Search results for: question

Authors: Aya Mousa, Mahmoud Alsaheb

Abstract:

Question Answering System (QAS) aims to provide the most suitable answer to the user's question in any natural language. In the recent future, it will be a future version of web search. Much research has already been done on answering Arabic factoid questions and achieved good accuracy. In contrast, the progress in research on Arabic non-factoid question answering is still immature. In this survey, we summarize, discuss, and compare the existing Arab non-factoid question-answering systems to identify the limitations and the achievements that were accomplished. Furthermore, we investigate the challenges in developing non-factoid Arabic QAS and the possible future improvements. The survey is written to help the researchers to understand the field of Arabic non-factoid QAS and to motivate them to utilize different approaches to develop and enhance the Non-factoid Arabic QAS

Keywords: Arabic question answering system, non-factoid question answering, Arabic NLP, question answering

Procedia PDF Downloads 53

Authors: Wided Bakari, Patrice Bellot, Omar Trigui, Mahmoud Neji

Abstract:

This article constitutes an opening to think of the modeling and analysis of Arabic texts in the context of a question-answer system. It is a question of exceeding the traditional approaches focused on morphosyntactic approaches. Furthermore, we present a new approach that analyze a text in order to extract correct answers then transform it to logical predicates. In addition, we would like to represent different levels of information within a text to answer a question and choose an answer among several proposed. To do so, we transform both the question and the text into logical forms. Then, we try to recognize all entailment between them. The results of recognizing the entailment are a set of text sentences that can implicate the user’s question. Our work is now concentrated on an implementation step in order to develop a system of question-answering in Arabic using techniques to recognize textual implications. In this context, the extraction of text features (keywords, named entities, and relationships that link them) is actually considered the first step in our process of text modeling. The second one is the use of techniques of textual implication that relies on the notion of inference and logic representation to extract candidate answers. The last step is the extraction and selection of the desired answer.

Keywords: NLP, Arabic language, question-answering, recognition text entailment, logic forms

Procedia PDF Downloads 306

Authors: Touila Ahmed, Elie Louis, Hamza Gharbi

Abstract:

State of the art question answering models have recently shown impressive performance especially in a zero-shot setting. This approach is particularly useful when confronted with a highly diverse domain such as the legal field, in which it is increasingly difficult to have a dataset covering every notion and concept. In this work, we propose a flexible generative question answering approach to contract analysis as well as a weakly supervised procedure to leverage unannotated data and boost our models’ performance in general, and their zero-shot performance in particular.

Keywords: question answering, contract analysis, zero-shot, natural language processing, generative models, self-supervision

Procedia PDF Downloads 136

Authors: Sara Tusian, Zahra Salehi Motaahed, Narges Sajjadie, Nikoo Dialame

Abstract:

One of the methods which have frequently been used in Quran is the “question”. In the Quran, in addition to the content, methods are also important. Using analysis-interpretation method, the present study has investigated Quranic questions, and extracted its functions from educational perspective. In so doing, it has first investigated all the questions in Quran and then taking the three-stage classification of education into account, it has offered question functions. The results obtained from this study suggest that question functions in Quran are presented in three categories: the preparation stage (including preparation of the audience, revising the insights, and internal Evolution); main body (including the granting the insight, and elimination of intellectual negligence and the question of innate and logical axioms, the introducting of the realm of thinking, creating emotional arousal and alleged in the claim) and the third stage as modification and revision (including invitation to move in the framework of tasks using the individual beliefs to reveal the contradictions and, Error detection and contribution to change the function) that each of which has a special role in the education process.

Keywords: education, question, Quranic questions, Quran

Procedia PDF Downloads 469

Authors: M. H. Imam, Imran A. Tasadduq, Abdul-Rahim Ahmad, Fahd M. Aldosari

Abstract:

Learning outcomes of a course (CLOs) and the abilities at the time of graduation referred to as Student Outcomes (SOs) are required to be assessed for ABET accreditation. A question in an assessment must target a CLO as well as an SO and must represent a required level of competence. This paper presents the idea of an Expert System (ES) to select a proper question to satisfy ABET accreditation requirements. For ES implementation, seven attributes of a question are considered including the learning outcomes and Bloom’s Taxonomy level. A database contains all the data about a course including course content topics, course learning outcomes and the CLO-SO relationship matrix. The knowledge base of the presented ES contains a pool of questions each with tags of the specified attributes. Questions and the attributes represent expert opinions. With implicit rule base the inference engine finds the best possible question satisfying the required attributes. It is shown that the novel idea of such an ES can be implemented and applied to a course with success. An application example is presented to demonstrate the working of the proposed ES.

Keywords: expert system, student outcomes, course learning outcomes, question attributes

Procedia PDF Downloads 221

Authors: Aviv Yaniv, Ron Ben Arosh, Nadav Gasner, Michael Konviser, Arbel Yaniv

Abstract:

This paper introduces two methods for the evaluation of Question Decomposition Meaning Representation (QDMR) as predicted by sequence-to-sequence model and COPYNET parser for natural language questions processing, motivated by the fact that previous evaluation metrics used for this task do not take into account some characteristics of the representation, such as partial ordering structure. To this end, several heuristics to extract such partial dependencies are formulated, followed by the hereby proposed evaluation methods denoted as Proportional Graph Matcher (PGM) and Conversion to Normal String Representation (Nor-Str), designed to better capture the accuracy level of QDMR predictions. Experiments are conducted to demonstrate the efficacy of the proposed evaluation methods and show the added value suggested by one of them- the Nor-Str, for better distinguishing between high and low-quality QDMR when predicted by models such as COPYNET. This work represents an important step forward in the development of better evaluation methods for QDMR predictions, which will be critical for improving the accuracy and reliability of natural language question-answering systems.

Keywords: NLP, question answering, question decomposition meaning representation, QDMR evaluation metrics

Procedia PDF Downloads 30

Authors: Igor A. Podgorny

Abstract:

TurboTax AnswerXchange is a social Q/A system supporting users working on federal and state tax returns. Content quality and popularity in the AnswerXchange can be predicted with propensity models using attributes of the question and answer. Using uplift modeling, we identify features of questions and answers that can be modified during the question-asking and question-answering experience in order to optimize the AnswerXchange content quality. We demonstrate that adding details to the questions always results in increased question popularity that can be used to promote good quality content. Responding to close-ended questions assertively improve content quality in the AnswerXchange in 90% of cases. Answering knowledge questions with web links increases the likelihood of receiving a negative vote from 60% of the askers. Our findings provide a rationale for employing the uplift modeling approach for AnswerXchange operations.

Keywords: customer relationship management, human-machine interaction, text mining, uplift modeling

Procedia PDF Downloads 219

Authors: Haozheng Luo, Ruiyang Qin

Abstract:

People with visual impairments urgently need assistance, not only on the fundamental tasks such as guiding and retrieving objects but on the advanced like picturing the new environments. More than a guiding dog, they might want such devices that can provide linguistic interaction. Building on this idea, we aim to study the interaction between the robot agent and visually impaired people. In our research, we are going to develop a robot agent that will be able to analyze the test environment and answer the participants’ questions. We also will study the relevant issues regarding the interaction between human beings and the robot agents to figure out which and how the factors will affect the interaction.

Keywords: HRI, video question answering, visual question answering, natural language processing

Procedia PDF Downloads 185

Authors: S. Shujan, A. T. Rupasinghe, N. L. Gunawardena

Abstract:

Numerous studies have determined that there is a direct correlation between the successful interviewee and the nonverbal behavioral patterns of that person during the interview. In this study, we focus on formations of interview questions in such a way that, it gets an opportunity for assessing interviewee through the answers using the nonverbal behavioral cues. From all the nonverbal behavioral factors we have identified, in this study priority is given to the ‘facial expression variations’ with the assistance of facial expression analytics tool; this research proposes a novel approach in question formation for the assessment of interviewees in ‘Software Industry’.

Keywords: assessments, hirability, interviews, non-verbal behaviour patterns, question formation

Procedia PDF Downloads 282

Authors: Rahma Amri, Narjès Bellamine Ben Saoud

Abstract:

Sustainable development or sustainability is one of the most urgent issues in actual debate in almost domains. Particularly the significant way the software pervades our live should make it in the center of sustainability concerns. The social aspects of sustainability haven’t been well studied in the context of software systems and still immature research field that needs more interest among researchers’ community. This paper presents a Goal-Question-Metric based approach to assess social sustainability of software systems. The approach is based on a generic social sustainability model taken from Social sciences.

Keywords: software assessment approach, social sustainability, goal-question-metric paradigm, software project metrics

Procedia PDF Downloads 360

Authors: Olga Koutsika

Abstract:

The paper deals primarily with the question of the legal framework of non-orbital flights. The submission is based upon two pillars, starting with the ill-defined current legal regime and proceeding to further recommendations for the prospective legal regime for non-orbital flights. For this reason, the paper focuses on certain key legal aspects of the topic, including among other things liability, responsibility, jurisdiction, registration and authorisation. Furthermore, taking into consideration the hybrid nature of both the craft conducting non-orbital flights and of the flights themselves, which exit airspace but do not enter an orbit in outer space, the paper addresses each legal question from the perspective of both air law and space law and concludes to a number of recommendations regarding the applicability of each legal regime for each legal question individually.

Keywords: current regime, legal framework, non-orbital flights, prospective regime

Procedia PDF Downloads 347

Authors: Min Woo Lee, Kyoung Seok Kim

Abstract:

We made an effort to resolve a research question, which is about the relationship between employees’ corporate social responsibility (CSR) participation and their organizational citizenship behavior (OCB), and an effect of profiles of job characteristics. To test the question, we divided sample into two groups that have the profiles of each job characteristic. One group had high level on the five dimensions of job characteristic (D group), whereas another group had low level on the dimensions (R group). As a result, regression analyses showed that the relationship between CSR participation and OCB is positive in the D group, but the relationship is not significant in the R group. The results raise a question to the argument of recent studies showing that there is positive relationship between the CSR and the OCB. Implications and limitations are demonstrated in the conclusion.

Keywords: CSR, OCB, job characteristics, cluster analysis

Procedia PDF Downloads 287

Authors: Qisheng Hu, Jianglei Han, Yue Yang, My Hoa Ha

Abstract:

When a company is considering purchasing software for commercial use, contract risk assessment is critical to identify risks to mitigate the potential adverse business impact, e.g., security, financial and regulatory risks. Contract risk assessment requires reviewers with specialized knowledge and time to evaluate the legal documents manually. Specifically, validating contracts for a software vendor requires the following steps: manual screening, interpreting legal documents, and extracting risk-prone segments. To automate the process, we proposed a framework to assist legal contract document risk identification, leveraging pre-trained deep learning models and natural language processing techniques. Given a set of pre-defined risk evaluation problems, our framework utilizes the pre-trained transformer-based models for question-answering to identify risk-prone sections in a contract. Furthermore, the question-answering model encodes the concatenated question-contract text and predicts the start and end position for clause extraction. Due to the limited labelled dataset for training, we leveraged transfer learning by fine-tuning the models with the CUAD dataset to enhance the model. On a dataset comprising 287 contract documents and 2000 labelled samples, our best model achieved an F1 score of 0.687.

Keywords: contract risk assessment, NLP, transfer learning, question answering

Procedia PDF Downloads 91

Authors: Helen Ngozi Ibe, Chimmuanya Ezere

Abstract:

The study investigated the effect of Question Answer Relationships (QARs) in science reading on secondary school students’ achievement in Biology in Owerri Education Zone II of Imo State. The study adopted a quasi-experimental design and was guided by two research questions and two hypotheses. The sample comprised of 67 SS2 Biology students. The sample was drawn using random sampling technique. One researcher made instrument titled: Biology Achievement Test (BAT) was used for collecting the data of the study. The reliability of the instrument was established using Kuder Richardson formula (KR-20) which yielded a reliability index of 0.85 and Cronbach alpha for the BSIRS with an index of 0.71. Research questions were answered using mean and standard deviation. T-test statistics was used to test the hypotheses at 0.05 level of significance. The major findings are that students exposed to QARs strategy in science reading had higher achievement mean scores in biology than students in the control group; there is no significant difference between the achievement mean scores of male and female students exposed to QARs. The researchers recommended that science teachers should teach students the Question Answer Relationship reading strategy and that science students should endeavour to use the question - answer relationship reading strategy in classroom and individual science reading in order to enhance high academic achievement in the subjects being read.

Keywords: academic achievement, biology, science reading, question-answer relationship

Procedia PDF Downloads 81

Authors: Saheed A. Gbadegeshin

Abstract:

Commercialization method is a means to make inventions available at the market for final consumption. It is described as an important tool for keeping business enterprises sustainable and improving national economic growth. Thus, there are several scholarly publications on it, either presenting or testing different methods for commercialization. However, young entrepreneurs, technologists and scientists would like to know the best method to commercialize their innovations. Then, this question arises: What is the best commercialization method? To answer the question, a systematic literature review was conducted, and practitioners were interviewed. The literary results revealed that there are many methods but new methods are needed to improve commercialization especially during these times of economic crisis and political uncertainty. Similarly, the empirical results showed there are several methods, but the best method is the one that reduces costs, reduces the risks associated with uncertainty, and improves customer participation and acceptability. Therefore, it was concluded that new commercialization method is essential for today's high technologies and a method was presented.

Keywords: commercialization method, technology, knowledge, intellectual property, innovation, invention

Procedia PDF Downloads 295

Authors: Matthew Heidman, Susan Dallabrida, Analice Costa

Abstract:

Background:Accuracy of caregiver reported outcomes is essential for infant growth and tolerability study success. Crying/fussiness, stool consistencies, and other gastrointestinal characteristics are important parameters regarding tolerability, and inter-caregiver reporting can see a significant amount of subjectivity and vary greatly within a study, compromising data. This study sought to elucidate how caregiver reported questions related to stool frequency are answered before and after a short amount of training and how training impacts caregivers’ understanding, and how they would answer the question. Methods:A digital survey was issued for 90 daysin the US (n=121) and 30 days in Mexico (n=88), targeting respondents with children ≤4 years of age. Respondents were asked a question in two formats, first without a line of training text and second with a line of training text. The question set was as follows, “If your baby had stool in his/her diaper and you changed the diaper and 10 min later there was more stool in the diaper, how many stools would you report this as?” followed by the same question beginning with “If you were given the instruction that IF there are at least 5 minutes in between stools, then it counts as two (2) stools…”.Four response items were provided for both questions, 1) 2 stools, 2) 1stool, 3) it depends on how much stool was in the first versus the second diaper, 4) There is not enough information to be able to answer the question. Response frequencies between questions were compared. Results: Responses to the question without training saw some variability in the US, with 69% selecting “2 stools”,11% selecting “1 stool”, 14% selecting “it depends on how much stool was in the first versus the second diaper”, and 7% selecting “There is not enough information to be able to answer the question” and in Mexico respondents selected 9%, 78%, 13%, and 0% respectively. However, responses to the question after training saw more consolidation in the US, with 85% of respondents selecting“2 stools,” representing an increase in those selecting the correct answer. Additionally in Mexico, with 84% of respondents selecting “1 episode” representing an increase in the those selecting the correct response. Conclusions: Caregiver reported outcomes are critical for infant growth and tolerability studies, however, they can be highly subjective and see a high variability of responses without guidance. Training is critical to standardize all caregivers’ perspective regarding how to answer questions accurately in order to provide an accurate dataset.

Keywords: infant nutrition, clinical trial optimization, stool reporting, decentralized clinical trials

Procedia PDF Downloads 67

Authors: Prathiksha Kamath, Pratibha Jamkhandi, Prateek Ghanti, Priyanshu Gupta, M. Lakshmi Neelima

Abstract:

Combining Image Captioning and Visual Question Answering (VQA) tasks have emerged as a new and exciting research area. The image captioning task involves generating a textual description that summarizes the content of the image. VQA aims to answer a natural language question about the image. Both these tasks include computer vision and natural language processing (NLP) and require a deep understanding of the content of the image and semantic relationship within the image and the ability to generate a response in natural language. There has been remarkable growth in both these tasks with rapid advancement in deep learning. In this paper, we present a comprehensive review of recent progress in combining image captioning and visual question-answering (VQA) tasks. We first discuss both image captioning and VQA tasks individually and then the various ways in which both these tasks can be integrated. We also analyze the challenges associated with these tasks and ways to overcome them. We finally discuss the various datasets and evaluation metrics used in these tasks. This paper concludes with the need for generating captions based on the context and captions that are able to answer the most likely asked questions about the image so as to aid the VQA task. Overall, this review highlights the significant progress made in combining image captioning and VQA, as well as the ongoing challenges and opportunities for further research in this exciting and rapidly evolving field, which has the potential to improve the performance of real-world applications such as autonomous vehicles, robotics, and image search.

Keywords: image captioning, visual question answering, deep learning, natural language processing

Procedia PDF Downloads 46

Authors: María José Núñez-Ruiz, Luis Álvarez-González, Cristian Olivares-Rodriguez, Benjamin Lazo-Letelier

Abstract:

This paper begins with some concept of formative assessment and the relationship with learning objective: contents objectives, processes objectives, and metacognitive objectives. Two methodologies are describes Evidence-Based teaching and Question Drive Instruction. To do formative assessments in larges classes a Classroom Response System (CRS) is needed. But most of CRS use only Multiple Choice Questions (MCQ), True/False question, or text entry; however, this is insufficient to formative assessment. To do that a new CRS, call FAMA was developed. FAMA support six types of questions: Choice, Order, Inline choice, Text entry, Associated, and Slider. An experiment participated in 149 students from four engineering careers. For results, Kendall's Range Correlation Analysis and descriptive analysis was done. In conclusion, there is a strong relation between contents question, process questions (ask in formative assessment without a score) and metacognitive questions, asked in summative assessment. As future work, the lecturer can do personalized teaching, because knows the behavior of all students in each formative assessment

Keywords: Python language, formative assessment, classroom response systems, evidence-Based teaching, question drive instruction

Procedia PDF Downloads 97

Authors: Anes Enakoa, Yawei Liang

Abstract:

Question Answering (QA) system is one of the most important and demanding tasks in the field of Natural Language Processing (NLP). In QA systems, the answer generation task generates a list of candidate answers to the user's question, in which only one answer is correct. Answer selection is one of the main components of the QA, which is concerned with selecting the best answer choice from the candidate answers suggested by the system. However, the selection process can be very challenging especially in Arabic due to its particularities. To address this challenge, an approach is proposed to answer questions with multiple answer choices for Arabic QA systems based on Textual Entailment (TE) recognition. The developed approach employs a Support Vector Machine that considers lexical, semantic and syntactic features in order to recognize the entailment between the generated hypotheses (H) and the text (T). A set of experiments has been conducted for performance evaluation and the overall performance of the proposed method reached an accuracy of 67.5% with C@1 score of 80.46%. The obtained results are promising and demonstrate that the proposed method is effective for TE recognition task.

Keywords: information retrieval, machine learning, natural language processing, question answering, textual entailment

Procedia PDF Downloads 114

Authors: Wided Bakari, Patrce Bellot, Mahmoud Neji

Abstract:

With the development of electronic media and the heterogeneity of Arabic data on the Web, the idea of building a clean corpus for certain applications of natural language processing, including machine translation, information retrieval, question answer, become more and more pressing. In this manuscript, we seek to create and develop our own corpus of pair’s questions-texts. This constitution then will provide a better base for our experimentation step. Thus, we try to model this constitution by a method for Arabic insofar as it recovers texts from the web that could prove to be answers to our factual questions. To do this, we had to develop a java script that can extract from a given query a list of html pages. Then clean these pages to the extent of having a database of texts and a corpus of pair’s question-texts. In addition, we give preliminary results of our proposal method. Some investigations for the construction of Arabic corpus are also presented in this document.

Keywords: Arabic, web, corpus, search engine, URL, question, corpus building, script, Google, html, txt

Procedia PDF Downloads 292

Authors: Shahzad Faisal, Khalid Iqbal, Atif Inayat

Abstract:

Internet is growing rapidly and new community-based content is added by people every second. With this fast growing community-based content, if a user requires answers of particular questions then reviews are required from experts or community. However, is difficult to get quality answers. Muslim community all over the world is seeking help to get their questions and issues discussed to get answers. Online web portals of religious schools and community based question answering sites are two big platforms to solve the issues of users. In case of religious schools, there are experts and qualified religious scholars (Mufti) who can give the expert opinion. However, the quality of community-based content cannot be guaranteed as it may not be an answer that satisfies the question of a user. Users on community based Q&A sites may be spammers or just criticizing the questioner instead of answering. In this paper, we research strategies to distinguish the right content naturally. As an experiment, we concentrate on Yahoo! Answers, and Quora, popular online Q&A sites; where questions are asked, answered, edited and organized by a large community of users. We present classification of data to categorize relevant and irrelevant answers. Specifically, we demonstrate that our framework can isolate quality answer from the rest with an exactness near that of people.

Keywords: answer classification, community based question and answering, evaluation and prediction of quality answer, quality assessment of content

Procedia PDF Downloads 306

Authors: Meghana Srivatsav, Timothy J. Luke, Par Anders Granhag, Aldert Vrij

Abstract:

The aim of this study was to understand how the phrasing of questions influences guilty suspects’ inferences regarding prior information held by the interviewer about the suspect’s crime-related activities. Three phrasing factors were explored namely specificity (crime-related details within questions), stressor (emphasis on the importance of the information in the question) and phase presentation (whether a specific activity was questioned about). 370 participants were recruited and randomly assigned into 6 different question-phrasing groups. Participants assumed the role of a suspect, read a crime narrative and an interview transcript based on the suspect’s activities. Participants responded to scales that measured their perception of interviewer’s knowledge (PIK) based on the questions posed by the interviewer in the interview transcripts. The researchers found that there is an effect of specific details revealed in the questions on the suspect’s perception of interviewer knowledge. Questioning about a specific activity also increased their perception of interviewer’s prior knowledge. However, the individual hypotheses were only partially supported. The study allowed the researchers to explore a psycholinguistic approach to investigate the underlying mechanisms of inferences drawn by suspects from the phrasing of investigative questions.

Keywords: police interviewing, question framing effects on suspects, suspect inferences from questions, suspect interviews

Procedia PDF Downloads 119

Authors: Mohammadreza Khanmohammadi, Noureddin Nakhostin Ansari, Soofia Naghdi

Abstract:

Purpose: Our study aimed to validate single item presenteeism question (SIPQ) into the Persian language for patients with low back pain. Background information: low back pain is a common health problem, and it is one of the most prevalent disorder in working people. There are the different subjective way to evaluate the effect of back pain on work productivity that one of them is by implementing single item presenteeism question. This question has not been validated into the Persian language. Method: Patients were asked to answer SIPQ and pain from 0 to 10 according to numerical rating scale (NRS). The functional rating index was administrated to evaluate construct validity. For test-retest reliability, almost 50 patients re-completed the Persian SIPQ. The construct validity of SIPQ was assessed by analyzing Spearman rank correlation between this question and the Persian version of Functional rating index questionnaire. To analyze test-retest reliability, we assessed intraclass correlation coefficient (agreement) (ICC agreement) (two-way random effects model, single measure). Results: The SIPQ score of two groups of patients (84 males, 16 females, mean age ±SD: 33.85±11.16 years, range: 19-67 years) and healthy subjects (48 male, 2 female ones, mean age ±SD: 24.24 ±8.07 years) was statistically significant. (Mann-Whitney U =198.00, P<.001). The Spearman correlation of data showed that there is a significant correlation between Persian SIPQ score and Persian FRI band (r= .559, P<.001). The ICC was .62. So, the analysis indicated good, test-retest reliability. Conclusion: This study showed that Persian version of SIPQ is reliable and valid when applied to back pain patients.

Keywords: cross cultural adaptation, economic burden, low back pain, Persian language, translation

Procedia PDF Downloads 383

Authors: Haya Sammana

Abstract:

A well-defined curricula must be adopted to meet the increasing complexity and diversity in the software applications. In reality, some IT majors such as computer science and computer engineering receive the software engineering education in a single course which is considered as a big challenged for the instructors and universities. Also, it requires students to gain the most of practical experiences that simulate the real work in software companies. Furthermore, we have noticed that there is no consensus on how, when and what to teach in that introductory course to gain the practical experiences that are required by the software companies. Because all of software engineering disciplines will not fit in just one course, so the course needs reasonable choices in selecting its topics. This arises an important question which is an essential one to ask: Is this course has the ability to formulate a true software engineer that meets the needs of industry? This question arises a big challenge in selecting the appropriate topics. So answering this question is very important for the next undergraduate students. During teaching this course in the curricula, the feedbacks from an undergraduate students and the keynotes of the annual meeting for an advisory committee from industrial side provide a probable answer for the proposed question: it is impossible to build a true software engineer who possesses all the essential elements of software engineering education such teamwork, communications skills, project management skills and contemporary industrial practice from one course and it is impossible to have a one course covering all software engineering topics. Besides the used teaching approach, the author proposes an implemented three supportive ways aiming for mitigating the expected risks and increasing the opportunity to build a true software engineer.

Keywords: software engineering course, software engineering education, software experience, supportive approach

Procedia PDF Downloads 329

Authors: Cholpassorn Sitthiwarongchai

Abstract:

The purposes of this paper were to search for the uniqueness of community products from Bang Khonthi District, Samut Songkram Province, Thailand and to create a proper brand for the community products. Four important questions were asked to identify the uniqueness of the community products. The first question: What is the brand of coconut sugar that community wants to imply? The answer was 100 percent authentic coconut sugar. The second question: What is the nature of this product? The answer was that it is a natural product without any harmful chemical. The third question is: Who are the target customers? The answer was that homemakers and tourists are target customers. The fourth question: What is the brand guarantee to customers? The answer was that the brand guarantees that the product is 100 percent natural process with a high quality and it is a community production. The findings revealed that in terms of product, customers rated quality and package as the two most important factors. In terms of price, customers rated lower price and a visible label as the two most important factors. In terms of place, customer rated layout and the cleanliness of the place as the two most important factors. In terms of promotion, customer rated public relations and brochure at the store as the most important factors. From the group discussion, the local community agreed that the brand for the community coconut sugar of Salapi community should be a picture of a green coconut tree and yellow color background. This brand implies the strength of community and authentic of the high quality natural product.

Keywords: coconut sugar, community brand, Samut Songkram, natural product

Procedia PDF Downloads 359

Authors: Shraddha Chaudhary, Raksha Agarwal, Niladri Chatterjee

Abstract:

This work demonstrates a web crawler-based generalized end-to-end open domain Question Answering (QA) system. An efficient QA system requires a significant amount of domain knowledge to answer any question with the aim to find an exact and correct answer in the form of a number, a noun, a short phrase, or a brief piece of text for the user's questions. Analysis of the question, searching the relevant document, and choosing an answer are three important steps in a QA system. This work uses a web scraper (Beautiful Soup) to extract K-documents from the web. The value of K can be calibrated on the basis of a trade-off between time and accuracy. This is followed by a passage ranking process using the MS-Marco dataset trained on 500K queries to extract the most relevant text passage, to shorten the lengthy documents. Further, a QA system is used to extract the answers from the shortened documents based on the query and return the top 3 answers. For evaluation of such systems, accuracy is judged by the exact match between predicted answers and gold answers. But automatic evaluation methods fail due to the linguistic ambiguities inherent in the questions. Moreover, reference answers are often not exhaustive or are out of date. Hence correct answers predicted by the system are often judged incorrect according to the automated metrics. One such scenario arises from the original Google Natural Question (GNQ) dataset which was collected and made available in the year 2016. Use of any such dataset proves to be inefficient with respect to any questions that have time-varying answers. For illustration, if the query is where will be the next Olympics? Gold Answer for the above query as given in the GNQ dataset is “Tokyo”. Since the dataset was collected in the year 2016, and the next Olympics after 2016 were in 2020 that was in Tokyo which is absolutely correct. But if the same question is asked in 2022 then the answer is “Paris, 2024”. Consequently, any evaluation based on the GNQ dataset will be incorrect. Such erroneous predictions are usually given to human evaluators for further validation which is quite expensive and time-consuming. To address this erroneous evaluation, the present work proposes an automated approach for evaluating time-dependent question-answer pairs. In particular, it proposes a metric using the current timestamp along with top-n predicted answers from a given QA system. To test the proposed approach GNQ dataset has been used and the system achieved an accuracy of 78% for a test dataset comprising 100 QA pairs. This test data was automatically extracted using an analysis-based approach from 10K QA pairs of the GNQ dataset. The results obtained are encouraging. The proposed technique appears to have the possibility of developing into a useful scheme for gathering precise, reliable, and specific information in a real-time and efficient manner. Our subsequent experiments will be guided towards establishing the efficacy of the above system for a larger set of time-dependent QA pairs.

Keywords: web-based information retrieval, open domain question answering system, time-varying QA, QA evaluation

Procedia PDF Downloads 68

Authors: Jui-Teng Liao

Abstract:

The selected-response (SR) format has been commonly adopted to assess academic reading in both formal and informal testing (i.e., standardized assessment and classroom assessment) because of its strengths in content validity, construct validity, as well as scoring objectivity and efficiency. When developing a second language (L2) reading test, researchers indicate that the longer the test (e.g., more test items) is, the higher reliability and validity the test is likely to produce. However, previous studies have not provided specific guidelines regarding the optimal length of a test or the most suitable number of test items or reading passages. Additionally, reading tests often include different question types (e.g., factual, vocabulary, inferential) that require varying degrees of reading comprehension and cognitive processes. Therefore, it is important to investigate the impact of question types on the number of items in relation to the score reliability of L2 reading tests. Given the popularity of the SR question format and its impact on assessment results on teaching and learning, it is necessary to investigate the degree to which such a question format can reliably measure learners’ L2 reading comprehension. The present study, therefore, adopted the generalizability (G) theory to investigate the score reliability of the SR format in L2 reading tests focusing on how many test items a reading test should include. Specifically, this study aimed to investigate the interaction between question types and the number of items, providing insights into the appropriate item count for different types of questions. G theory is a comprehensive statistical framework used for estimating the score reliability of tests and validating their results. Data were collected from 108 English as a second language student who completed an English reading test comprising factual, vocabulary, and inferential questions in the SR format. The computer program mGENOVA was utilized to analyze the data using multivariate designs (i.e., scenarios). Based on the results of G theory analyses, the findings indicated that the number of test items had a critical impact on the score reliability of an L2 reading test. Furthermore, the findings revealed that different types of reading questions required varying numbers of test items for reliable assessment of learners’ L2 reading proficiency. Further implications for teaching practice and classroom-based assessments are discussed.

Keywords: second language reading assessment, validity and reliability, Generalizability theory, Academic reading, Question format

Procedia PDF Downloads 34

Authors: Ameema Mahroof, Muhammad Saeed

Abstract:

The purpose of this study was to analyze the papers of computer science conducted by Board of Intermediate and Secondary Education with reference to Bloom’s taxonomy. The present study has two parts. First, the analysis is done on the papers conducted by Board of Intermediate of Secondary Education on the basis of basic rules of item construction especially Bloom’s (1956). And the item analysis is done to improve the psychometric properties of a test. The sample included the question papers of computer science of higher secondary classes (XI-XII) for the years 2011 and 2012. For item analysis, the data was collected from 60 students through convenient sampling. Findings of the study revealed that in the papers by Board of intermediate and secondary education the maximum focus was on knowledge and understanding level and very less focus was on the application, analysis, and synthesis. Furthermore, the item analysis on the question paper reveals that item difficulty of most of the questions did not show a balanced paper, the items were either very difficult while most of the items were too easy (measuring knowledge and understanding abilities). Likewise, most of the items were not truly discriminating the high and low achievers; four items were even negatively discriminating. The researchers also analyzed the items of the paper through software Conquest. These results show that the papers conducted by Board of Intermediate and Secondary Education were not well constructed. It was recommended that paper setters should be trained in developing the question papers that can measure various cognitive abilities of students so that a good paper in computer science should assess all cognitive abilities of students.

Keywords: Bloom’s taxonomy, question paper, item analysis, cognitive domain, computer science

Procedia PDF Downloads 114

Authors: Aroob Binhimd, Lyan Sayoti, Rana Almansour

Abstract:

In recent years, artificial intelligence has grown drastically. This has led to the growth of educational programs to help students in solving educational problems and assist them in understanding certain topics. The purpose of this report is to investigate the Mathway application. Mathway is a mathematics software that teaches students how to solve and handle mathematical issues. The app allows students to insert questions manually on the platform or take a picture of the question, and then they get an answer to this mathematical question. It helps students enhance their performance in mathematics. This app can also be used to verify or check if their answers are correct. The report will include a questionnaire to collect data and analyze the users of this application.

Keywords: artificial intelligence, Mathway, mathematics, mathematical problems

Procedia PDF Downloads 219

Authors: Okoh Chinasa, Asimuonye Augusta

Abstract:

This study investigated the trends in language testing in Primary Schools in Rivers State. English language past question papers were collected from four (4) Primary Schools in Onelga Local Government Area and Ahoada East Local Government Area. Four research questions guided the study. The study is aimed at finding out the appropriateness of test formats used for language testing and the language skills tested. The past question papers collected which served as the instrument were analyzed based on given criteria developed by the researchers in line with documentary frequency studies, a type of survey study. The study revealed that some of the four language skills were not adequately assessed and that the termly question papers were developed by a central examination body. From the past questions, it was observed that an imbalance exists in the test format used. The paper recommended that all the language skills should be tested using correct test formats to ensure that pupils were given a fair chance to show what they know and can do in English language and for teachers to be able to use the test results for effective decision making.

Keywords: discrete test, integrative test, testing approach, test format

Procedia PDF Downloads 386