Showing papers on "Chatbot published in 2017"

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 contains 1 dialog (10 question-answer pairs) on ~140k images from the COCO dataset, with a total of ~1.4M 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. Our dataset, code, and trained models will be released publicly at https://visualdialog.org. Putting it all together, we demonstrate the first visual chatbot!.

Why People Use Chatbots

Abstract: There is a growing interest in chatbots, which are machine agents serving as natural language user interfaces for data and service providers. However, no studies have empirically investigated people’s motivations for using chatbots. In this study, an online questionnaire asked chatbot users (N = 146, aged 16–55 years) from the US to report their reasons for using chatbots. The study identifies key motivational factors driving chatbot use. The most frequently reported motivational factor is “productivity”; chatbots help users to obtain timely and efficient assistance or information. Chatbot users also reported motivations pertaining to entertainment, social and relational factors, and curiosity about what they view as a novel phenomenon. The findings are discussed in terms of the uses and gratifications theory, and they provide insight into why people choose to interact with automated agents online. The findings can help developers facilitate better human–chatbot interaction experiences in the future. Possible design guidelines are suggested, reflecting different chatbot user motivations.

A New Chatbot for Customer Service on Social Media

Abstract: Users are rapidly turning to social media to request and receive customer service; however, a majority of these requests were not addressed timely or even not addressed at all. To overcome the problem, we create a new conversational system to automatically generate responses for users requests on social media. Our system is integrated with state-of-the-art deep learning techniques and is trained by nearly 1M Twitter conversations between users and agents from over 60 brands. The evaluation reveals that over 40% of the requests are emotional, and the system is about as good as human agents in showing empathy to help users cope with emotional situations. Results also show our system outperforms information retrieval system based on both human judgments and an automatic evaluation metric.

A Theoretical Framework for Conversational Search

Abstract: This paper studies conversational approaches to information retrieval, presenting a theory and model of information interaction in a chat setting. In particular, we consider the question of what properties would be desirable for a conversational information retrieval system so that the system can allow users to answer a variety of information needs in a natural and efficient manner. We study past work on human conversations, and propose a small set of properties that taken together could measure the extent to which a system is conversational. Following this, we present a theoretical model of a conversational system that implements the properties. We describe how this system could be implemented, making the action space of an conversational search agent explicit. Our analysis of this model shows that while theoretical, the model could be practically implemented to satisfy the desirable properties presented. In doing so, we show that the properties are also feasible.

SuperAgent: A Customer Service Chatbot for E-commerce Websites

Abstract: Conventional customer service chatbots are usually based on human dialogue, yet significant issues in terms of data scale and privacy. In this paper, we present SuperAgent, a customer service chatbot that leverages large-scale and publicly available e-commerce data. Distinct from existing counterparts, SuperAgent takes advantage of data from in-page product descriptions as well as user-generated content from e-commerce websites, which is more practical and cost-effective when answering repetitive questions, freeing up human support staff to answer much higher value questions. We demonstrate SuperAgent as an add-on extension to mainstream web browsers and show its usefulness to user’s online shopping experience.

Evaluating Quality of Chatbots and Intelligent Conversational Agents.

Abstract: Chatbots are one class of intelligent, conversational software agents activated by natural language input (which can be in the form of text, voice, or both). They provide conversational output in response, and if commanded, can sometimes also execute tasks. Although chatbot technologies have existed since the 1960s and have influenced user interface development in games since the early 1980s, chatbots are now easier to train and implement. This is due to plentiful open source code, widely available development platforms, and implementation options via Software as a Service (SaaS). In addition to enhancing customer experiences and supporting learning, chatbots can also be used to engineer social harm - that is, to spread rumors and misinformation, or attack people for posting their thoughts and opinions online. This paper presents a literature review of quality issues and attributes as they relate to the contemporary issue of chatbot development and implementation. Finally, quality assessment approaches are reviewed, and a quality assessment method based on these attributes and the Analytic Hierarchy Process (AHP) is proposed and examined.

A Deep Reinforcement Learning Chatbot

Abstract: We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including template-based models, bag-of-words models, sequence-to-sequence neural network and latent variable neural network models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed significantly better than many competing systems. Due to its machine learning architecture, the system is likely to improve with additional data.

Chatbot for university related FAQs

Abstract: Chatbots are programs that mimic human conversation using Artificial Intelligence (AI). It is designed to be the ultimate virtual assistant, entertainment purpose, helping one to complete tasks ranging from answering questions, getting driving directions, turning up the thermostat in smart home, to playing one's favorite tunes etc. Chatbot has become more popular in business groups right now as they can reduce customer service cost and handles multiple users at a time. But yet to accomplish many tasks there is need to make chatbots as efficient as possible. To address this problem, in this paper we provide the design of a chatbot, which provides an efficient and accurate answer for any query based on the dataset of FAQs using Artificial Intelligence Markup Language (AIML) and Latent Semantic Analysis (LSA). Template based and general questions like welcome/ greetings and general questions will be responded using AIML and other service based questions uses LSA to provide responses at any time that will serve user satisfaction. This chatbot can be used by any University to answer FAQs to curious students in an interactive fashion.

AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine

Abstract: We propose AliMe Chat, an open-domain chatbot engine that integrates the joint results of Information Retrieval (IR) and Sequence to Sequence (Seq2Seq) based generation models. AliMe Chat uses an attentive Seq2Seq based rerank model to optimize the joint results. Extensive experiments show our engine outperforms both IR and generation based models. We launch AliMe Chat for a real-world industrial application and observe better results than another public chatbot.

A Chatbot for Psychiatric Counseling in Mental Healthcare Service Based on Emotional Dialogue Analysis and Sentence Generation

Abstract: There are early studies to attempt users for psychiatric counseling with chatbot. They lead to changes in drinking habit based on intervention approach via chat bot. The application does not consider the user's psychiatric status through the conversations, continuous user monitoring, and ethical judgment in the intervention. We contend that more accurate and continuous emotion recognition gives better satisfaction to users who need mental health care. In addition, appropriate clinical psychological response based on ethical responses is as well. We suggest a conversational service for psychiatric counseling that is adapted methodologies to understand counseling contents based on of high-level natural language understanding (NLU), and emotion recognition based on multi-modal approach. The methodologies enable continuous observation of emotional changes sensitively. In addition, the case-based counseling response model that combines ethical judgment model provides a suitable response to clinical psychiatric counseling.

Programming challenges of chatbot: Current and future prospective

Abstract: In the modern Era of technology, Chatbots is the next big thing in the era of conversational services Chatbots is a virtual person who can effectively talk to any human being using interactive textual skills Currently, there are many cloud base Chatbots services which are available for the development and improvement of the chatbot sector such as IBM Watson, Microsoft bot, AWS Lambda, Heroku and many others A virtual person is based on machine learning and Artificial Intelligence (AI) concepts and due to dynamic nature, there is a drawback in the design and development of these chatbots as they have built-in AI, NLP, programming and conversion services This paper gives an overview of cloud-based chatbots technologies along with programming of chatbots and challenges of programming in current and future Era of chatbot

A Survey of Design Techniques for Conversational Agents

Abstract: A conversational agent also referred to as chatbot is a computer program which tries to generate human like responses during a conversation. Earlier chatbots employed much simpler retrieval based pattern matching design techniques. However, with time a number of new chatbots evolved with an aim to make it more human like and hence to pass the Turing test. Now, most of the chatbots employ generative knowledge based techniques. This paper will discuss about various chatbot design techniques, classification of chatbot and discussion on how the modern chatbots have evolved from simple pattern matching, retrieval based model to modern complex knowledge based models. A table of major conversational agents in chronological order along with their design techniques is also provided at the end of the paper.

Towards a chatbot for digital counselling

Abstract: The aim of this paper is to outline the design of a chatbot to be used within mental health counselling. One of the main causes of the burden of disease worldwide is mental health problems. Mental health contributes to 28% of the total burden of disease, compared to 16% each for cancer and heart disease in the UK. Stress, anxiety or depression accounted for 15.8 million days of sickness absence across the UK in 2016. By 2020, the gap between the demand for mental health care and the resources the National Health Service (NHS) can provide is likely to widen, therefore providers are increasingly needing to find more cost-effective ways to deliver mental health care. Digital Interventions have been created to help with these issues, for example anxiety, stress and depression. Chatbots can be incorporated into digital interventions, or used as standalone interventions. Chatbots can be a more interactive experience for the user to receive information, or complete diagnostic tools, or to even be used for counselling. A demo chatbot was created using interactive emoji’s and GIFs to improve the user experience when searching for online self-help tips. This chatbot will be further developed and incorporated into a full web based programme for mental health in the workplace. It is envisaged that the chatbot will be able to provide initial counselling, and lead users into the correct services or self-help information.

I'm Sorry, Dave, I'm Afraid I Can't Do That: Chatbot Perception and Expectations

Abstract: Artificial intelligence continues to grow in popularity on mobile platforms, increasing exposure to chatbot apps. Chatbot technology has evolved over time, yet the purpose and added value that chatbots offer has not been clearly defined. In order to design a chatbot that provides a meaningful experience, we must first understand what expectations people have for this technology, and what opportunities are there for chatbots based on user needs. This study includes qualitative data from 54 participants in the US and India, sharing their expectations and experiences with a chatbot. The research objectives include:1) understand user perception and expectations of chatbots 2) surface preferences for input modality and 3) identify domains where chatbots can add meaningful purpose.

MANDY: Towards a Smart Primary Care Chatbot Application

Abstract: The paper reports on a proof-of-concept of \(\mathsf {Mandy}\), a primary care chatbot system created to assist healthcare staffs by automating the patient intake process. The chatbot interacts with a patient by carrying out an interview, understanding their chief complaints in natural language, and submitting reports to the doctors for further analysis. The system provides a mobile-app front end for the patients, a diagnostic unit, and a doctor’s interface for accessing patient records. The diagnostic unit consists of three main modules: An analysis engine for understanding patients symptom descriptions, a symptom-to-cause mapper for reasoning about potential causes, and a question generator for deriving further interview questions. The system combines data-driven natural language processing capability with knowledge-driven diagnostic capability. We evaluate our proof-of-concept on benchmark case studies and compare the system with existing medical chatbots.

The chatbot feels you - a counseling service using emotional response generation

Abstract: Early study tries to use chatbot for counseling services. They changed drinking habit of who being consulted by leading them via intervene chatbot. However, the application did not concerned about psychiatric status through continuous conversation with user monitoring. Furthermore, they had no ethical judgment method that about the intervention of the chatbot. We argue that more reasonable and continuous emotion recognition will make better mental healthcare experiment. It will be more proper clinical psychiatric consolation in ethical view as well. This paper suggests a introduce a novel chatbot system for psychiatric counseling service. Our system understands content of conversation based on recent natural language processing (NLP) methods with emotion recognition. It senses emotional flow through the continuous observation of conversation. Also, we generate personalized counseling response from user input, to do this, we use additional constrains to generation model for the proper response generation which can detect conversational context, user emotion and expected reaction.

Beyond the Words: Predicting User Personality from Heterogeneous Information

Abstract: An incisive understanding of user personality is not only essential to many scientific disciplines, but also has a profound business impact on practical applications such as digital marketing, personalized recommendation, mental diagnosis, and human resources management. Previous studies have demonstrated that language usage in social media is effective in personality prediction. However, except for single language features, a less researched direction is how to leverage the heterogeneous information on social media to have a better understanding of user personality. In this paper, we propose a Heterogeneous Information Ensemble framework, called HIE, to predict users' personality traits by integrating heterogeneous information including self-language usage, avatar, emoticon, and responsive patterns. In our framework, to improve the performance of personality prediction, we have designed different strategies extracting semantic representations to fully leverage heterogeneous information on social media. We evaluate our methods with extensive experiments based on a real-world data covering both personality survey results and social media usage from thousands of volunteers. The results reveal that our approaches significantly outperform several widely adopted state-of-the-art baseline methods. To figure out the utility of HIE in a real-world interactive setting, we also present DiPsy, a personalized chatbot to predict user personality through heterogeneous information in digital traces and conversation logs.

How Do You Want Your Chatbot? An Exploratory Wizard-of-Oz Study with Young, Urban Indians

Abstract: As text-messaging chatbots become increasingly “human”, it will be important to understand the personal interactions that users are seeking with a chatbot. What chatbot personalities are most compelling to young, urban users in India? To explore this question, we first conducted exploratory Wizard-of-Oz (WoZ) studies with 14 users that simulated interactions with a hypothetical chatbot. We evaluated three personalities for the chatbot—Maya, a productivity oriented bot with nerd wit; Ada, a fun, flirtatious bot; and Evi, an emotional buddy bot. We followed up with one-on-one interviews with the users discussing their experiences with each of the chatbots, what they liked, and what they did not. Overall our results show that users wanted a chatbot like Maya, who could add value to their life while being a friend, by making useful recommendations. But they also wanted preferred traits of Ada and Evi infused into Maya.

Home automation using IoT and a chatbot using natural language processing

Abstract: Home automation — controlling the fans, lights and other electrical appliances in a house using Internet of things is widely preferred in recent days. In this paper, we propose a web application using which the fans, lights and other electrical appliances can be controlled over the Internet. The important features of the web application is that firstly, we have a chatbot algorithm such that the user can text information to control the functioning of the electrical appliances at home. The messages sent using the chatbot is processed using Natural Language processing techniques. Secondly, any device connected to the local area network of the house can control the devices and other appliances in the house. Thirdly, the web application used to enable home automation also has a security feature that only enables certain users to access the application. And finally, it also has a functionality of sending an email alert when intruder is detected using motion sensors.

SHIHbot: A Facebook chatbot for Sexual Health Information on HIV/AIDS

Abstract: We present the implementation of an autonomous chatbot, SHIHbot, deployed on Facebook, which answers a wide variety of sexual health questions on HIV/AIDS The chatbot’s response database is com-piled from professional medical and public health resources in order to provide reliable information to users The system’s backend is NPCEditor, a response selection platform trained on linked questions and answers; to our knowledge this is the first retrieval-based chatbot deployed on a large public social network

VILLAGE- Virtual Immersive Language Learning and Gaming Environment: Immersion and presence.

Abstract: 3 D virtual worlds are promising for immersive learning in English as a Foreign Language ( EFL). Unlike English as a Second Language ( ESL), EFL typically takes place in the learners' home countries, and the potential of the language is limited by geography. Although learning contexts where English is spoken is important, in most EFL courses at the college level, EFL is taught by acquiring vocabularies, grammar and pragmatic features without contextual immersion. In this study, an immersive English learning environment in a 3 D virtual world, Open Simulator, was developed with two key learning artifacts, chatbot and time machine. A single-factor, independent measures design was used to examines learners' presence under four learning conditions: virtual learning environment without digital learning artifacts ( VE), virtual learning environment with chatbot ( VEC), virtual learning environment with time machine ( VETM) and virtual learning environment with chatbot and time machine ( VECTM). Three research questions emerging from the four learning conditions form the backbone of this study: (1) Does chatbot increase language learners' presence in the immersive virtual English learning environment? (2) Does time machine increase language learners' presence in the immersive virtual English learning environment? (3) Does the combined use of chatbot and time machine increase presence more than either learning artifact alone? The experimental results indicate that the chatbot and time machine increase the learners' sense of immersion and presence. Best design practices should address how immersion and presence can be integrated into affordances of virtual worlds. [ABSTRACT FROM AUTHOR]

Interacting with a conversational agent system for educational purposes in online courses

Abstract: Since distance education creates new opportunities for learners, the enrollment in online courses has been sharply increasing in higher education. However, the higher attrition rate is one of the more significant concerns in this field. Educational researchers have found that meaningful interactions play a significant role in learner persistence in online courses. Still, it is challenging for an individual instructor to promote learners' positive interaction experiences. The expectation of improved learners' interaction with conversational agent systems has received attention in the distance education field. Few conversational agent systems have been developed for educational purposes, and few systems are used in real online learning settings. This study aims at designing and developing a conversational agent system to promote the learner's meaningful interaction in online courses, and also exploring the feasibility of human interaction with the conversational agent system, or chatbot, in online courses in higher education. The primary findings of this study show that instant, content-related, and quality interactions between the learner and the conversational agent system is applicable to graduate-level online courses. Implications and future research are discussed.

Mobile conversational commerce: messenger chatbots as the next interface between businesses and consumers

Abstract: Nowadays, businesses are slowly starting to deploy mobile messenger chatbots as a new method of communication with its customers. Due to the subject’s infancy and lack of research on the subject, the purpose of this study is to explore the concept of mobile messenger chatbots and an attempt is made to determine the Dutch Millennials’ intention to use messenger chatbots as the next interface for mobile commerce. A research model is proposed based on the Technology Acceptance Model (TAM) and Innovation Diffusion Theory (IDT). Data is collected by means of an online survey among 195 participants. The proposed research model is tested by means of simple regression analysis and results are cross-validated using IBM Watson Analytics. All proposed hypotheses are supported. However, there is no unambiguous answer to whether Dutch Millennials have the intention to use mobile messenger chatbots as the next interface for commerce. Nonetheless, more than half of the respondents express a positive first impression towards mobile messenger chatbots. This study knows some limitations regarding external validity and the research model is limited to five independent constructs. Additional constructs or measurement tools could be used to obtain a deeper understanding regarding the subject. Moreover, using a real-life experiment may generate distinctive results. Organizations wanting to deploy messenger chatbots, marketers and chatbot developers should consider compatibility, the consumers’ lifestyle and shopping preferences, for a successful implementation. Similarly, the consumers’ privacy concerns and resistance to intrusive mobile advertisement are important topics to be considered.

Hands-On Chatbots and Conversational UI Development: Build chatbots and voice user interfaces with Chatfuel, Dialogflow, Microsoft Bot Framework, Twilio, and Alexa Skills

Abstract: Build over 8 chatbots and conversational user interfaces with leading tools such as Chatfuel, Dialogflow, Microsoft Bot Framework, Twilio, Alexa Skills, and Google Actions and deploying them on channels like Facebook Messenger, Amazon Alexa and Google Home Key Features Understand the different use cases of Conversational UIs with this project-based guideBuild feature-rich Chatbots and deploy them on multiple platforms Get real-world examples of voice-enabled UIs for personal and home assistanceBook Description Conversation as an interface is the best way for machines to interact with us using the universally accepted human tool that is language. Chatbots and voice user interfaces are two flavors of conversational UIs. Chatbots are real-time, data-driven answer engines that talk in natural language and are context-aware. Voice user interfaces are driven by voice and can understand and respond to users using speech. This book covers both types of conversational UIs by leveraging APIs from multiple platforms. We'll take a project-based approach to understand how these UIs are built and the best use cases for deploying them. We'll start by building a simple messaging bot from the Facebook Messenger API to understand the basics of bot building. Then we move on to creating a Task model that can perform complex tasks such as ordering and planning events with the newly-acquired-by-Google Dialogflow and Microsoft Bot framework. We then turn to voice-enabled UIs that are capable of interacting with users using speech with Amazon Alexa and Google Home. By the end of the book, you will have created your own line of chatbots and voice UIs for multiple leading platforms. What you will learn Design the flow of conversation between the user and the chatbot Create Task model chatbots for implementing tasks such as ordering foodGet new toolkits and services in the chatbot ecosystem Integrate third-party information APIs to build interesting chatbots Find out how to deploy chatbots on messaging platforms Build a chatbot using MS Bot Framework See how to tweet, listen to tweets, and respond using a chatbot on Twitter Publish chatbots on Google Assistant and Amazon Alexa Who This Book Is For This book is for developers who are interested in creating interactive conversational UIs/Chatbots. A basic understanding of JavaScript and web APIs is required.

Design and Evaluation of a Mobile Chat App for the Open Source Behavioral Health Intervention Platform MobileCoach

Abstract: The open source platform MobileCoach (mobile-coacheu) has been used for various behavioral health interventions in the public health context However, so far, MobileCoach is limited to text message-based interactions That is, participants use error-prone and laborious text-input fields and have to bear the SMS costs Moreover, MobileCoach does not provide a dedicated chat channel for individual requests beyond the processing capabilities of its chatbot Intervention designers are also limited to text-based self-report data In this paper, we thus present a mobile chat app with pre-defined answer options, a dedicated chat channel for patients and health professionals and sensor data integration for the MobileCoach platform Results of a pretest (N = 11) and preliminary findings of a randomized controlled clinical trial (N = 14) with young patients, who participate in an intervention for the treatment of obesity, are promising with respect to the utility of the chat app

An Adaptive Learning with Gamification & Conversational UIs: The Rise of CiboPoliBot

Abstract: Gamification in the era of chatbots is a novel way to engage users with the chatbot application. When developing a gamified chatbot system, there are factors related to user types (ages, gender and others) that we should consider to effectively integrate the game elements into the chatbot while targeting the right audience. In this study, we discuss the development of an educational chatbot game 'CiboPoli', that's specialised in teaching children about healthy lifestyle through an interactive social game environment. The presented game is based on a paper prototype that we developed to teach primary school students about healthy diet and food waste management. The current approach will be more engaging and pose AI capabilities. This is still a work in progress and we plan to improve its design by incorporating additional components, such as dialog management module, user-specific knowledge module or machine learning module. Future work will be devoted to integrating machine learning to automatically identify learners emotions and provide personalised suggestions. Moreover, we tested the initial prototype with school students and found that it outperforms the paper version. Future work will focus on applying it to other domains and demographics.

A Review of Technologies for Conversational Systems

Abstract: During the last 50 years, since the development of ELIZA by Weizenbaum, technologies for developing conversational systems have made a great stride. The number of conversational systems is increasing. Conversational systems emerge almost in every digital device in many application areas. In this paper, we present the review of the development of conversational systems regarding technologies and their special features including language tricks.

A chatbot using LSTM-based multi-layer embedding for elderly care

Abstract: According to demographic changes, the services designed for the elderly are becoming more needed than before and increasingly important. In previous work, social media or community-based question-answer data were generally used to build the chatbot. In this study, we collected the MHMC chitchat dataset from daily conversations with the elderly. Since people are free to say anything to the system, the collected sentences are converted into patterns in the preprocessing part to cover the variability of conversational sentences. Then, an LSTM-based multi-layer embedding model is used to extract the semantic information between words and sentences in a single turn with multiple sentences when chatting with the elderly. Finally, the Euclidean distance is employed to select a proper question pattern, which is further used to select the corresponding answer to respond to the elderly. For performance evaluation, five-fold cross-validation scheme was employed for training and evaluation. Experimental results show that the proposed method achieved an accuracy of 79.96% for top-1 response selection, which outperformed the traditional Okapi model.

DeepProbe: Information Directed Sequence Understanding and Chatbot Design via Recurrent Neural Networks

Abstract: Information extraction and user intention identification is a central topic in modern query understanding and recommendation systems. In this paper, we propose DeepProbe, a generic information-directed interaction framework which is built around an attention-based sequence to sequence (seq2seq) recurrent neural network. DeepProbe can rephrase, evaluate, and even actively ask questions, leveraging the generative ability and likelihood estimation made possible by seq2seq models. DeepProbe makes decisions based on a derived uncertainty (entropy) measure conditioned on user inputs, possibly with multiple rounds of interactions. Three applications, namely a rewritter, a relevance scorer and a chatbot for ad recommendation, were built around DeepProbe, with the first two serving as precursory building blocks for the third. We first use the seq2seq model in DeepProbe to rewrite a user query into one of standard query form, which is submitted to an ordinary recommendation system. Secondly, we evaluate DeepProbe's seq2seq model-based relevance scoring. Finally, we build a chatbot prototype capable of making active user interactions, which can ask questions that maximize information gain, allowing for a more efficient user intention idenfication process. We evaluate first two applications by 1) comparing with baselines by BLEU and AUC, and 2) human judge evaluation. Both demonstrate significant improvements compared with current state-of-the-art systems, proving their values as useful tools on their own, and at the same time laying a good foundation for the ongoing chatbot application.