Timo Hartmann

Eyob Mengiste, Borja Garcia de Soto, Timo Hartmann

This study proposes a method to automate the development of lookahead planning. The proposed method uses construction material conditions (i.e., appearances) and site space utilization to predict task completion rates. A Gated Recurrent Unit (GRU) based Recurrent Neural Network (RNN) model was trained using a segment of a construction project timeline to estimate completion rates of tasks and propose data-aware lookahead plans. The proposed method was evaluated in a sample construction project involving finishing works such as plastering, painting, and installing electrical fixtures. The results show that the proposed method can assist with developing automated lookahead plans. In doing so, this study links construction planning with actual events at the construction site. It extends the traditional scheduling techniques and integrates a broader spectrum of site spatial constraints into lookahead planning.

Han Gao, Timo Hartmann, Botao Zhong et al.

Building Information Modeling (BIM) is essential for managing building data across the entire lifecycle, supporting tasks from design to maintenance. Natural Language Interface (NLI) systems are increasingly explored as user-friendly tools for information retrieval in Building Information Modeling (BIM) environments. Despite their potential, accurately extracting BIM-related data through natural language queries remains a persistent challenge due to the complexity use queries and specificity of domain knowledge. This study presents a comparative analysis of two prominent approaches for developing NLI-based BIM information retrieval systems: domain-specific fine-tuning and prompt-based learning using large language models (LLMs). A two-stage framework consisting of intent recognition and table-based question answering is implemented to evaluate the effectiveness of both approaches. To support this evaluation, a BIM-specific dataset of 1,740 annotated queries of varying types across 69 models is constructed. Experimental results show that domain-specific fine-tuning delivers superior performance in intent recognition tasks, while prompt-based learning, particularly with GPT-4o, shows strength in table-based question answering. Based on these findings, this study identify a hybrid configuration that combines fine-tuning for intent recognition with prompt-based learning for question answering, achieving more balanced and robust performance across tasks. This integrated approach is further tested through case studies involving BIM models of varying complexity. This study provides a systematic analysis of the strengths and limitations of each approach and discusses the applicability of the NLI to real-world BIM scenarios. The findings offer insights for researchers and practitioners in designing intelligent, language-driven BIM systems.

Zeyd Boukhers, Timo Hartmann, Jan Jürjens

Due to the significant advancement of Natural Language Processing and Computer Vision-based models, Visual Question Answering (VQA) systems are becoming more intelligent and advanced. However, they are still error-prone when dealing with relatively complex questions. Therefore, it is important to understand the behaviour of the VQA models before adopting their results. In this paper, we introduce an interpretability approach for VQA models by generating counterfactual images. Specifically, the generated image is supposed to have the minimal possible change to the original image and leads the VQA model to give a different answer. In addition, our approach ensures that the generated image is realistic. Since quantitative metrics cannot be employed to evaluate the interpretability of the model, we carried out a user study to assess different aspects of our approach. In addition to interpreting the result of VQA models on single images, the obtained results and the discussion provides an extensive explanation of VQA models' behaviour.

Zeyd Boukhers, Nada Beili, Timo Hartmann et al.

Extracting metadata from scientific papers can be considered a solved problem in NLP due to the high accuracy of state-of-the-art methods. However, this does not apply to German scientific publications, which have a variety of styles and layouts. In contrast to most of the English scientific publications that follow standard and simple layouts, the order, content, position and size of metadata in German publications vary greatly among publications. This variety makes traditional NLP methods fail to accurately extract metadata from these publications. In this paper, we present a method that extracts metadata from PDF documents with different layouts and styles by viewing the document as an image. We used Mask R-CNN that is trained on COCO dataset and finetuned with PubLayNet dataset that consists of ~200K PDF snapshots with five basic classes (e.g. text, figure, etc). We refine-tuned the model on our proposed synthetic dataset consisting of ~30K article snapshots to extract nine patterns (i.e. author, title, etc). Our synthetic dataset is generated using contents in both languages German and English and a finite set of challenging templates obtained from German publications. Our method achieved an average accuracy of around $90\%$ which validates its capability to accurately extract metadata from a variety of PDF documents with challenging templates.

Zijian Wang, Scott A. Hale, David Adelani et al.

Social media provide access to behavioural data at an unprecedented scale and granularity. However, using these data to understand phenomena in a broader population is difficult due to their non-representativeness and the bias of statistical inference tools towards dominant languages and groups. While demographic attribute inference could be used to mitigate such bias, current techniques are almost entirely monolingual and fail to work in a global environment. We address these challenges by combining multilingual demographic inference with post-stratification to create a more representative population sample. To learn demographic attributes, we create a new multimodal deep neural architecture for joint classification of age, gender, and organization-status of social media users that operates in 32 languages. This method substantially outperforms current state of the art while also reducing algorithmic bias. To correct for sampling biases, we propose fully interpretable multilevel regression methods that estimate inclusion probabilities from inferred joint population counts and ground-truth population counts. In a large experiment over multilingual heterogeneous European regions, we show that our demographic inference and bias correction together allow for more accurate estimates of populations and make a significant step towards representative social sensing in downstream applications with multilingual social media.