- Paper Submission Deadline: May 22, 2023
- Paper Notification: July 17, 2023
- Paper Camera-ready: August 7, 2023
Chatbots and Conversation Agents are software applications that mimic human-like discussions with humans by using AI and Natural Language Processing. Several businesses, including e-commerce, healthcare, finance, and education, use Conversation Agents. Websites, chat services, smartphone applications, and even actual physical devices like smart speakers might incorporate them. The importance of Conversation Agents has grown significantly in recent years due to the increasing demand for personalised, efficient, and convenient communication channels with the users. At the same time, Knowledge Graphs are becoming increasingly important in the development of Conversational Agents and Chatbots. A Knowledge Graph is a type of database that represents knowledge as a network of interconnected nodes and edges. In the context of conversational systems, Knowledge Graphs can be used to represent the entities, relationships, and concepts that are relevant to a particular domain. One of the key benefits of using Knowledge Graphs in conversational systems is that they enable more natural and intuitive interactions between users and machines. By modelling the relationships between different pieces of information, Knowledge Graphs can help Conversational Agents better understand the context and intent of a user's input, and provide more relevant and accurate responses. In addition to improving the accuracy and relevance of conversational systems, Knowledge Graphs also facilitate more efficient and effective dialogue management. Because Knowledge Graphs can represent complex relationships and dependencies between different pieces of information, Conversational Agents can use them to dynamically generate and modify dialogue based on user input, context, and other factors. This can help conversational systems adapt to changing user needs and preferences, and provide a more seamless and personalised experience.
This special session focuses on the role of Knowledge Graphs in addressing key challenges in the development of Chatbots and Conversational Agents, including Natural Language Processing (NLP)/Natural Language Understanding (NLU), Dialogue Management, and Language Generation. Knowledge graphs offer a powerful way to represent and reason about the world, enabling conversational agents to provide intelligent responses to user queries. However, a number of challenges must be addressed in order to achieve truly effective conversational agents, such as Context Understanding (clarifications, temporal aspects, topic switch), Data and Training (open/closed domain, handle questions/requests, argumentation), User Experience (non-active/non-native speaker), Maintenance and Updates (incremental knowledge updates, dynamic ontology extension). This special session brings together researchers and practitioners to share their insights and experiences in addressing these challenges through the use of knowledge graphs, and to discuss future directions for research and development in this area.
This workshop provides the opportunity to discuss specific research and technical topics in utilising Knowledge Graphs for Conversational Agents, with a special emphasis on the key tasks of Natural Language Processing (NLP)/Natural Language Understanding (NLU), Dialogue Management, and Language Generation. Conversational Agents are becoming more advanced and sophisticated, with the integration of Knowledge Graphs, Machine Learning, and other AI technologies. As a result, they are able to provide more accurate and personalised responses, and handle complex tasks with greater efficiency. The main objective is to stimulate original, unpublished research that proposes techniques for the integration of Knowledge Graphs in Conversational Agents and/or in all tasks or challenges related to the Conversational Agents. Surveys are very welcome too. The special session concept could include ideas in every field/task related to Conversational Agents, such as:
- NLP/NLU and other related tasks, such as Topic Understanding
- Dialogue management
- Language generation, etc.
The research topics of interest for this special session include, but are not limited to:
- Knowledge-driven natural language understanding and dialogues
- Pattern-based query interpretation and feedback
- Neuro-symbolic Conversational Agents
- Knowledge patterns in natural language analysis and generation
- Query answering empowered by ontologies and Knowledge Graphs
- Knowledge-based representation of conversational context
- Knowledge-based representation of dialogue management policies
- Intelligent multimodal dialogues and knowledge fusion
- Knowledge Graph presentation in conversational search
- Fairness and explainability of dialogues
- Knowledge updates for the efficient representation of unseen relations and entities
- Argumentation-based explanations and Knowledge Graphs
- Hybrid question answering (OWL, rules, graphs, ML)
- Logic-based methods for addressing dialogue phenomena in conversational context, e.g. ambiguities, repairs, restarts, discourse relations, etc.
- Graph-based multilingual question answering
- Evaluation metrics for effectiveness, engagement, user satisfaction of conversational systems
- Applications in healthcare, education, government, creative industries, workplaces, migration, and others.
- The length of each paper submitted should be no more than 10 pages, and formatted following the standard 2-column U.S. letter style of IEEE Conference template. See the IEEE Proceedings Author Guidelines for further information and instructions.
- All submissions will be double-blind reviewed by the Program Committee on the basis of technical quality, relevance to the scope of the special session, originality, significance, and clarity. The names and affiliations of authors must not appear in the submissions, and bibliographic references must be adjusted to preserve author anonymity. Submissions failing to comply with paper formatting and authors anonymity will be rejected without reviews.
- Authors are also encouraged to submit supplementary materials, i.e., providing the source code and data through a GitHub-like public repository to support the reproducibility of their research results.
All accepted full-length special session papers will be published by IEEE in the DSAA main conference proceedings under its Special Session scheme. All papers will be submitted for inclusion in the IEEEXplore Digital Library. The conference proceedings will be submitted for EI indexing through INSPEC by IEEE.
- (i) information necessary for reproducing the experimental results reported in the paper (e.g., various algorithmic and model parameters and configurations, hyper parameter search spaces, details related to data set filtering and train/test splits, software versions, detailed hardware configuration, etc.).
- (ii) any data, pseudo-code and proofs that could not be included in the main page of the manuscript due to space limitations.
The list of authors at the time of submission is considered final and any further changes of the authorship are not allowed.
DSAA is an archival publication venue as such submissions that have been previously published, accepted, or are currently under consideration at other peer-review publication venues (i.e., journals, conferences, workshops with published proceedings, etc) are not permitted.
COIs must be declared at the time of submission. COIs include employment at the same institution within the past three years, collaborations during the past three years, advisor/advisee relationships, plus family and close friends.
At least one of the authors of each accepted paper must register in full and attend the conference to present the paper. No-show papers will be removed from the IEEE Xplore proceedings.
- Thanassis Mavropoulos, Centre for Research and Technology Hellas, Information Technologies Institute
- Georgios Meditskos, School of Informatics, Aristotle University of Thessaloniki
- Stefanos Vrochidis, Centre for Research and Technology Hellas, Information Technologies Institute Inquiries about this special session should be sent to: firstname.lastname@example.org