The Paper Submission Deadline extended to May 22, 2018 11:59 PST

In conjunction with KDD 2018
August 20, 2018 - London, UK

Conversational AI and its Applications


Conversational AI Data challenges are becoming increasingly common. Examples include the Amazon Alexa prize, AWS Chatbot challenges, NIPS Conversational Intelligence Challenge, DSTC6 Dialog Systems Technology Challenge, etc. These standards provide a shared challenge and a common basis for interdisciplinary researchers and industrial practitioners to come together and work on a cross-pollination of innovation through sharing, discussing, and debating ideas. Now more than ever, it is crucial to promote this workshop for the advancement, education, and knowledge discovery on ideas of conversational AI and its applications.

The goal of the workshop is to encourage researchers and practitioners around the world to share insights on early research and introduce novel applications in the area of conversational artificial intelligence. In addition to research papers, we also welcome submissions of innovative applications or survey papers highlighting recent work, breakthroughs, and trends.


Speaker Title Duration
Dr. Chu-Cheng Hsieh Opening speech 5 mins
Dr. Haixun Wang Keynote: Chatbots and Natural Language Interfaces for Databases 30 mins
Zijun Xue Recent progress in Conversational AI 20 mins
Ruirui Li Enhancing Response Generation by Chat Flow Identification 20 mins
Rogers Jeffrey Leo John A Conversational Interface for Data Analysis - Applications in the Neuroimaging and Biomedical Domain 20 mins
Shan-Yun Teng UrBot: Unknowns Recommendation by Exploring Concept Graphs with Reinforcement Learning 20 mins
Break 5 mins
Khatri Chandra Keynote: Advancing the State of Dialog Systems in End-to-End manner through Conversational Topic Models 25 mins
Dr. Miguel Molina-Solana Conversational AI for Data Exploration 20 mins
Indrajit Bhattacharya Learning Knowledge Graph Schema via Dialog 20 mins
Mingen Hsieh ObjFind: An Objective Identification Conversational AI Framework Incorporating Multimedia Widgets 20 mins
Prof Lingyun Sun Keynote: A New Paradigm of Design Empowered by Creative AI 30 mins
Closing 5 mins


Haixun Wang

Title: Chatbots and Natural Language Interfaces for Databases

Summary: One biggest challenge of conversation AI is interfacing with databases. Relational database management systems (RDBMSs) are powerful because they are able to optimize and answer queries against any relational database. A natural language interface (NLI) for a database, on the other hand, is tailored to support that specific database and its applications. In this talk, I will introduce a general purpose transfer-learnable NLI with the goal of learning one model that can be used as NLI for any relational database. We adopt the data management principle of separating data and its schema, but with the additional support for the idiosyncrasy and complexity of natural languages. Specifically, we introduce an automatic annotation mechanism that separates the schema and the data, where the schema also covers knowledge about natural language. Furthermore, we propose a customized sequence model that translates annotated natural language queries to SQL statements.

Dr. Haixun Wang is an IEEE fellow and a VP of Engineering and Distinguished Scientist at WeWork, where he leads the Research and Applied Science division. He was Director of Natural Language Processing at Amazon. Before Amazon, he led the NLP Infra team in Facebook working on Query and Document Understanding. From 2013 to 2015, he was with Google Research, working on natural language processing. From 2009 to 2013, he led research in semantic search, graph data processing systems, and distributed query processing at Microsoft Research Asia. His knowledge base project Probase has created significant impact in industry and academia. He had been a research staff member at IBM T. J. Watson Research Center from 2000 – 2009. He was Technical Assistant to Stuart Feldman (Vice President of Computer Science of IBM Research) from 2006 to 2007, and Technical Assistant to Mark Wegman (Head of Computer Science of IBM Research) from 2007 to 2009. He received the Ph.D. degree in Computer Science from the University of California, Los Angeles in 2000. He has published more than 150 research papers in referred international journals and conference proceedings. He served PC Chair of conferences such as CIKM’12, and he is on the editorial board of journals such as IEEE Transactions of Knowledge and Data Engineering (TKDE) and Journal of Computer Science and Technology (JCST). He won the best paper award in ICDE 2015, 10-year best paper award in ICDM 2013, and best paper award of ER 2009.

Fei Wu

Title: Memory-augmented sequence2sequence learning

Summary:Neural networks with a memory capacity provide a promising approach to media understanding (e.g., Q-A and visual classification). In this talk, I will present how to utilize the information in external memory to boost media understanding. In general, the relevant information (e.g., knowledge instance and exemplar data) w.r.t the input data is sparked from external memory in the manner of memory-augmented learning. Memory-augmented learning is an appropriate method to integrate data-driven learning, knowledge-guided inference and experience exploration.

Fei Wu is a professor at the college of computer science, Zhejiang University. From October, 2009 to August 2010, Fei Wu was a visiting scholar at Prof. Bin Yu's group, University of California, Berkeley. Currently, he is the vice-dean of college of Computer Science, and the director of Institute of Artificial Intelligence of Zhejiang University. His research interests mainly include Artificial Intelligence, cross-media computing, and multimedia retrieval. He has won various honors such as the Award of National Science Fund for Distinguished Young Scholars of China (2016).

Lingyun Sun

Title: Creative AI

Summary: The traditional process of creative design is performed as a chain in the product lifecycle. Due to the little interaction between user and designer in a design process, the output design results are often constrained by the input user needs. Now, with the emergence of Creative AI, the designers are equipped with technologies like experience computing, design intelligence, and perception enhancement. Design intelligence enables us to generate large volumes of personalized content; Perception enhancement provides us more information with rich channels and media; Experience computing allows us to get real user experiences under actual scenarios. With the power of Creative AI, the design can respond much better to user’s needs, provide personalized or customized content, and deliver these content to users with the most appropriate channel or media. Thus, the design, empowered by Creative AI, is not a chain in the life cycle of a product, but an organic and seamless integration with users and all links of productization

Prof Lingyun Sun is the Deputy Director of International Design Institute at Zhejiang University, the Director of Alibaba-ZJU Joint Lab on Intelligence, Design, Experience and Aesthetics, the Director of ZJU-SUTD Innovation, Design and Entrepreneurship Alliance, and the Deputy Director of ZJU-Beidou Joint Innovation Design Engineering Center. Prof Sun’s research interests include design intelligence, design thinking, information and interaction design, design cognition and computation. He is a PI to research grants funded by National Natural Science Foundation and National Basic Research Program of China.

Khatri Chandra

Title: Advancing the state of Dialog Systems using Conversational Topic Model

Summary: Topic models find a lot of applications in Natural Language Processing tasks. While the most popular variant of topic models has been unsupervised (LDA, PLSA), they suffer from issues like cluster numbers, noise, and interpretability. In this talk, I will present a supervised conversational topic model trained using Bi-LSTM and Attentional Deep Average Networks (ADAN), which can predict topics like “Sports”, “Politics”, “Technology”, etc. for a given text along with the keywords pertaining to the topic. Given the interpretability and robustness of the proposed topic model, I show that such a model can be used for a variety of tasks. In this talk, I depict the applications and advancements brought by the model in Conversational Speech Recognition, Natural Language Understanding, Response Generation and Dialog Evaluation. Lastly, the application of this topic model is depicted in context with the “Alexa Prize”, a 3.5 million-dollar university competition to advance Conversational AI, and is depicted that this model is extremely useful for open-domain conversations.

Khatri Chandra is an Artificial Intelligence Scientist at Amazon Lab126 with a research and development team responsible for making Alexa conversational. Currently, he is the leading scientist for Alexa Prize competition, which is a $3.5 Million university competition for advancing the state of Conversational AI. Some of his recent work involves Open-domain Dialog Planning, Natural Language Generation, Evaluation, and Conversational Speech Recognition.
Prior to Alexa, Chandra was a Research Scientist at eBay in an Applied Science group. At eBay he lead various Deep Learning and NLP initiatives such as Automatic Text Summarization and Automatic Content Generation within the eCommerce domain. His work led to significant gains at eBay. He holds degrees in Machine Learning and Computational Science & Engineering from Georgia Tech and BITS, Pilani.


The objective of this workshop is to create a forum for researchers and practitioners to exchange ideas and highlight current trends, common roadblocks, and insights for the future of applications in dialogue systems, conversational AI, intelligent assistants, and similar technologies.
This workshop will include invited talks from academia and industry, open discussion, and a panel of academic and industrial researchers/practitioners. We will invite papers on interacting with a machine with or without a human in the loop. Topics of interest include, but are not limited to, the following:

    Data, Competitions, Implementations, and Software
    Algorithms, Theory, Optimization Techniques
    Probabilistic Methods
    Deep Learning and Reinforcement Learning in CUI
    General purpose vs. domain specific conversation agents

Submissions should follow the KDD 2018 requirements and do not exceed 6 pages and will be evaluated using the KDD 2018 Research Track evaluation criteria. Preference will be given to papers that are reproducible, and authors are encouraged to share their data and code publicly whenever possible. In addition to research papers, we also welcome submissions of innovative applications or survey papers highlighting recent work, breakthroughs, and trends.

Travel grants of $2500 per submission are available to students whose papers we accept.

We’re issuing Student Travel Grant to both full-time students and recent graduates. As long as the first author of the paper is a full-time student or graduated after April 1st, 2017, the paper is eligible for the grant.

Submissions Here


    Paper Submission Deadline: May 08 May 15 May 22, 2018 11:59 PST
    Author Notification: June 08, 2018 11:59 PST
    Workshop Date: August 20,2018


Chucheng Hsieh

Dr. Chucheng Hsieh is a data science executive at Intuit, focusing on Artificial Intelligence and Machine Learning area.

Diane Chang

Dr. Diane Chang is a Distinguished Data Scientist at Intuit, currently focusing on using Artificial Intelligence and Machine Learning to improve Customer Care.

Bharath Kadaba

Dr. Bharath Kadaba is the Chief Innovation Officer at Intuit.

Ashok Srivastava

Dr. Ashok Srivastava is Chief Data Officer at Intuit.
Personal Website

Valentin Vrzheshch

Dr Valentin Vrzheshch is a data scientist at Intuit working on applying Artificial Intelligence and Machine Learning to Customer Care.

Divya Beeram

Divya Beeram is a Data Scientist at Intuit. Currently, she is focused on improving user experience in Customer Care.

Miguel Molina-Solana

Dr. Miguel Molina-Solana is a Marie Curie Research Fellow at the Data Science Institute (DSI) at Imperial College London.

Julio Amador

Julio holds a PhD in economics from the University of Essex. His area of expertise is applied machine learning (ML). Julio is now a research associate at Imperial Business Analytics. He is also CTO at

Contact Us