generate natural language justifications that explain  ...  Entailment scenarios can range from a simple syntactic variation to more complex semantic relationships between pieces of text, but most approaches try a one-size-fits-all solution that usually favors  ...  Some text entailment approaches focus on exploring the syntactic structures of T and H, trying to transform the syntactic representation of T into that of H to determine whether they are equivalent and  ... 
arXiv:2009.12431v1 fatcat:cqlnab54yvdyjevzij7yzaxsaq

Syntactic REAP.PT: Exercises on Clitic Pronouning

Tiago Freitas, Jorge Baptista, Nuno Mamede, Marc Herbstritt
2013 Symposium on Languages, Applications and Technologies  
It proved invaluable in easing the development of this complex exercise, and is expected to make a relevant step forward in the development of future syntactic exercises, with the potential of becoming  ...  The emerging interdisciplinary field of Intelligent Computer Assisted Language Learning (ICALL) aims to integrate the knowledge from computational linguistics into computer-assisted language learning (  ...  Current Syntactic Exercises on Pronominalization There are several pronominalization exercises in textbooks and on-line resources: given three forms of pronouns, choose the right one to replace the signalled  ... 
doi:10.4230/oasics.slate.2013.271 dblp:conf/slate/FreitasBM13 fatcat:fwny65x32zgnfisjx5pgv5kjg4


Saad Salem Alshamrani
2021 Occasional Papers in the Development of English Education  
To this affect, the researcher utilized two sources of data for reliable and valid outcomes.  ...  The researcher gives a special attention to lexical and syntactical translational mistakes and errors.  ...  It mainly attempted to investigate such translational potential exercises at lexical and syntactical levels and the possible triggers causing such linguistic practice to come into play.  ... 
doi:10.21608/opde.2021.195308 fatcat:m5zrmqdpxnejfh5lmph7a4wwpi

The components of paraphrase evaluations

Philip M. McCarthy, Rebekah H. Guess, Danielle S. McNamara
2009 Behavior Research Methods  
AUTHOR NOTE This research was supported in part by the Institute for Education Sciences (Grants R305GA080589, R305G020018-02, and R305G040046), and in part by the National Science Foundation (Grant IIS  ...  Testing the Validity of the Model To test the validity of the model, we generated a new composite variable based on the B-weights of the model generated from the training set data (see Table 5 ).  ...  Testing the Validity of the Computational Model To test the validity of the computational model, we generated a new composite variable based on the model generated from the training set data (see Table  ... 
doi:10.3758/brm.41.3.682 pmid:19587179 fatcat:slk7jkcllne4hjw3bip3mnv3wu

Lexical and Syntactic Competency through Language Camp Activities Based on Multiple Intelligence Approach

Sasiwimon Sutthisan
2018 International Journal of Pedagogy and Teacher Education  
The attempts of the present research were 1) to investigate the students' problems in terms of lexical and syntactic usage in Language camp prior to the implementation of the activities based on multiple  ...  intelligence approach 2) to develop the students in terms of lexical and syntactic used in Language camp and 3) to compare the students' learning achievement in terms of lexical and syntactic used in  ...  ACKNOWLEDGEMENTS The researcher would like to express sincere appreciation to all those who assisted until the completion of this paper.  ... 
doi:10.20961/ijpte.v2i0.25146 fatcat:2fbdmzxy2nfitac7knmpsd7cw4

Automatic Generation of Exercises for Second Language Learning from Parallel Corpus Data

2021 International Journal of TESOL Studies  
We present an approach to generate a novel type of language learning exercise from a large parallel corpus based on movie subtitles.  ...  It combines two elements which have proven to be effective for language learning: a gamified approach, to awaken the students' competitive desire, and the identification of syntactic structures and vocabulary  ...  Acknowledgements This research is partly supported by the Swiss National Science Foundation under grant P2ZHP1_184212 through the project "From parallel corpora to multilingual exercises -Making use of  ... 
doi:10.46451/ijts.2021.06.05 fatcat:z5i4rgd46zg4xljgja6g6hzhve
« Previous Showing results 1 — 15 out of 5,666 results