Showing papers on "Chatbot published in 2014"

Engaging high school students using chatbots

Abstract: Chatbots have been used in different scenarios for getting people interested in CS for decades. However, their potential for teaching basic concepts and their engaging effect has not been measured. In this paper we present a software platform called Chatbot designed to foster engagement while teaching basic CS concepts such as variables, conditionals and finite state automata, among others. We carried out two experiences using Chatbot and the well known platform Alice: 1) an online nation-wide competition, and 2) an in-class 15-lesson pilot course in 2 high schools. Data shows that retention and girl interest are higher with Chatbot than with Alice, indicating student engagement.

Luke, I am Your Father: Dealing with Out-of-Domain Requests by Using Movies Subtitles

Abstract: Even when the role of a conversational agent is well known users persist in confronting them with Out-of-Domain input. This often results in inappropriate feedback, leaving the user unsatisfied. In this paper we explore the automatic creation/enrichment of conversational agents’ knowledge bases by taking advantage of natural language interactions present in the Web, such as movies subtitles. Thus, we introduce Filipe, a chatbot that answers users’ request by taking advantage of a corpus of turns obtained from movies subtitles (the Subtle corpus). Filipe is based on Say Something Smart, a tool responsible for indexing a corpus of turns and selecting the most appropriate answer, which we fully describe in this paper. Moreover, we show how this corpus of turns can help an existing conversational agent to answer Out-of-Domain interactions. A preliminary evaluation is also presented.

Conversation with a Chatbot before an Online EFL Group Discussion and the Effects on Critical Thinking

Abstract: This study investigated learners of English as a foreign language (EFL) who engaged in a group discussion and saw how their discussion was affected by a preceding conversation with a chatbot. The chatbot was designed to reflect the Socratic inquiry method based on Eliza, a computer program developed for psychotherapy. Two case studies were conducted, and 130 university students (Case 1: n=63; Case 2: n=67) were divided into experimental and control groups and observed. Case 1 served as the pilot study and focused on the effects of a chatbot conversation on the discussion; the critical thinking, satisfaction, and number of conversations in experimental and control groups were analyzed. Case 2 examined the difference in critical thinking preand post-discussion in both groups. Case 1 showed that a preceding conversation with a chatbot might lead to an increase in the number of contributions that students made to conversations and could increase the number of conversations in which the students participated. Case 2 results showed that pre-discussion with a chatbot could increase the students’ awareness of critical thinking and enable them to form inquiring mindsets.

Measuring effectiveness of learning chatbot systems on Student’s learning outcome and memory retention

Abstract: Creating a learning environment in which students learn more effectively remains the great challenge from decades; different approaches are proposed, for example, Intelligent Tutoring Systems, Question Answering System and chatbot. All these approaches used natural language to achieve that goal. A comparison of these systems viz-a-viz student learning outcome and behavior is of eminent importance. To achieve this goal a chatbot system with knowledge base for Object-Oriented Programming Languages is developed and deployed. Case study was made to assess and evaluate the chatbot system for student learning methodology. Learning outcomes and Memory retention have been measured for the developed system. Comparisons were made between the results obtained using Google search engine and our chatbot system. The results indicate that learning through Chabot have a significant impact on memory retention and Learning outcomes of the students.

Toward an Ontology-Based Chatbot Endowed with Natural Language Processing and Generation

Abstract: With the last evolution of the web, several new means of communication have showed up In the commercial domain, chatbot tech-nologies are now considered as essential for providing a wide range of ser-vices (eg search, FAQ, assistance) to the end-user, and to make a client a faithful customer In this paper, we propose an on-going work on the denition and implementation of SynchroBot, an ontology-based chat-bot that relies on Semantic Web and NLP models and technologies to support user-machine dialogical interaction in the e-commerce domain

Developing multimodal conversational agents for an enhanced e-learning experience

Abstract: Conversational agents have become a strong alternative to enhance educational systems with intelligent communicative capabilities, provide motivation and engagement, and increment significant learning and helping in the acquisition of meta-cognitive skills. In this paper, we present Geranium, a multimodal conversational agent that helps children to appreciate and protect their environment. The system, which integrates an interactive chatbot, has been developed by means of a modular and scalable framework that eases building pedagogic conversational agents that can interact with the students using speech and natural language.

Problematic Situation Analysis and Automatic Recognition for Chinese Online Conversational System

Abstract: Automatic problematic situation recognition (PSR) is important for an online conversational system to constantly improve its performance. A PSR module is responsible of automatically identifying users’ un-satisfactions and then sending feedbacks to conversation managers. In this paper, we collect dialogues from a Chinese online chatbot, annotate the problematic situations and propose a framework to predict utterance-level problematic situations by integrating intent and sentiment factors. Different from previous work, the research field is set as open-domain in which very few domain specific textual features could be used and the method is easy to be adapted to other domains. Experimental results show that integrating both intent and sentiment factors gains the best performance.

A Chatbot Dialogue Manager - Chatbots and Dialogue Systems: A Hybrid Approach

Abstract: Conversational software, that is software with which a user can converse in a natural language such as English or Dutch, can be classified into two distinct categories: chatbots and dialogue systems. Both categories of systems have their advantages and disadvantages. Chatbot systems are trivial to build and maintain, but are too simplistic for applications that do more than answering frequently asked questions. Dialogue systems on the other hand are harder to develop and maintain, can deal with less variety in user input, but are capable of handling and generating all kinds of linguistic phenomena such as grounding and information revision. This thesis presents a system that combines ideas from chatbots and dialogue system. This hybrid system doesn’t parse natural language into a semantic presentation, but contains a dialogue manager that can handle natural language directly. This system would make it easy to implement and maintain new domains even when the developer has little or no knowledge of computational linguistics. A statistics tutor has been implemented using this hybrid system with which three students interacted. This shows that the statistics tutor is able to deal with phenomena such as grounding, question accommodation and information revision.

Chatbots as Interface to Ontologies

Abstract: Chatbots are simple conversational agents using “pattern matching rules” to carry out the dialogue with the user and various expedients to improve their credibility. However, the rules on which they are based on are too restrictive and their language understanding capability is very limited. Nevertheless chatbots are widespread in several applications, especially to provide information to users in a new and enjoyable way. In this chapter we describe different chatbot architectures, exploiting the use of ontologies in order to create clever information suppliers overcoming the main limits of chatbots: the knowledge base building and the rigidness of the dialogue mechanism.

Chatbot for admissions

Abstract: The communication of potential students with a university department is performed manually and it is a very time consuming procedure. The opportunity to communicate with on a one-to-one basis is highly valued. However with many hundreds of applications each year, one-to-one conversations are not feasible in most cases. The communication will require a member of academic staff to expend several hours to find suitable answers and contact each student. It would be useful to reduce his costs and time. The project aims to reduce the burden on the head of admissions, and potentially other users, by developing a convincing chatbot. A suitable algorithm must be devised to search through the set of data and find a potential answer. The program then replies to the user and provides a relevant web link if the user is not satisfied by the answer. Furthermore a web interface is provided for both users and an administrator. The achievements of the project can be summarised as follows. To prepare the background of the project a literature review was undertaken, together with an investigation of existing tools, and consultation with the head of admissions. The requirements of the system were established and a range of algorithms and tools were investigated, including keyword and template matching. An algorithm that combines keyword matching with string similarity has been developed. A usable system using the proposed algorithm has been implemented. The system was evaluated by keeping logs of questions and answers and by feedback received by potential students that used it.

The forensic challenger

Abstract: This paper proposes a game based e-Learning tool called The forensic challenger (TFC) to teach digital forensic investigation By combining elements from game theory with the use of e-Learning, the authors are able to provide a solution that offers a more efficient way of learning how to perform digital forensics investigations Contrary to traditional learning methods, TFC is built on a Hyper Interactive Presenter (HIP) platform that incorporates VARK learning style model to take into account individuals' learning preferences For visual and audio learners, it provides a video playback and Powerpoint presentation Learners who prefer to read, there is a custom designed wiki page containing information relevant to the presented topic While for kinesthetic learners, a multiple choice question based quiz is implemented, and a pedagogical chatbot agent is there to assist users It provides easy navigation and interaction within the content Preliminary results of the subjective experiment to evaluate the effectiveness of TFC suggests that such a system will prove useful in teaching digital forensic investigation to young students

The Geranium System: Multimodal Conversational Agents for E-learning

Abstract: Many e-learning applications use conversational agents as means to obtain enhanced pedagogical results such as fostering motivation and engagement, incrementing significant learning and helping in the acquisition of meta-cognitive skills. In this paper, we present Geranium, a multimodal conversational agent that helps children to appreciate and protect their environment. The system, which integrates an interactive chatbot, provides a modular and scalable framework that eases building pedagogic conversational agents that can interact with the students using speech and natural language.

Chatbot for IT Security Training: Using Motivational Interviewing to Improve Security Behaviour.

Abstract: We conduct a pre-study with 25 participants on Mechanical Turk to find out which security behavioural problems are most important for online users. These questions are based on motivational interviewing (MI), an evidence-based treatment methodology that enables to train people about different kinds of behavioural changes. Based on that the chatbot is developed using Artificial Intelligence Markup Language (AIML). The chatbot is trained to speak about three topics: passwords, privacy and secure browsing. These three topics were ’most-wanted’ by the users of the pre-study. With the chatbot three training sessions with people are conducted.

Automated Attendance Monitoring and Personal Intelligent system

Abstract: 4 Abstract: In today's world, a paper based approach is followed for marking attendance, where the students sign on the attendance sheets. This data is then manually entered into the system. Managing the attendance of the students during lectures is a difficult task and it becomes more difficult during the report generation phase and manual computation produces errors and also wastes a lot of time. For this reason, the development of Automated Attendance Monitoring System (AMS) using android platform is proposed. Additionally, implementation of an intelligent system which will interact with users and provide environment where chatbot will interact to provide dedicated chat. So, user can access database using internet enabled Smartphone to solve his queries and get desired output with voice chat.

Wittgensteinian Perspectives on the Turing Test

Abstract: This paper discusses some difficulties in understanding the Turing test. It emphasizes the importance of distinguishing between conceptual and empirical perspectives and highlights the former as introducing more serious problems for the TT. Some objections against the Turingian framework stemming from the later Wittgenstein’s philosophy are exposed. The following serious problems are examined: 1) It considers a unique and exclusive criterion for thinking which amounts to their identification; 2) it misidentifies the relationship of speaking to thinking as that of a criterion; 3) it neglects the “natural” course of the development in semantics. However, these considerations suggest only that it is problematic to label a successful chatbot as a “thinking entity” without further qualifications, but not necessarily and once and for all incorrect. Philosophy has only little to say about the technical possibility of creating such an effective program.

Towards Fully Automated Digital Alibis with Social Interaction

Abstract: Digital traces found on local hard drives as a result of online activities have become very valuable in reconstructing events in digital forensic investigations. This paper demonstrates that forged alibis can be created for online activities and social interactions. In particular, a novel, automated framework is presented that uses social interactions to create false digital alibis. The framework simulates user activity and supports communications via email as well as instant messaging using a chatbot. The framework is evaluated by extracting forensic artifacts and comparing them with the results obtained from a human user study.

An empirical evaluation of an IR-based strategy for chat-oriented dialogue systems

Abstract: This work reports the evaluation of a data-driven chatbot strategy, which is based on the vector space model IR framework. The evaluation is conducted by means of an empirical comparison between the proposed strategy and a baseline system that implements a similar, but naive, strategy. The proposed chatbot strategy combines semantic evidence from both the current user input and the previous recent chatting-history, while the baseline system only uses the current user input as source of evidence. As a result of the conducted comparative evaluation, the proposed chatbot strategy happened to outperform the baseline strategy by a small, but statistically significant, difference.

Chatbots and natural automatedlanguage : A comparison between rst word and most signicantword search

Abstract: This study aims to determine if there is any dierence in the perceived naturalness of chatbots implemented with either a rst word search- or a most signicant word search-algorithm. To this end two versions of the same chatbot were implemented using parsed movie dialogue used as a knowledge base and evaluated using methods developed for chatbot competitions. The results of the study were inconclusive and no statistically certain dierence between the two implementations was found.

A Novel Approach to Smart Higen Chatbot System by Using Data Mining Algorithm

Abstract: Data mining is important and useful tool as compare to several efficient tools for extracting data that are stored in a database. Frequent pattern mining is one of data mining algorihtm, which will extract the items that occur more number of times. Data may be in the form of facts, numbers, or text.In current years, Organizations are accumulating vast and increasing amounts of data in different formats and different databases. In Frequent itemset mining, which focuses on finding a association among data. Change mining, which detects and report any considerable changes if occurs in the set of mined itemsets from different time periods. This project extends the Dynamic change mining problem, in the framework of frequent itemsets, by exploiting recurrent generalized itemsets to characterize information linked with infrequent patterns. To address this issue, I introduce two novel kinds of vibrant patterns, namely the HIGEN MINER (History Generalized pattern) and NON- REDUNDANT HIGEN MINERs. HIGEN MINER detects the mined frequent itemset, if any items become infrequent during next extraction those changes are focused and avoided by Apriori based support driven approach. NON- REDUNDANT HIGEN MINER, which stores items whose support value is minimum, these infrequent items may become frequent during next extraction. If it remains same, then these infrequent items are discarded. HIGEN Chatbot System is the system that helps to understand the human conversation. A chatbot is a computer program designed to simulate an intelligent conversation with one or more human users. Primarily for engaging different types of application. The main aim of HIGEN chatbot is support to multiple domains the user into thinking that the program's output has been produced by a human. Programs playing this role are sometimes referred to as Artificial Intelligence Conversational Entities, talk bots or chatterboxes. The objective of the paper is to predict more accurately the presence of type of domain suppose user wants any type of questions of answers of any types of domains such as Medical related queries, Libraray related questions etc. In proposed work HIGEN chatbot gives the correct answers to particular questions using two variant kinds of algorithms Modified HIGEN and Non redundant HIGEN and techniques are used Naive Byes and NLP are used to implement this work and comparison of these two system has been given in the present paper based on accuracy .As per the results,accuracy of HIGEN chatbot system and ALICE chatbot system is likely to have 98%,and 50 % respectively. The analysis shows that out of thses two chatbot system is predictthe accurate answer to the particular question with highest accuracy.

A System of Simple Sentence Parsing Rules to Produce "Answer Matching" Chatbots

Abstract: Producing interactive chatbots usually involves complex sentence parsing approaches that are beyond the scope of material that can be handled in introductory CS courses. In this paper, a simple framework is presented for parsing a sentence from a user during a chat with a chatbot using an "answer matching" strategy that is not at a level of complexity that is too difficult for an introductory CS student.

MILLA A Multimodal Interactive Language Agent

Abstract: We describe the motivation behind, design, and implementation of MILLA, a prototype speech-to-speech English language tutoring system. 1 Background Learning a new language involves the acquisition and integration of a range of skills. A human tutor aids learners by (i) providing a framework of tasks suitable to the learner’s needs, (ii) monitoring learner progress and adapting task content and delivery style to suit, and (iii) providing a source of speaking practice and motivation. With the advent of audiovisual technology and the communicative paradigm in language pedagogy, focus has shifted from written grammar and translation to activities focusing more on communicative competence in listening and spoken production. In recent years the Common European Framework of Reference for Language Learning and Teaching (CEFR) officially added a more integrative fifth skill – spoken interaction to the traditional four skills – reading and listening, and writing and speaking (Little, 2006) . While second languages have always been learned interactively through negotiation of meaning between speakers of different languages sharing living or working environments, these methods did not figure in formal (funded) settings. However, with increased mobility and globalisation, many formal learners now need language as a practical tool for everyday life and business rather than simply as an academic achievement. Developments in Computer Assisted Language Learning (CALL) have resulted in a range of free and commercial language learning material for autonomous study. Much of this material transfers long-established paper-based and audiovisual exercises to the computer screen. Pronunciation training exercises have been developed which provide feedback either through the learner listening back to their own efforts and comparing to a model, or the system providing a score or other feedback. These resources are very useful in development of discrete skills, but the challenge of providing spoken interaction tuition and practice remains. The MILLA system, developed at the 2014 eNTERFACE workshop (‘The 10th International Summer Workshop on Multimodal Interfaces eNTERFACE’14 ISCA Training School’, 2014) is a multimodal spoken dialogue system combining custom modules with existing web resources in a balanced curriculum, and, by integrating spoken dialogue, modelling some of the advantages of a human tutor. 2 MILLA System Components MILLA’s spoken dialogue Tuition Manager consults a two-level curriculum of language learning tasks, a learner record, and a learner state module to greet and enroll learners, direct them to language learning submodules, provide feedback and scoring, and monitor user state with Kinect sensors. All of the tuition manager’s interaction with the user can be performed using speech through a Cereproc TTS voice using Cereproc’s Python SDK (‘CereVoice Engine Text-to-Speech SDK | CereProc Text-to-Speech’, 2014) and understanding via CMU’s Sphinx4 ASR (Walker et al., 2004) through custom Python bindings using W3C compliant Java Speech Format Grammars. Tasks include spoken dialogue practice with two different chatbots, first language (L1) focused and general pronunciation training, and grammar and vocabulary exercises. Several speech recognition (ASR) engines (HTK, Google Speech) and text-to speech (TTS) voices (Mac and Windows system voices, Google Speech) are incorporated in the modules to meet the demands of particular tasks and to provide a cast of voice characters which provide a variety of speech models to the learner. Microsoft’s Kinect SDK (‘Kinect for Windows SDK’, 2014) is used for gesture recognition and as a platform for affect recognition. The tuition manager and all interfaces are written in Python 2.6, with additional C#, Javascript, Java, and Bash coding in the Kinect, chat, Sphinx4, and pronunciation elements. For rapid prototyping many of the dialogue modules were first written in VoiceXML, and then ported to Python modules. 2.1 Pronunciation Tuition MILLA incorporates two pronunciation modules, based on comparison of learner production with model production: (i) a focused pronunciation tutor using HTK ASR with the five-state 32 Gaussian mixture monophone acoustic models provided with the Penn Aligner toolkit (Young, n.d.; Yuan & Liberman, 2008) on the system’s local machine and (ii) MySpeech a phrase level trainer hosted on University College Dublin’s cluster and accessed by the system via Internet (Cabral et al., 2012). For the focused pronunciation system, we used the baseline implementation of the Goodness of Pronunciation algorithm, (Witt & Young, 2000). GOP scoring involves two phases: 1) a free phone loop recognition phase which determines the most likely phone sequence given the input speech without giving the ASR any information about the target sentence, and 2) a forced alignment phase which provides the ASR system with the orthographic transcription of the input sentence and force aligns the speech signal with the expected phone sequence. For each phone realization aligned to the speech signal, comparison of the log-likelihoods of the forced alignment and thevfree recognition phases, produces a GOP score where zero reflects a perfect match and increasing positive scores correspond to inaccuracies. Phone specific threshold scores were set to decide whether a phone was mispronounced (``rejected'') or not (``accepted''), by artificially inserting errors in the pronunciation lexicon and running the algorithm on native recordings, as in (Kanters, Cucchiarini, & Strik, 2009). After preliminary testing, we constrained the free phone loop recogniser for more robust behavior, using phone confusions common in specific L1’s to define constrained phone grammars. A database of common errors in several L1s with test utterances was built into the curriculum module. 2.2 Spoken Interaction Tuition (Chat) To provide spoken interaction practice, MILLA sends the user to Michael (Level1) or Susan (Level 2), two chatbots created using the Pandorabots web-based chatbot hosting service . The bots were first implemented in text-to-text form in AIML (Artificial Intelligence Markup Language) and then TTS and ASR were added through the Web Speech API, conforming to W3C standards (W3C, 2014). Based on consultation with language teachers and learners, the system allows users to speak directly to the chat bot, or enter chat responses using text input. A chat log was also implemented into the interface, allowing the user to read back or replay several of their previous interactions with the chat bot. 2.3 Grammar, Vocabulary and External Resources MILLA’s curriculum includes a number of graded activities from the OUP’s English File and the British Council’s Learn English websites (REF). Wherever possible the system scrapes any scores returned for exercises and incorporates them into the learner’s record, while in other cases the progression and scoring system includes a time required to be spent on the exercises before the user progresses to the next exercises. There are also a number of custom morphology and syntax exercises designed for MILLA using Voxeo’s Prophecy platform and VoiceXML which will be ported to MILLA in the near future. 2.4 User State and Gesture Recognition MILLA includes a learner state module which will eventually infer boredom or involvement in the learner. As a first pass, gestures indicating various commands were designed and incorporated into the system using Microsoft’s Kinect SDK. The current implementation comprises four gestures (Stop, I don’t know, Swipe Left/Right), which were designed by tracking the skeletal movements involved and extracting joint coordinates on the x,y, and z planes to train the recognition process. As MILLA is multiplatform (Unix and Windows), Python’s socket programming modules was used to communicate between the Windows machine running the Kinect and the Mac laptop hosting MILLA.

Wallace: Incorporating Search into Chatting

Abstract: Chatbots are a well-established technology, however the conversational ability of the typical chatbot is greatly restricted. This paper investigates how the performance of a chatbot could be improved by connecting it with a knowledge source that could be used during its interactions with users. A new chatbot, Wallace, was created by extending Alice to incorporate knowledge from Wikipedia into its conversations. Mechanisms were designed and developed to retrieve Wikipedia pages, parse them, and select suitable sentences for the conversation. A user evaluation was conducted on the prototype, which showed that Wallace was generally more effective than Alice at providing factual answers to questions denoting an informational need. Participants also expressed that Wallace was more specific and more entertaining than Alice.

The chatbot strikes back

Abstract: Categories and Subject DescriptorsCategories and Subject DescriptorsH.1.2 [Models and Principles]: User/Machine SystemsGeneral TermsExperimentation, Human Factors, Theory

Film Theory and Chatbots

Abstract: The tools described in film theory are used to invoke feelings in the viewer as a form of entertainment. Some of these tools apply more directly to chatbots than others. Film combines visual images, music, and dialog to accomplish its goals. Conversing with a chatbot is akin to using a telegraph, or instant messaging on a cell phone. However, written communication may still convey emotions and feelings that people interpret on their own as they chat. It is useful to speak of the emotional content of written communications using film theory terminology.

Fairytale Child Chatbot

Abstract: WWW home page: http://ufal.mff.cuni.cz/rudolf-rosa Abstract: Fairytale Child (Pohadkove ditˇ e) is a simple chatbot trying to simulate a curious child. It asks the user to tell a fairy tale, often interrupting to ask for details and clarifications. However, it remembers what it was told and tries to show it if possible. The chatbot can communi- cate in Czech and in English. It analyzes the morphol- ogy of each sentence produced by the user with natural language processing tools, tries to identify potential ques- tions to ask, and then asks one. A morphological gener- ator is employed to generate correctly inflected sentences in Czech, so that the resulting sentences sound as natural as possible.