scholarly journals AQG: Arabic Question Generator

2020 ◽  
Vol 34 (6) ◽  
pp. 721-729
Author(s):  
Kheira Z. Bousmaha ◽  
Nour H. Chergui ◽  
Mahfoud Sid Ali Mbarek ◽  
Lamia Belguith Hadrich
Keyword(s):  
Natural Language ◽  
Arabic Language ◽  
Semantic Role ◽  
Question Generation ◽  
Generator System ◽  
Semantic Role Labelling ◽  
Natural Language Process ◽  
Automatic Question Generation ◽  
F Measure

The Arabic natural language process (ANLP) community does not have an automatic generator of questions for texts in the Arabic language. Our objective is to provide it one. This paper presents a novel automatic question generation approach that generates questions as a form of support for children learning through the platform QUIZZITO. Our approach combines the semantic role labelling of PropBank (SRL) and the flexibility of question models. It essentially relates to an approach of instantiation model of representation based on an analysis focused on the semantics. This allowed us to capture the maximum sense of sentence given the flexibility of the grammar of the Arabic language. This model was written in a set of Patterns and Templates based on the REGEX languages. Our goal is to enrich Quizzito's online quiz platform, which contains more than 254.5k quizzes, and to provide it with a generator of Arabic language questions for children's texts. Our Arabic Question Generator system (AQG) is functional and reaches up to 86% f-measure.

scholarly journals Steganography Arabic Text Based on Natural Language Process Documents

2018 ◽  
Vol 1 (25) ◽  
pp. 457-480
Author(s):  
Hanaa M. Ahmed ◽  
Maisa'a A. A. Khohder
Keyword(s):  
Singular Value Decomposition ◽  
Natural Language ◽  
Rapid Development ◽  
Arabic Language ◽  
Singular Value ◽  
Secret Message ◽  
Linguistic Steganography ◽  
The One ◽  
Value Decomposition ◽  
Natural Language Process

: Obscurity is a main reason whereas computers can not know natural language. It have made great transaction steps trend developing instrument to morphological and syntactic analyzers for Arabic . One of the manners used in security areas is  steganography. The rapid development of steganography scripts, it is a large security and confidentiality problem, it becomes necessary to find appropriate protection because of the significance, accuracy and sensitivity of the data during transmitted. In this research is offer in a new method and to use one level to hide, this level is hiding by embedding and addition. The one level is embed a secret message twice, one bit in the LSB in the FFT and the addition of one kashida and add Single-Double Quotation in the same secret message. Using Random Singular Value Decomposition (RSVD) is NRG to find positions that are hiding within the text.      Linguistic steganography is covering all the techniques that deal with using written natural language to hide secret message. in this research presents a linguistic steganography for scripts written in Arabic language, using kashida, Single-Double Quotation and Fast Fourier Transform on the bases of using new technique entitled Random Singular Value Decomposition  (RSVD) as allocation to hide secret message. The proposed approach is an attempt to present a transform linguistic steganography using one level for hiding to improve implementation of kashida and Single-Double Quotation , and improve the security of the secret message by using Random Singular Value Decomposition  (RSVD). Are testing this method in terms of security and capacity, transparency, and robustness and this is way better than previous methods. The proposed algorithm ideal steganography properties.

scholarly journals Automatic Question Generation using Sequence to Sequence RNN Model

2020 ◽  
Vol 9 (5) ◽  
pp. 1799-1803
Keyword(s):  
Natural Language ◽  
Short Term Memory ◽  
Question Generation ◽  
Level Information ◽  
Core Components ◽  
Memory Power ◽  
Long Short Term Memory ◽  
The Impact ◽  
Automatic Question Generation ◽  
System Focus

Automatic Question Generation (AQG) has recently received growing focus in the processing of natural language (NLP). This attempts to create questions from a text paragraph, where certain sub-spans of the passage in question will answer the questions produced.. Traditional methods predominantly use rigid heuristic rules to turn a sentence into related questions. In this research, we suggest using the neural encoder-decoder model to produce substantive and complex questions from the sentences of natural language. We apply a attention-based sequence to sequence learning paradigm for the task and analyze the impact of encoding sentence vs. knowledge at paragraph level. Information retrieval and NLP are the core components of AQG. It incorporates the application of production rules; recurrent neural network (RNN) based encoder-decoder sequence to sequence (seq2seq) models, and other intelligent techniques. RNN is used because of its long short term memory power (LSTM).The proposed system focus on generating factual WH type questions.

Knowledge Acquisition Through Ontologies from Medical Natural Language Texts

2017 ◽  
Vol 10 (4) ◽  
pp. 56-69 ◽  
Author(s):  
José Medina-Moreira ◽  
Katty Lagos-Ortiz ◽  
Harry Luna-Aveiga ◽  
Oscar Apolinario-Arzube ◽  
María del Pilar Salas-Zárate ◽  
...  
Keyword(s):  
Life Cycle ◽  
General Solution ◽  
Natural Language ◽  
The Other ◽  
Semantic Role ◽  
Semantic Role Labeling ◽  
Clinical Knowledge ◽  
Biomedical Ontologies ◽  
Biomedical Field ◽  
F Measure

Ontologies are used to represent knowledge and they have become very important in the Semantic Web era. Ontologies evolve continuously during their life cycle to adapt to new requirements and needs, especially in the biomedical field, where the number of ontologies and their complexity have increased during the last years. On the other hand, a vast amount of clinical knowledge resides in natural language texts. For these reasons, building and maintaining biomedical ontologies from natural language texts is a relevant and challenging issue. In order to provide a general solution and to minimize the experts' participation during the ontology enriching process, a methodology for extracting terms and relations from natural language texts is proposed in this work. This framework is based on linguistic and statistical methods and semantic role labeling technologies, having been validated in the domain of diabetes, where they have obtained encouraging results with an F-measure of 82.1% and 79.9% for concepts and relations, respectively.

Automatic question generation based on sentence structure analysis using machine learning approach

2021 ◽  
pp. 1-31
Author(s):  
Miroslav Blšták ◽  
Viera Rozinajová
Keyword(s):  
Machine Learning ◽  
Natural Language ◽  
Language Processing ◽  
State Of The Art ◽  
Sentence Structure ◽  
Question Generation ◽  
Transformation Rules ◽  
Input Text ◽  
Automatic Question Generation

Abstract Automatic question generation is one of the most challenging tasks of Natural Language Processing. It requires “bidirectional” language processing: first, the system has to understand the input text (Natural Language Understanding), and it then has to generate questions also in the form of text (Natural Language Generation). In this article, we introduce our framework for generating the factual questions from unstructured text in the English language. It uses a combination of traditional linguistic approaches based on sentence patterns with several machine learning methods. We first obtain lexical, syntactic and semantic information from an input text, and we then construct a hierarchical set of patterns for each sentence. The set of features is extracted from the patterns, and it is then used for automated learning of new transformation rules. Our learning process is totally data-driven because the transformation rules are obtained from a set of initial sentence–question pairs. The advantages of this approach lie in a simple expansion of new transformation rules which allows us to generate various types of questions and also in the continuous improvement of the system by reinforcement learning. The framework also includes a question evaluation module which estimates the quality of generated questions. It serves as a filter for selecting the best questions and eliminating incorrect ones or duplicates. We have performed several experiments to evaluate the correctness of generated questions, and we have also compared our system with several state-of-the-art systems. Our results indicate that the quality of generated questions outperforms the state-of-the-art systems and our questions are also comparable to questions created by humans. We have also created and published an interface with all created data sets and evaluated questions, so it is possible to follow up on our work.

Knowledge Acquisition Through Ontologies from Medical Natural Language Texts

2020 ◽  
pp. 1023-1037
Author(s):  
José Medina-Moreira ◽  
Katty Lagos-Ortiz ◽  
Harry Luna-Aveiga ◽  
Oscar Apolinario-Arzube ◽  
María del Pilar Salas-Zárate ◽  
...  
Keyword(s):  
Life Cycle ◽  
General Solution ◽  
Semantic Web ◽  
Natural Language ◽  
Statistical Methods ◽  
The Other ◽  
Semantic Role ◽  
Semantic Role Labeling ◽  
Biomedical Field ◽  
F Measure

Ontologies are used to represent knowledge and they have become very important in the Semantic Web era. Ontologies evolve continuously during their life cycle to adapt to new requirements and needs, especially in the biomedical field, where the number of ontologies and their complexity have increased during the last years. On the other hand, a vast amount of clinical knowledge resides in natural language texts. For these reasons, building and maintaining biomedical ontologies from natural language texts is a relevant and challenging issue. In order to provide a general solution and to minimize the experts' participation during the ontology enriching process, a methodology for extracting terms and relations from natural language texts is proposed in this work. This framework is based on linguistic and statistical methods and semantic role labeling technologies, having been validated in the domain of diabetes, where they have obtained encouraging results with an F-measure of 82.1% and 79.9% for concepts and relations, respectively.

scholarly journals Automatic Question Generation (AQG) Dari Dokumen Teks Bahasa Indonesia Berdasarkan Non-Factoid Quesion

2018 ◽  
Vol 5 (2) ◽  
pp. 217
Author(s):  
Aminudin Aminudin ◽  
Azhari SN ◽  
Baaras Ahmad
Keyword(s):  
Naive Bayes ◽  
Naïve Bayes ◽  
Bayes Classifier ◽  
Question Generation ◽  
Knowledge Assets ◽  
The Right ◽  
The Given ◽  
Automatic Question Generation ◽  
F Measure ◽  
Bahasa Indonesia

<p class="Abstrak"><em><span lang="IN">Automatic Question Generation</span></em><span lang="IN"> (AQG) adalah sistem yang dapat membangkitkan pertanyaan secara otomatis dari teks atau dokumen dengan menggunakan metode atau pola-pola tertentu. Diharapkan sistem AQG yang dikembangkan bekerja seperti halnya manusia membuat pertanyaan setelah diberikan suatu teks. <span class="longtext"><span>Manusia dapat membuat pertanyaan, dikarenakan manusia dapat memahami teks yang diberikan dan berdasarkan pengetahuan-pengetahuan yang dimilikinya. Untuk mengembangkan sistem AQG penelitian ini, dilakukan kombinasi beberapa metode diantaranya algoritme <em>Naive Bayes Classifier</em> untuk mengklasifikasikan kalimat ke dalam jenis kalimat <em>non-factoid</em>. Chunking labelling untuk memberikan label pada masing-masing kalimat dari hasil klasifikasi dan pendekatan template untuk mencocokan hasil kalimat dengan template pertanyaan yang dibuat. Hasil pertanyaan yang dihasilkan oleh sistem akan diukur berdasarkan paramater yang telah ditentukan yang didasarkan atas pengukuran recall, precision dan F-Measure. Dengan adanya sistem AQG ini diharapkan dapat membantu guru mata pelajaran Biologi untuk membuat pertanyaan secara otomatis dan efektif serta efisien.</span></span></span></p><p class="Abstrak"> </p><p class="Abstrak">Abstract</p><p><em>Automatic Question Generation (AQG) is a system can generate question with automatically from text or document by using methods or certain patterns. Expected system AQG developed works like it does humans make create a question after being given a text. Humans can create a question, because humans can understand the given text and based on knowledge assets. To develop the system of AQG in this research, will do a combination of several methods including Naïve Bayes Clasifier algorithm to classify the sentence into a kind of non-sentence factoid. Chunking labelling to provide labels on each sentence and template approach to match the right results sentences with question templates created. The results of the question that are generated by the system will be measured based on predetermined parameters required that is based on the measuring precision, recall and F-Measure. With the existence of the AQG system is expected to help teachers of Biology subjects to make the question automatically, effectively and efficiently.</em></p>

Sign in / Sign up

Export Citation Format

Share Document