Filters








200 Hits in 3.0 sec

Conversational Question Answering in Low Resource Scenarios: A Dataset and Case Study for Basque

Arantxa Otegi, Aitor Gonzalez-Agirre, Jon Ander Campos, Aitor Soroa, Eneko Agirre
2020 International Conference on Language Resources and Evaluation  
Conversational Question Answering (CQA) systems meet user information needs by having conversations with them, where answers to the questions are retrieved from text.  ...  There exist a variety of datasets for English, with tens of thousands of training examples, and pre-trained language models have allowed to obtain impressive results.  ...  Jon Ander Campos enjoys a doctoral grant from the Spanish MECD. We also acknowledge the support of Google Cloud.  ... 
dblp:conf/lrec/OtegiGCSA20 fatcat:guuf6vad5bfcpa7awlfuup46s4

Mining Text with Pimiento

J.J. Garcia Adeva, R. Calvo
2006 IEEE Internet Computing  
In particular, we introduce Pimiento, a new Object-Oriented Application Framework (OOAF) for text mining.  ...  Information systems are using an increasing amount of unstructured information in the form of text.  ...  • Information Extraction (IE): search engines like Google can not provide answers to specific questions (e.g. "how many papers has Dr. Who published?")  ... 
doi:10.1109/mic.2006.85 fatcat:kotc3bflqbbfvppimajpag3aby

Dependency Treebanks: Methods, Annotation Schemes and Tools [article]

Tuomo Kakkonen
2006 arXiv   pre-print
The methods used for building the resources, the annotation schemes applied, and the tools used (such as POS taggers, parsers and annotation software) are discussed.  ...  Acknowledgments The research reported in this work has been supported by the European Union under a Marie Curie Host Fellowship for Early Stage Researchers Training at MUL-TILINGUA, Bergen, Norway and  ...  The aim of this paper is to answer the following questions about the current state-ofart in dependency treebanking: • What kinds of texts do the treebanks consist of?  ... 
arXiv:cs/0610124v1 fatcat:ndrnaldljzgrzimthqc4ryjyku

Syntactic REAP.PT: Exercises on Clitic Pronouning

Tiago Freitas, Jorge Baptista, Nuno Mamede, Marc Herbstritt
2013 Symposium on Languages, Applications and Technologies  
A pioneer feedback system with detailed and automatically generated explanations for each answer is also presented, improving the learning experience, as stated in user comments.  ...  a syntactic exercise generation framework.  ...  Arikiturri [8, 9] is a modular and multilingual automatic question generation system. It is currently implemented for Basque and English language learning and science domains.  ... 
doi:10.4230/oasics.slate.2013.271 dblp:conf/slate/FreitasBM13 fatcat:fwny65x32zgnfisjx5pgv5kjg4

SENSEVAL-2: Overview

Philip Edmonds, Scott Cotton
2001 International Workshop on Semantic Evaluation  
This paper gives an overview of SENSEV AL-2, discussing the evaluation exercise, the tasks, the scoring system, and the results. It ends with some recommendations for future evaluation exercises.  ...  SENSEV AL-2: The Second International Workshop on Evaluating Word Sense Disambiguation Systems was held on July 5-6, 2001.  ...  Specifically, it accommodated the multi-lingual nature of the data by using an XML document type definition which allowed for a flexible mapping from lexical items to their textual instances.  ... 
dblp:conf/semeval/EdmondsC01 fatcat:73gle5epkfabxprptc55dcucpm

An Environment for Automatic Test Generation

Nina Stancheva, Asya Stoyanova-Doycheva, Stanimir Stoyanov, Ivan Popchev, Vanya Ivanova
2017 Cybernetics and Information Technologies  
This paper presents an environment which generates tests automatically. It is designed for assistance in the software engineering education and is part of the Virtual Education Space.  ...  The test generation is supported by specialized ontologies, which are served by two intelligent agents known as Questioner Operative and Assessment Operative.  ...  In addition, a novel framework for web-based testing with automatic assessment is also discussed in this paper. The framework is tested in a mathematics question data base.  ... 
doi:10.1515/cait-2017-0025 fatcat:yidvvb3ckjbvbargkbawhhpyri

Natural Language Processing and Language Technologies for the Basque Language

Itziar Gonzalez-Dios, Begoña Altuna
2022 Cuadernos Europeos de Deusto  
In this paper, we present an overview of the natural language processing and language technology resources developed for Basque, their impact in the process of making Basque a "digital language" and the  ...  In order to develop advanced systems that are considered the basics for an efficient digital communication (e.g. machine translation systems, text-to-speech and speech-to-text converters and digital assistants  ...  Acknowledgements This survey has been partially funded by Basque Government postdoctoral grant POS 2021 2 0030.  ... 
doi:10.18543/ced.2477 fatcat:erhjfz7jx5fhrihaapbmd7dnd4

Tapping into the Power of Automatic Question Generation

Ibrahim EldesokyFattoh, Amal Elsayed Aboutabl, Mohamed Hassan Haggag
2014 International Journal of Computer Applications  
Question Generation (QG) is an important element of learning environments, information seeking systems, help systems, and other applications.  ...  There are a number of distinct research subfields which are concerned with the Automatic Question Generation (AQG) Systems.  ...  An automatic Sentence-to-Question generation system presented in [17] , where given a sentence, the system generates a set of questions for which the sentence contains, implies, or needs answers.  ... 
doi:10.5120/18035-7636 fatcat:b7xp4telhfg23g4wizz374rzz4

An Automated Multiple-Choice Question Generation Using Natural Language Processing Techniques [article]

Chidinma A. Nwafor, Ikechukwu E. Onyenwe
2021 arXiv   pre-print
In this paper, we present an NLP-based system for automatic MCQG for Computer-Based Testing Examination (CBTE).We used NLP technique to extract keywords that are important words in a given lesson material  ...  Despite its usefulness, manually creating sizeable, meaningful and relevant questions is a time-consuming and challenging task for teachers.  ...  [5] developed ArikIturri, an AQG for Basque language test questions.  ... 
arXiv:2103.14757v1 fatcat:pgo5pwwj7fawvjqd5arhtysoue

The Design of Tests with Multiple Choice Questions Automatically Generated from Essays in a Learner Corpus

Olga Vinogradova, Nikita Login
2017 Social Science Research Network  
Acknowledgement The article was prepared within the framework of the Academic Fund Program at the National Research University Higher School of Economics (HSE) in 2016-2017(grant №16-05-0057) and the Russian  ...  Aldabe Arregi [2011] describes the creation and implementation of a system called ArikIturri, a computer-assisted learning tool for Basque and English languages, which generates questions automatically  ...  This system uses a corpus-based approach and can generate questions of five types: error correction, fill-in-the-blank questions, word formation, multiple choice questions and short answer questions.  ... 
doi:10.2139/ssrn.3087215 fatcat:el34vh3cqzewnc4g6aiv5wogji

An Automated Multiple-Choice Question Generation using Natural Language Processing Techniques

Chidinma A. Nwafor, Ikechukwu E. Onyenwe
2021 International Journal on Natural Language Computing  
In this paper, we present an NLP-based system for automatic MCQG for Computer-Based Testing Examination (CBTE).We used NLP technique to extract keywords that are important words in a given lesson material  ...  Despite its usefulness, manually creating sizeable, meaningful and relevant questions is a time-consuming and challenging task for teachers.  ...  [5] developed ArikIturri, an AQG for Basque language test questions.  ... 
doi:10.5121/ijnlc.2021.10201 fatcat:4yojvcm7sjcjrehcukh7maoxmi

What Happened in CLEF2009: Introduction to the Working Notes

Carol Peters
2009 Conference and Labs of the Evaluation Forum  
Appendices are also included containing run statistics for the Ad Hoc and Grid@CLEF tracks, and a list of all participating institutions.  ...  These Working Notes contain descriptions of the experiments conducted within CLEF 2009 -the tenth in a series of annual system evaluation campaigns.  ...  Participants had to conduct experiments according to the CIRCO (Coordinated Information Retrieval Components Orchestration) protocol, an XML-based framework which allows for a distributed, loosely-coupled  ... 
dblp:conf/clef/Peters09b fatcat:p5tpt2abovetffp3tjip2n3n6a

PARTHENOS D2.3 Report on the assessment of data policies and standardization

Steven Krauwer, Sara Di Giorgio, Karolien Verbrugge, Claus Spiecker, Christos Chatzimichail, Emiliano Degl'Innocenti, Hélène Gautier, Roberta Giacomi, Lina Henriksen, Klaus Illmayer, Antonio Davide Madonna, Maurizio Sanesi
2017 Zenodo  
provides collect needs and experiences from the project constituencies (research communities, ESFRI and non-ESFRI Research Infrastructures, other projects) and to organize and feed them as requirements for  ...  The framework includes an abstract data model and an XML serialization of that model for representing annotations of primary data.  ...  However, part of the questions are aimed at institutions and researchers will not be able to answer these questions.  ... 
doi:10.5281/zenodo.2662524 fatcat:kovfreaafrdfdlmzhgka6nshdq

The stability and breakup of nations: a quantitative analysis

Klaus Desmet, Michel Le Breton, Ignacio Ortuño-Ortín, Shlomo Weber
2011 Journal of economic growth (Boston)  
We also provide empirical support for the use of genetic distances as a proxy for cultural heterogeneity. JEL Classification Codes: H77, D70, F02, H40.  ...  As a test of the theory, we show that the model can account for the breakup of Yugoslavia and the dynamics of its disintegration.  ...  For example, suppose that question i has three possible answers, a 1 , a 2 and a 3 .  ... 
doi:10.1007/s10887-011-9068-z fatcat:y3x5u5gsoncabc62sp7pi362ue

The Stability and Breakup of Nations: A Quantitative Analysis

Klaus Desmet, Michel Le Breton, Ignacio Ortuno-Ortin, Shlomo Weber
2009 Social Science Research Network  
We also provide empirical support for the use of genetic distances as a proxy for cultural heterogeneity. JEL Classification Codes: H77, D70, F02, H40.  ...  As a test of the theory, we show that the model can account for the breakup of Yugoslavia and the dynamics of its disintegration.  ...  For example, suppose that question i has three possible answers, a 1 , a 2 and a 3 .  ... 
doi:10.2139/ssrn.1586772 fatcat:dew6arxrmbd5te5ro2iz4cl2qi
« Previous Showing results 1 — 15 out of 200 results