Showing papers on "Chatbot published in 2016"

Deep Reinforcement Learning for Dialogue Generation

Abstract: Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on future outcomes. Modeling the future direction of a dialogue is crucial to generating coherent, interesting dialogues, a need which led traditional NLP models of dialogue to draw on reinforcement learning. In this paper, we show how to integrate these goals, applying deep reinforcement learning to model future reward in chatbot dialogue. The model simulates dialogues between two virtual agents, using policy gradient methods to reward sequences that display three useful conversational properties: informativity, coherence, and ease of answering (related to forward-looking function). We evaluate our model on diversity, length as well as with human judges, showing that the proposed algorithm generates more interactive responses and manages to foster a more sustained conversation in dialogue simulation. This work marks a first step towards learning a neural conversational model based on the long-term success of dialogues.

Deep Reinforcement Learning for Dialogue Generation

Abstract: Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on future outcomes. Modeling the future direction of a dialogue is crucial to generating coherent, interesting dialogues, a need which led traditional NLP models of dialogue to draw on reinforcement learning. In this paper, we show how to integrate these goals, applying deep reinforcement learning to model future reward in chatbot dialogue. The model simulates dialogues between two virtual agents, using policy gradient methods to reward sequences that display three useful conversational properties: informativity (non-repetitive turns), coherence, and ease of answering (related to forward-looking function). We evaluate our model on diversity, length as well as with human judges, showing that the proposed algorithm generates more interactive responses and manages to foster a more sustained conversation in dialogue simulation. This work marks a first step towards learning a neural conversational model based on the long-term success of dialogues.

The return of the chatbots

Abstract: By all accounts, 2016 is the year of the chatbot. Some commentators take the view that chatbot technology will be so disruptive that it will eliminate the need for websites and apps. But chatbots have a long history. So what's new, and what's different this time? And is there an opportunity here to improve how our industry does technology transfer?

Building a Chatbot with Serverless Computing

Abstract: Chatbots are emerging as the newest platform used by millions of consumers worldwide due in part to the commoditization of natural language services, which provide provide developers with many building blocks to create chatbots inexpensively. However, it is still difficult to build and deploy chatbots. Developers need to handle the coordination of the cognitive services to build the chatbot interface, integrate the chatbot with external services, and worry about extensibility, scalability, and maintenance. In this work, we present the architecture and prototype of a chatbot using a serverless platform, where developers compose stateless functions together to perform useful actions. We describe our serverless architecture based on function sequences, and how we used these functions to coordinate the cognitive microservices in the Watson Developer Cloud to allow the chatbot to interact with external services. The serverless model improves the extensibility of our chatbot, which currently supports 6 abilities: location based weather reports, jokes, date, reminders, and a simple music tutor.

DocChat: An Information Retrieval Approach for Chatbot Engines Using Unstructured Documents

Abstract: Most current chatbot engines are designed to reply to user utterances based on existing utterance-response (or Q-R)1 pairs. In this paper, we present DocChat, a novel information retrieval approach for chatbot engines that can leverage unstructured documents, instead of Q-R pairs, to respond to utterances. A learning to rank model with features designed at different levels of granularity is proposed to measure the relevance between utterances and responses directly. We evaluate our proposed approach in both English and Chinese: (i) For English, we evaluate DocChat on WikiQA and QASent, two answer sentence selection tasks, and compare it with state-of-the-art methods. Reasonable improvements and good adaptability are observed. (ii) For Chinese, we compare DocChat with XiaoIce2, a famous chitchat engine in China, and side-by-side evaluation shows that DocChat is a perfect complement for chatbot engines using Q-R pairs as main source of responses.

Chatbot Using a Knowledge in Database: Human-to-Machine Conversation Modeling

Abstract: A chatterbot or chatbot aims to make a conversation between both human and machine. The machine has been embedded knowledge to identify the sentences and making a decision itself as response to answer a question. The response principle is matching the input sentence from user. From input sentence, it will be scored to get the similarity of sentences, the higher score obtained the more similar of reference sentences. The sentence similarity calculation in this paper using bigram which divides input sentence as two letters of input sentence. The knowledge of chatbot are stored in the database. The chatbot consists of core and interface that is accessing that core in relational database management systems (RDBMS). The database has been employed as knowledge storage and interpreter has been employed as stored programs of function and procedure sets for pattern-matching requirement. The interface is standalone which has been built using programing language of Pascal and Java.

An e-business chatbot using AIML and LSA

Abstract: The e-business has completely changed the way of selling products. E-commerce is one of the e-business models which mostly do business over the internet. The major drawback of this field is quality of customer service they provide. In every e-business model, customers have to wait for a long time to get response from the customer service representative. Especially in case of live chat, they talk to multiple customers at a time. The responses may not be relevant as they copy paste pre-written answers. Also, the slow response and the long time wait for the service agent is the biggest headache in this field of online services. As a solution to this problem, we propose a chatbot which automatically gives immediate responses to the users based on the data set of Frequently Answered Questions(FAQs), using Artificial Intelligence Markup Language (AIML) and Latent Semantic Analysis (LSA). Template based questions like greetings and general questions will be answered using AIML and other service related questions use LSA to give responses.

The Rise of the Conversational Interface: A New Kid on the Block?

Abstract: The conversational interface has become a hot topic in the past year or so, providing the primary means of interaction with chatbots, messaging apps, and virtual personal assistants. Major tech companies have been making huge investments in the supporting technologies of artificial intelligence, such as deep learning and natural language processing, with the aim of creating systems that will enable users of smartphones and other devices to obtain information and access services in a natural, conversational way. Yet the vision of the conversational interface is not new, and indeed there is a history of research in dialogue systems, voice user interfaces, embodied conversational agents, and chatbots that goes back more than fifty years. This chapter explores what has changed to make the conversational interface particularly relevant today, examines some key issues from earlier work that could inform the next generation of conversational systems, and highlights some challenges for future work.

Implementation of an inquisitive chatbot for database supported knowledge bases

Abstract: Chatbot is a piece of software that responds to natural language input and attempts to hold a conversation in a way that imitates a real person. Some chatbots are used for entertainment purposes, while others for business and commercial purposes. Chatbots are getting a lot of attention from business community right now as they can save costs in customer service centers and can handle multiple clients at a time. Successful implementation of a chatbot calls for correct analysis of user’s query by the bot and the formation of the correct response that should be given to the user. In many scenarios the information available from the user’s query is inadequate to provide the answer. In such contexts, the chatbot needs to be inquisitive so that it will be more interactive and can mimic a more natural human interaction. This paper reports the implementation of an inquisitive chatbot, which finds the missing data in query and probes the questions to users to collect data that are required to answer the query. Through this implementation, the level of interactivity between the user and the chatbot is improved.

MOOCBuddy: a Chatbot for personalized learning with MOOCs.

Abstract: With the proliferation of MOOCs (Massive Open Online Courses) providers, like Coursera, edX, FutureLearn, UniCampus.ro, NOVAMOOC.uvt.ro or MOOC.ro, it’s a real challenge to find the best learning resource. MOOCBuddy – a MOOC recommender system as a chatbot for Facebook Messenger, based on user’s social media profile and interests, could be a solution. MOOCBuddy is looking like the big trend of 2016, based on the Messenger Platform launched by Facebook in the mid of April 2016. Author

Sanative Chatbot For Health Seekers

Abstract: Now a day people tend to seek knowledge or information from internet that concern with health through online healthcare services. The basic aim of this system is to bridge the vocabulary gap between the health providers by proving instant replies to the questions posted by patients. Automatic generated content for healthcare services are chosen instead of traditional community generated systems because they are reliable, compatible, and provide instant replies. This paper proposes a scheme to code the medical record using local mining and global approaches. Local mining aims to code the medical records by extracting the medical concepts from individual record and then mapping them to terminologies based on external authenticated vocabularies. Local Mining establishes a tri-stage framework to accomplish this task. Global learning aims to learn missing key concepts and propagates precise terminologies among underlying connected records over a large collection. Index Terms Local mining, global learning, corpus aware terminology, POS tagger

Android based educational Chatbot for visually impaired people

Abstract: The purpose of this android application is to provide educational based Chatbot for visually impaired people. It will give an answer to the educational based queries asked by the visually impaired people. They can easily launch the application with the help of google voice search. Once the application is open, it will give a voice instruction to use an application. Output will be provided in voice form as well as in text form. So normal people can also use this application.

Visual Dialog

Abstract: We introduce the task of Visual Dialog, which requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content Specifically, given an image, a dialog history, and a question about the image, the agent has to ground the question in image, infer context from history, and answer the question accurately Visual Dialog is disentangled enough from a specific downstream task so as to serve as a general test of machine intelligence, while being grounded in vision enough to allow objective evaluation of individual responses and benchmark progress We develop a novel two-person chat data-collection protocol to curate a large-scale Visual Dialog dataset (VisDial) VisDial v09 has been released and contains 1 dialog with 10 question-answer pairs on ~120k images from COCO, with a total of ~12M dialog question-answer pairs We introduce a family of neural encoder-decoder models for Visual Dialog with 3 encoders -- Late Fusion, Hierarchical Recurrent Encoder and Memory Network -- and 2 decoders (generative and discriminative), which outperform a number of sophisticated baselines We propose a retrieval-based evaluation protocol for Visual Dialog where the AI agent is asked to sort a set of candidate answers and evaluated on metrics such as mean-reciprocal-rank of human response We quantify gap between machine and human performance on the Visual Dialog task via human studies Putting it all together, we demonstrate the first 'visual chatbot'! Our dataset, code, trained models and visual chatbot are available on this https URL

A Web-based Platform for Collection of Human-Chatbot Interactions

Abstract: Over recent years, the world has seen multiple uses for conversational agents. Chatbots has been implemented into ecommerce systems, such as Amazon Echo's Alexa [1]. Businesses and organizations like Facebook are also implementing bots into their applications. While a number of amazing chatbot platform exists, there are still difficulties in creating data-driven-systems as they large amount of data is needed for development and training. This paper we describe an advanced platform for evaluating and annotating human-chatbot interactions, its main features and goals, as well as the future plans we have for it.

Botta: An Arabic Dialect Chatbot

Abstract: This paper presents BOTTA, the first Arabic dialect chatbot. We explore the challenges of creating a conversational agent that aims to simulate friendly conversations using the Egyptian Arabic dialect. We present a number of solutions and describe the different components of the BOTTA chatbot. The BOTTA database files are publicly available for researchers working on Arabic chatbot technologies. The BOTTA chatbot is also publicly available for any users who want to chat with it online.

Usefulness, localizability, humanness, and language-benefit: additional evaluation criteria for natural language dialogue systems

Abstract: Human---computer dialogue systems interact with human users using natural language. We used the ALICE/AIML chatbot architecture as a platform to develop a range of chatbots covering different languages, genres, text-types, and user-groups, to illustrate qualitative aspects of natural language dialogue system evaluation. We present some of the different evaluation techniques used in natural language dialogue systems, including black box and glass box, comparative, quantitative, and qualitative evaluation. Four aspects of NLP dialogue system evaluation are often overlooked: "usefulness" in terms of a user's qualitative needs, "localizability" to new genres and languages, "humanness" or "naturalness" compared to human---human dialogues, and "language benefit" compared to alternative interfaces. We illustrated these aspects with respect to our work on machine-learnt chatbot dialogue systems; we believe these aspects are worthwhile in impressing potential new users and customers.

Conversational Interfaces: Past and Present

Abstract: Conversational interfaces have a long history, starting in the 1960s with text-based dialog systems for question answering and chatbots that simulated casual conversation. Speech-based dialog systems began to appear in the late 1980s and spoken dialog technology became a key area of research within the speech and language communities. At the same time commercially deployed spoken dialog systems, known in the industry as voice user interfaces (VUI), began to emerge. Embodied conversational agents (ECA) and social robots were also being developed. These systems combine facial expression, body stance, hand gestures, and speech in order to provide a more human-like and more engaging interaction. In this chapter we review developments in spoken dialog systems, VUI, embodied conversational agents, social robots, and chatbots, and outline findings and achievements from this work that will be important for the next generation of conversational interfaces.

A model of a social chatbot

Abstract: Traditional chatbots lack the capability to correctly manage conversations according to the social context. However a dialogue is a joint activity that must consider both individual and social processes. In this work we propose a model of a social chatbot able to choose the most suitable dialogue plans according to what in sociological literature is called a “social practice”. The proposed model is discussed considering a case study of a work in progress aimed at the development of a serious game for communicative skills learning.

Smart answering Chatbot based on OCR and Overgenerating Transformations and Ranking

Abstract: with rapid development of information and communication technology, people are very diverse in education, learning style, and knowledge improvement methods. This paper presents an approach of converting documents into knowledge of Chatbot system that enables users to make more benefits of it by asking and answering questions through the use of electronic documents integrated with simulate system. It is an integrated system for enrich contents of documents from popular format such as Portable Document Format (PDF) and digital photos. The workflow of this system is started from extracts texts using Optical Character Recognition (OCR) from files, then generates questions via Overgenerating Transformations and Ranking algorithm, and finally let Chatbot response to the user's question when it is matched with the String pattern.

Chatbot Technology with Synthetic Voices in the Acquisition of an Endangered Language: Motivation, Development and Evaluation of a Platform for Irish

Abstract: This paper describes the development and evaluation of a chatbot platform designed for the teaching/learning of Irish. The chatbot uses synthetic voices developed for the dialects of Irish. Speech-enabled chatbot technology offers a potentially powerful tool for dealing with the challenges of teaching/learning an endangered language where learners have limited access to native speaker models of the language and limited exposure to the language in a truly communicative setting. The sociolinguistic context that motivates the present development is explained. The evaluation of the chatbot was carried out in 13 schools by 228 pupils and consisted of two parts. Firstly, learners’ opinions of the overall chatbot platform as a learning environment were elicited. Secondly, learners evaluated the intelligibility, quality, and attractiveness of the synthetic voices used in this platform. Results were overwhelmingly positive to both the learning platform and the synthetic voices and indicate that the time may now be ripe for language learning applications which exploit speech and language technologies. It is further argued that these technologies have a particularly vital role to play in the maintenance of the endangered language.

Combined menu-based and natural-language-based communication with chatbots

Abstract: A user is allowed to communicate with a chatbot. A menu is provided to the user that includes a list of actions that can be performed by the user. Whenever natural language input asking a question is received from the user, this input is forwarded to the chatbot, a response to this input is received from the chatbot, this response is provided to the user, and the menu is again provided to the user. Whenever natural language input is received from the user requesting an action that is not one of the actions in the menu, this input is forwarded to the chatbot, a response to this input is received from the chatbot, where this response includes another menu that includes a list of subsequent actions that are related to the requested action and can be performed by the user, and this other menu is provided to the user.

Forming chatbot output based on user state

Abstract: Techniques are described herein for chatbots to achieve greater social grace by tracking users' states and providing corresponding dialog In various implementations, input may be received from a user at a client device operating a chatbot, eg, during a first session between the user and the chatbot The input may be semantically processed to determine a state expressed by the user to the chatbot An indication of the state expressed by the user may be stored in memory for future use by the chatbot It may then be determined, eg, by the chatbot based on various signals, that a second session between the user and the chatbot is underway In various implementations, as part of the second session, the chatbot may output a statement formed from a plurality of candidate words, phrases, and/or statements based on the stored indication of the state expressed by the user

Context-aware chatbot system and method

Abstract: A context-aware chatbot method and system are provided. The context-aware chatbot method comprises receiving a user's voice; converting the user's voice to a question to be answered; determining a question type of the question to be answered; generating at least one answer to the question based on a context-aware neural conversation model; validating the answer generated by the context-aware neural conversation model; and delivering the answer validated to the user. The context-aware neural conversation model takes contextual information of the question into consideration, and decomposes the contextual information of the question into a plurality of high dimension vectors.

Creating a Conversational Interface Using Chatbot Technology

Abstract: Conversational interfaces can be built using a variety of technologies. This chapter shows how to create a conversational interface using chatbot technology in which pattern matching is used to interpret the user’s input and templates are used to provide the system’s output. Numerous conversational interfaces have been built in this way, initially to develop systems that could engage in conversation in a human-like way but also more recently to create automated online assistants to complement or even replace human-provided services in call centers. In this chapter, some working examples of conversational interfaces using the Pandorabots platform are presented, along with a tutorial on AIML, a markup language for specifying conversational interactions.

Chatbots' Greetings to Human-Computer Communication.

Abstract: Both dialogue systems and chatbots aim at putting into action communication between humans and computers. However, instead of focusing on sophisticated techniques to perform natural language understanding, as the former usually do, chatbots seek to mimic conversation. Since Eliza, the first chatbot ever, developed in 1966, there were many interesting ideas explored by the chatbots' community. Actually, more than just ideas, some chatbots' developers also provide free resources, including tools and large-scale corpora. It is our opinion that this know-how and materials should not be neglected, as they might be put to use in the human-computer communication field (and some authors already do it). Thus, in this paper we present a historical overview of the chatbots' developments, we review what we consider to be the main contributions of this community, and we point to some possible ways of coupling these with current work in the human-computer communication research line.

The Dawn of the Conversational Interface

Abstract: With a conversational interface, people can speak to their smartphones and other smart devices in a natural way in order to obtain information, access Web services, issue commands, and engage in general chat. This chapter presents some examples of conversational interfaces and reviews technological advances that have made conversational interfaces possible. Following this, there is an overview of the technologies that make up a conversational interface.

Challenges facing the development of the Arabic chatbot

Abstract: The future information systems are expected to be more intelligent and will take human queries in natural language as input and answer them promptly. To develop a chatbot or a computer program that can chat with humans in realistic manner to extent that human get impressions that he/she is talking with other human is a challenging task. To make such chatbots, different technologies will work together ranging from artificial intelligence to development of semantic resources. Sophisticated chatbots are developed to perform conversation in number of languages. Arabic chatbots can be helpful in automating many operations and serve people who only know Arabic language. However, the technology for Arabic language is still in its infancy stage due to some challenges surrounding the Arabic language. This paper offers an overview of the chatbot application and the several obstacles and challenges that need to be resolved to develop an effective Arabic chatbot.

Natural language platform for database system

Abstract: An artificial intelligence assistant (“chatbot”) operates within a multi-tenant database and allows users to interact with the underlying structured database through a natural language interface without using a standard structured query language or database interface. Users may interact with the chatbot via a chatroom and perform database queries using natural language expressions in the same manner as asking a person to perform the tasks. In addition, the chatbot may check user permissions and security parameters to determine if the user is permitted to access or alter data within the multi-tenant database.

Detecting Context Dependent Messages in a Conversational Environment

Abstract: While automatic response generation for building chatbot systems has drawn a lot of attention recently, there is limited understanding on when we need to consider the linguistic context of an input text in the generation process. The task is challenging, as messages in a conversational environment are short and informal, and evidence that can indicate a message is context dependent is scarce. After a study of social conversation data crawled from the web, we observed that some characteristics estimated from the responses of messages are discriminative for identifying context dependent messages. With the characteristics as weak supervision, we propose using a Long Short Term Memory (LSTM) network to learn a classifier. Our method carries out text representation and classifier learning in a unified framework. Experimental results show that the proposed method can significantly outperform baseline methods on accuracy of classification.