Papers by Bayan Abu Shawar
Journal for Language Technology and Computational Linguistics
Chatbots: Are they Really Useful? Chatbots are computer programs that interact with users using n... more Chatbots: Are they Really Useful? Chatbots are computer programs that interact with users using natural languages. This technology started in the 1960's; the aim was to see if chatbot systems could fool users that they were real humans. However, chatbot systems are not only built to mimic human conversation, and entertain users. In this paper, we investigate other applications where chatbots could be useful such as education, information retrival, business, and e-commerce. A range of chatbots with useful applications, including several based on the ALICE/AIML architecture, are presented in this paper. Chatbots sind Computerprogramme, die mit Benutzern in natürlicher Sprache kommunizieren. Die ersten Programme gab es in den 60er Jahren; das Ziel war festzustellen, ob Chatbots Benutzer davon überzeugen könnten, dass sie in Wirklichkeit Menschen seien. Chatbots werden aber nicht nur gebaut, um menschliche Kommunikation nachzuahmen und um Benutzer zu unterhalten. In diesem Artikel untersuchen wir andere Anwendungen für Chatbots, zum Beispiel in Bildung, Suchmaschinen, kommerzielle Anwendungen und e-commerce. Wir stellen eine Reihe von Chatbots mit nützlichen Anwendungen vor, einschliesslich mehrerer Chatbots, die auf der ALICE/AIML Architektur basieren.
Lecture Notes in Electrical Engineering, 2021
To promote the research and development of dialogue breakdown detection for dialogue systems, we ... more To promote the research and development of dialogue breakdown detection for dialogue systems, we have been organizing a series of dialogue breakdown detection challenges to detect a system's inappropriate utterances that lead to dialogue breakdowns in chat-oriented dialogue. In this paper, we overview Dialogue Breakdown Detection Challenge 4 (DBDC4). As in the previous challenges, we used datasets in English and Japanese. Four teams participated in the challenge, in which all four teams worked on English, and two of the four teams worked on Japanese as well. This paper describes the task setting, evaluation metrics, and datasets for the challenge and the results of the submitted runs of the participants.
Chatbot tools are computer programs which interact with users using natural languages. This thesi... more Chatbot tools are computer programs which interact with users using natural languages. This thesis shows that chatbot technology could be used in many different ways in addition to being a tool for having fun. A chatbot could be used as a tool to learn or to study a new language; a tool to access an information system, a tool to visualise the contents of a corpus; and a tool to give answers to questions in a specific domain. Instead of being restricted to a specific domain or written language, a chatbot could be trained with any text in any language. Some of the differences between real human conversations and human-chatbot dialogues are presented. A Java program has been developed to read a text from a machine readable text (corpus) and convert it to ALICE chatbot format language (AIML). The program was built to be general, the generality in this respect implies, no restrictions on specific language, domain, or structure. Different languages were tested: English, Arabic, Afrikaans,...
This paper focuses on the Learning Management System (LMS) from the point of present it as Knowle... more This paper focuses on the Learning Management System (LMS) from the point of present it as Knowledge Management (KM) base. There is huge information that can be extracted from any LMS that can be useful for many investigators. This information is not necessary to be only concentrating on the content of the LMS but it will cover also all parameters that are related to content, context, activities, and deferent types of users of the LMS. The extracted information will be presented in different format such as text data, tables, charts, and figures. Also this information is going to be useful for different information seekers from deferent specialties including higher management, financial department, quality assurance agency, registration, local accreditation, academic supervisors, and external examiners. A case study on using the LMS at the Arab Open University (AOU) will be presented including many samples of extracted information and its usability. In summery, this paper introduces ...
Instance-Based learners are simple, yet, effective learners. They classify a new instance based o... more Instance-Based learners are simple, yet, effective learners. They classify a new instance based on the k most similar instances which makes them sensitive to noise in training data sets. Obtaining good classification accuracy may, therefore, require cleaning the data sets using labor-extensive or computationally expensive data cleaning procedures. In this work, we present some Bayesian-based instance weighting techniques to make such learners more tolerant to noise. The basic idea is that typical or classical instances should be given more weight or voting power than less typical or noisy instances. We present three techniques to determine instance weights that are based on the conditional probability of an instance belonging to its actual class and not to another class. Our empirical results using the kNN algorithm shows that all presented techniques are effective in making the kNN more tolerant to noise. These results suggest that these techniques can be used with instance based l...
The Quran is held by Muslims to be a single-authored text, the direct words of God (Allah), conve... more The Quran is held by Muslims to be a single-authored text, the direct words of God (Allah), conveyed by the angel Gabriel to Mohammed 1355-1378 years ago, and later transcribed verbatim to be used as the sole authoritative source of knowledge, wisdom and law. The challenge for computer scientists is to represent this knowledge, wisdom and law in computer systems: to build intelligent systems which can answer any question with knowledge from the Quran, and can help society, both Muslim and non-Muslim, to understand and appreciate the Quran.
The rapid growth of online world and the great evolution in digital technology open new horizons ... more The rapid growth of online world and the great evolution in digital technology open new horizons in different domains including education one. Blended learning and e-Learning approaches are new trends that are based on using computers as a medium to deliver and share educational materials which makes education available anytime, and anywhere. Khan suggested eight dimensional e-learning framework which serves as a base to help institutions to plan, design, implement and evaluate their e-learning programs. This paper discusses whether learning management systems at Arab Open University (AOU) meet the eight dimensional e-learning frameworks suggested by Badrul Khans. A detailed description of Khan's framework and the LMS used at Arab Open University are included in this paper. We claim that the AOU LMS is a good framework for e-learning based on these eight dimensions.
This paper presents a complete description of the improvements that have been conducted for the l... more This paper presents a complete description of the improvements that have been conducted for the learning management system at Arab Open University. AOU is the first regional university for open learning in the Middle East and North Africa. The university has strict regulations on the learning process to assure the quality of delivering all learning activities in an optimal way. Accordingly, there is a need to improve the existing learning management system to guarantee the implementation of such quality assurance regulations electronically to save time and cost and to perform all required procedures. In addition of describing the improvements, this paper also conducts a comparison between conforming with such regulations manually and the new online procedures over the learning management system.
The great evolution of the online world effects many domains, mainly education and knowledge mana... more The great evolution of the online world effects many domains, mainly education and knowledge management era. The new trend in educational institutes moves towards online learning, e-learning instead of traditional approach of face-to-face teaching. The main aspect of knowledge management is to offer various kind of information in different formats such as: reports, meeting to exchange opinions and experiences from the gathering database repository and related expert systems. e-learning is basically concern of delivering learning materials to its target users via e-learning platforms or in other words via the learning management systems (LMS). In this paper we discuss the similarities and differences between knowledge management and e-learning. In more specific, the relationship between our learning management system used at Arab Open University and knowledge management systems is presented. We explore the main factors of LMS by displaying how these aspects can be extracted from such...
In this paper, we describe a way to access Arabic information using chatbot, without the need for... more In this paper, we describe a way to access Arabic information using chatbot, without the need for sophisticated natural language processing or logical inference. FAQs are Frequently-Asked Questions documents, designed to capture the logical ontology of a given domain. Any Natural Language interface to an FAQ is constrained to reply with the given Answers, so there is no need for NL generation to recreate well-formed answers, or for deep analysis or logical inference to map user input questions onto this logical ontology; simple (but large) set of pattern-template matching rules will suffice. In previous research, this works properly with English and other European languages. In this paper, we try to see how the same chatbot will react in terms of Arabic FAQs. Initial results shows that 93% of answers were correct, but because of a lot of characteristics related to Arabic language, changing Arabic questions into other forms may lead to no answers.
International Conference on E-Business, Enterprise Information Systems, E-Government, and Outsourcing, 2006
This paper follows the progress of improving the Arab Open University's Learning Management S... more This paper follows the progress of improving the Arab Open University's Learning Management System by integrating it with other online systems, such as the university's Student Information System and the Human Resource System. A complete description of the open source learning management system, Moodle, and the benefits of adapting open source platforms is presented. The paper also presents in detail
Proceedings of the Workshop on Bridging the Gap Academic and Industrial Research in Dialog Technologies - NAACL-HLT '07, 2007
A chatbot is a software system, which can interact or "chat" with a human user in natural languag... more A chatbot is a software system, which can interact or "chat" with a human user in natural language such as English. For the annual Loebner Prize contest, rival chatbots have been assessed in terms of ability to fool a judge in a restricted chat session. We are investigating methods to train and adapt a chatbot to a specific user's language use or application, via a usersupplied training corpus. We advocate open-ended trials by real users, such as an example Afrikaans chatbot for Afrikaansspeaking researchers and students in South Africa. This is evaluated in terms of "glass box" dialogue efficiency metrics, and "black box" dialogue quality metrics and user satisfaction feedback. The other examples presented in this paper are the Qur'an and the FAQchat prototypes. Our general conclusion is that evaluation should be adapted to the application and to user needs.
International Journal of Corpus Linguistics, 2005
A chatbot is a machine conversation system which interacts with human users via natural conversat... more A chatbot is a machine conversation system which interacts with human users via natural conversational language. Software to machine-learn conversational patterns from a transcribed dialogue corpus has been used to generate a range of chatbots speaking various languages and sublanguages including varieties of English, as well as French, Arabic and Afrikaans. This paper presents a program to learn from spoken transcripts of the Dialogue Diversity Corpus of English, the Minnesota French Corpus, the Corpus of Spoken Afrikaans, the Qur'an Arabic-English parallel corpus, and the British National Corpus of English; we discuss the problems which arose during learning and testing. Two main goals were achieved from the automation process. One was the ability to generate different versions of the chatbot in different languages, bringing chatbot technology to languages with few if any NLP resources: the corpus-based learning techniques transferred straightforwardly to develop chatbots for ...
Advances in Computer Science and Engineering, 2010
A chatbot is a program which can chat in natural language, on a topic built into the chatbot's in... more A chatbot is a program which can chat in natural language, on a topic built into the chatbot's internal knowledge model. Many chatbots exist, with different knowledge-bases programmed by the chatbot builders. We have built a system to convert a website text (corpus) to a chatbot knowledge-base format. In this paper the chatbot is used as a question answer interface, where TRE09 QA track is used to automatically retrain the chatbot knowledge-base. Evaluation shows promising results, 2/3 of generated answers were correct. We aim to see how to improve the algorithm for building the knowledge base before comparing this tool with other natural language interfaces.
Lecture Notes in Computer Science, 2004
... Accessing an Information System by Chatting Bayan Abu Shawar and Eric Atwell ... This involve... more ... Accessing an Information System by Chatting Bayan Abu Shawar and Eric Atwell ... This involves a chatbot, a program that emulates human conversation; the chatbot must be trainable with a text, to accept input and match it against the text to generate replies in the conversation. ...
Southern African Linguistics and Applied Language Studies, 2003
This paper presents two chatbot systems, ALICE and Elizabeth, illustrating the dialogue knowledge... more This paper presents two chatbot systems, ALICE and Elizabeth, illustrating the dialogue knowledge representation and pattern matching techniques of each. We discuss the problems which arise when using the Corpus of Spoken Afrikaans (Korpus Gesproke Afrikaans) to retrain the ALICE chatbot system with human dialogue examples. A Java program to convert from dialog transcripts to the AIML linguistic knowledge representation formalism provides a basic implementation of corpus-based chatbot training. The Java program used the Afrikaans dialogue corpus texts to generate two versions of the Afrikaans chatbot.
International Journal of Emerging Technologies in Learning (iJET), 2011
In this paper, we describe a way to access Arabic Web Question Answering (QA) corpus using a chat... more In this paper, we describe a way to access Arabic Web Question Answering (QA) corpus using a chatbot, without the need for sophisticated natural language processing or logical inference. Any Natural Language (NL) interface to Question Answer (QA) system is constrained to reply with the given answers, so there is no need for NL generation to recreate well-formed answers, or for deep analysis or logical inference to map user input questions onto this logical ontology; simple (but large) set of pattern-template matching rules will suffice. In previous research, this approach works properly with English and other European languages. In this paper, we try to see how the same chatbot will react in terms of Arabic Web QA corpus. Initial results shows that 93% of answers were correct, but because of a lot of characteristics related to Arabic language, changing Arabic questions into other forms may lead to no answers.
Citeseer
... e-Assignments) Allow personalization (user profiles, custom news, recent activity, RSS) E... more ... e-Assignments) Allow personalization (user profiles, custom news, recent activity, RSS) Enablemonitoring activities (QA ... Students attendance and absences ... For example, wireless classroom response systems can be integrated into classroom instructions to gather students ...
Uploads
Papers by Bayan Abu Shawar