Papers by Dirk Väth
ADVISER: A Dialog System Framework for Education & Research (P19-3)
Copied to clipboard
Daniel Ortega, Dirk Väth, Gianna Weber, Lindsey Vanderlyn, Maximilian Schmidt, Moritz Völkel, Zorica Karacevic, Ngoc Thang Vu
| Challenge: | In this paper, we focus on task-oriented dialog systems, although our framework allows easy integration of non-task dialog systems and their combination. |
| Approach: | They propose an open source dialog system framework for education and research that supports multi-domain task-oriented conversations in two languages. |
| Outcome: | The proposed framework supports multi-domain task-oriented conversations in two languages and is open source for education and research. |
Beyond Accuracy: A Consolidated Tool for Visual Question Answering Benchmarking (2021.emnlp-demo)
Copied to clipboard
| Challenge: | Existing evaluation tools for general Visual Question Answering (VQA) systems are limited to answering accuracy, but they can be used to evaluate performance in real-world scenarios. |
| Approach: | They propose a browser-based benchmarking tool with an API for easy integration of new models and datasets to keep up with the fast-changing landscape of VQA. |
| Outcome: | The proposed tool tests generalization capabilities of models across multiple datasets and includes metrics that measure biases and uncertainty to further explain model behavior. |
Understanding the Role of Mental Models in User Interaction with an Adaptive Dialog Agent (2025.findings-naacl)
Copied to clipboard
| Challenge: | Adaptive dialog systems can help users align their behavior with user expectations, but there is little research into what mental models users form when interacting with a task-oriented dialog system. |
| Approach: | They propose to use a publicly available dataset to explore user mental models of dialog systems to better align with users' mental models. |
| Outcome: | The proposed model can improve dialog efficiency, success, and user perception of the interaction, even when done implicitly. |
ADVISER: A Toolkit for Developing Multi-modal, Multi-domain and Socially-engaged Conversational Agents (2020.acl-demos)
Copied to clipboard
Chia-Yu Li, Daniel Ortega, Dirk Väth, Florian Lux, Lindsey Vanderlyn, Maximilian Schmidt, Michael Neumann, Moritz Völkel, Pavel Denisov, Sabrina Jenne, Zorica Kacarevic, Ngoc Thang Vu
| Challenge: | Existing toolkits for developing dialog systems are limited to core components and do not support multi-modal processing and social signals. |
| Approach: | They propose to use ADVISER to develop multi-modal dialog agents using multi-text and social signals. |
| Outcome: | The proposed toolkit is flexible, easy to use, and easy to extend for linguists and cognitive scientists, thereby providing a flexible platform for collaborative research. |
Conversational Tree Search: A New Hybrid Dialog Task (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing conversational interfaces are limited to FAQs and dialogs, allowing users to search for specific questions. |
| Approach: | They propose a task that bridges the gap between FAQ-style information retrieval and task-oriented dialog. |
| Outcome: | The proposed task bridges the gap between FAQ-style information retrieval and task-oriented dialog. |
DIAGRAPH: An Open-Source Graphic Interface for Dialog Flow Design (2023.acl-demo)
Copied to clipboard
| Challenge: | Dialog systems have gained attention as a convenient way for users to access information in a more personalized manner. |
| Approach: | They present a graphical dialog flow editor built on ADVISER toolkit . it provides a clean and intuitive graphical interface for creating dialog systems . |
| Outcome: | The tool is based on the ADVISER toolkit and is evaluated with subject-experts . it is able to quickly prototype dialog systems and provide a test bed for students learning about dialog systems. |
Towards a Zero-Data, Controllable, Adaptive Dialog System (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent approaches to controllable dialog systems require additional training data to be deployed in new domains. |
| Approach: | They propose to generate dialog tree data directly from dialog trees by using a commercial Large Language Model or a single GPU. |
| Outcome: | The proposed approach can achieve comparable dialog success to models trained on human data. |