1 - 10 of 1398
-
PublicationIncorporating Query Recommendation for Improving In-Car Conversational Search( 2024-03-23)Retrieval-augmented generation has become an effective mechanism for conversational systems in domain-specific settings. Retrieval of a wrong document due to the lack of context from the user utterance may lead to wrong answer generation. Such an issue may reduce the user engagement and thereby the system reliability. In this paper, we propose a context-guided follow-up question recommendation to internally improve the document retrieval in an iterative approach for developing an in-car conversational system. Specifically, a user utterance is first reformulated, given the context of the conversation to facilitate improved understanding to the retriever. In the cases, where the documents retrieved by the retriever are not relevant enough for answering the user utterance, we employ a large language model (LLM) to generate question recommendation which is then utilized to perform a refined retrieval. An empirical evaluation confirms the effectiveness of our proposed approaches in in-car conversations, achieving 48% and 22% improvement in the retrieval and system generated responses, respectively, against baseline approaches.
-
PublicationControlled Randomness Improves the Performance of Transformer Models( 2024-03-19)
-
PublicationExtending the Visual Data Exploration Loop towards Trustworthy Machine Learning in the Healthcare Domain( 2024)
-
PublicationUncovering Inconsistencies and Contradictions in Financial Reports using Large Language Models( 2023-12)
-
PublicationStudy-Buddy: A Knowledge Graph-Powered Learning Companion for School Students( 2023-10-21)Large Language Models (LLMs) have the potential to substantially improve educational tools for students. However, they face limitations, including factual accuracy, personalization, and the lack of control over the sources of information. This paper presents Study-Buddy, a prototype of a conversational AI assistant for school students to address the above-mentioned limitations. Study-Buddy embodies an AI assistant based on a knowledge graph, LLMs models, and computational persuasion. It is designed to support educational campaigns as a hybrid AI solution. The demonstrator showcases interactions with Study-Buddy and the crucial role of the Knowledge Graph for the bot to present the appropriate activities to the students. A video demonstrating the main features of Study-Buddy is available at: https://youtu.be/DHPTsN1RI9o.
-
PublicationMulti-Dimensional Data Farming: Extending Data Farming for Multi-Scale Decision Support by Integrating Novel AI Techniques( 2023-10-01)Traditional Data Farming (DF) consists of a toolbox of established analysis techniques that are available for an analyst-led study of a particular military operation in support of a single decision-maker. Multi-Dimensional Data Farming (MDDF) is a new and automated analytical process that provides accelerated support to military decision-making at multiple scales. At the strategic level, MDDF can inform decision-makers in planning long timescale campaigns, while at the tactical level, MDDF allows investigation of emerging technologies in shorter timescale operations. More importantly, MDDF explicitly addresses the interplay between a long timescale campaign and embedded short timescale operations, which is rarely tackled in the literature. MDDF extends DF by integrating novel AI techniques (Automated Machine Learning, eXplainable AI) and eXtended Reality visualization in an AI agent which automatically investigates the multi-dimensional parameter landscape and efficiently provides decision-makers with insight into the best, worst and most promising Courses of Action. We illustrate our new MDDF approach through a hybrid warfare scenario consisting of a Border Operation (interdiction of illegal migrants) embedded within a multi-faction (Blue, Red and Green forces) hybrid war campaign. Combining AI techniques exploring operations at multiple scales (domain, level, time) and boosting strategic and tactical understanding, MDDF innovates multi-scale decision-making.
-
PublicationSymmetry-Aware Siamese Network: Exploiting Pathological Asymmetry for Chest X-Ray Analysis( 2023-09-22)The human body shows elements of bilateral symmetry for various body parts, including the lung. This symmetry can be disturbed by a variety of diseases or abnormalities, e.g. by lung diseases such as pneumonia. While radiologists use lung field symmetry information in their radiological examinations to analyze chest X-rays, it is still underutilized in the field of computer vision. To investigate the potential of pathologically induced asymmetry of the lung field for the automatic detection of healthy and diseased patients, we implement a symmetry-aware architecture. The model is based on a Siamese network with a DenseNet backbone and a symmetry-aware contrastive loss function. Two different processing pipelines are investigated: first, the scan is processed as a whole image, and second, the left and right lung fields are separated. This enables an independent determination of the most important features of each lung field. Compared to state-of-the-art baseline models (DenseNet, Mask R-CNN), symmetry-aware training can improve the AUROC score by up to 10%. Furthermore, the findings indicate that, by integrating the bilateral symmetry of the lung field, the interpretability of the models increases. The generated probability maps show a stronger focus on lung field and disease features compared to state-of-the-art algorithms like Grad-Cam++ for heat map generation or Mask R-CNN for object detection.
-
Publicationsustain.AI: a Recommender System to analyze Sustainability Reports( 2023-09-07)
-
PublicationInvestigation of Drift Detection for Clinical Text Classification( 2023-09-02)
-
