LectureChat extends the WikiChat conversational AI system by integrating multilingual university lecture transcripts alongside

Wikipedia content. The demo showcases a dual retrieval architecture that combines structured encyclopedic knowledge with academic lecture

material, leveraging multiple segmentation strategies and cross index reconciliation to improve retrieval quality. The system maintains separate

citation spaces for Wikipedia (numeric) and lectures (alphabetic) and preserves temporal provenance for direct video navigation. We present

the overall architecture, interaction flow, implementation details, and a reproducibility plan.

Learning is at the heart of every progress the human species makes. It is most effective when it considers who we are as individuals, what learning approach we prefer and what we already know to begin with. In the digital age, we strive to capture such information in the form of a digital representation -- the so-called learner model --, to tailor learning-related systems to this information and build upon it to create more personalised learning experiences. Over recent years, the proliferation of diverse models across various educational applications and disciplines has made it challenging to access targeted research.

In this survey, we aim to address this gap, reviewing the latest advances in learner modelling and conducting a comprehensive analysis of the existing approaches, focusing on developments from 2014 to 2023. With the help of a systematic literature review, we want to provide designers and developers of learner models with a structured overview and simplified entrance into the topic and the field of learner models. We investigate the question: What do learner models look like and how are they filled, kept up-to-date, and used?

To this end, we analyse and classify existing approaches. Our findings provide a comprehensive and structured overview of the field of learner modelling, allowing researchers to navigate and understand the diverse approaches more easily and providing developers of learner models or adaptive systems with a practical tool to access relevant information according to their needs.

The textual realm and the geographic/spatial realm intersect when we use human language to talk about geographic space. Various terms have been used to talk about this intersection (“geoparsing”, “georeferencing”, “toponym resolution”, “spatial grounding” etc.) and related applications such as geographic information retrieval. In this keynote, I will review some things that the community has accomplished since 2003, what occupies people’s minds at the moment, and I will raise a few research questions that would be interesting to answer, or that would unlock the potential for new kinds of applications. I conclude with some personal conjectures about how one version of the future might look like.

A number of machine learning process models (SEMMA, KDD, CRISP-DM, CRISP-ML, Data-to-Value1 etc.) have been recently proposed to facilitate the development of machine learning models in their organizational context. While the existing proposals vary with respect to complexity and suitability for particular tasks, it would be desirable to have software tools that embody or support these process models, and make it easier for project teams to capture, share among team members and stakeholders and preserve the relevant project information pertaining to the various process stages. In particular, recorded past statistics may be applied to predict the duration of stages or the overall project effort.

Presently, to the best of our knowledge, no requirement analysis exists that stipulates the detailed needs. To this end, we present a first collection and analysis of a requirements document for the software tooling for machine learning process models. We describe the functional and non-functional requirements of a Computer-Aided Machine Learning Modeling (CAMLM) tool, the soft-computing world’s counter-part to a CASE (Computer Aided Software Engineering) tool.

Various software cover sub-areas such as team management and communication management (Confluence, Jira, Slack, Zoom...) or project management (CRISP-DM, Scrum, Kanban-Board...) or data and information management (model management [Weber, Christian; Hirmer, Pascal; Reimann, Peter; Schwarz, Holger (2019): A New Process Model for the Comprehensive Management of Machine Learning Models. In: Proceedings of the 21st International Conference on Enterprise Information Systems: SCITEPRESS - Science and Technology Publications.] ). What is not available to our knowledge, however, is software that covers the entire sub-areas and the entire life cycle of machine learning projects in detail.

To date, automatic summarization methods have been mostly developed for (and applied to) general news articles, whereas other document types have been neglected. In this paper, we introduce the task of summarizing financial earnings call transcripts, and we present a method for summarizing this text type essential for the financial industry. Earnings calls are briefing events common for public companies in many countries, typically in the form of conference calls held between company executives and analysts that consist of a spoken monologue part followed by moderated questions and answers.

We show that traditional methods work less well in this domain, we present a method suitable for summarizing earnings calls. Our large-scale evaluation on a new human-annotated corpus of summary-worthy sentences shows that this method outperforms a set of strong baselines, including a new one that we propose specifically for earnings calls. To the best of our knowledge, this is the first application of summarization to financial earnings calls transcripts, a primary source of information for financial professionals.

In this demonstration, we present Country Guesser, a live system that guesses the country that a photo is taken in. In particular, given a Google Street View image, our federated ranking model uses a combination of computer vision, machine learning and text retrieval methods to compute a ranking of likely countries of the location shown in a given image from Street View. Interestingly, using text-based features to probe large pre-trained language models can assist to provide cross-modal supervision. We are not aware of previous country guessing systems informed by visual and textual features.

Financial prediction is complex due to the stochastic nature of the stock market. Semi-structured financial documents present comprehensive financial data in tabular formats, such as earnings, profit-loss statements, and balance sheets, and can often contain rich technical analysis along with a textual discussion of corporate history, and management analysis, compliance, and risks. Existing research focuses on the textual and audio modalities of financial disclosures from company conference calls to forecast stock volatility and price movement, but ignores the rich tabular data available in financial reports. Moreover, the economic realm is still plagued with a severe under-representation of various communities spanning diverse demographics, gender, and native speakers. In this work, we show that combining tabular data from financial semi-structured documents with text transcripts and audio recordings not only improves stock volatility and price movement prediction by 5-12% but also reduces gender bias caused due to audio-based neural networks by over 30%.

While for data mining projects (for example in the context of e-commerce) some methodologies have already been developed (e.g. CRISP-DM, SEMMA, KDD), these do not account for (1) early evaluation in order to de-risk a project (2) dealing with text corpora (“unstructured” data) and associated natural language processing processes, and (3) non-technical considerations (e.g. legal, ethical, project management aspects). To address these three shortcomings, a new methodology, called “Data to Value”, is introduced, which is guided by a detailed catalog of questions in order to avoid a disconnect of large-scale NLP project teams with the topic when facing rather abstract box-and-arrow diagrams commonly associated with methodologies.

Despite recent advances in deep learning-based language modelling, many natural language processing (NLP) tasks in the financial domain remain challenging due to the paucity of appropriately labelled data. Other issues that can limit task performance are differences in word distribution between the general corpora – typically used to pre-train language models – and financial corpora, which often exhibit specialized language and symbology. Here, we investigate two approaches that can help to mitigate these issues. Firstly, we experiment with further language model pre-training using large amounts of in-domain data from business and financial news. We then apply augmentation approaches to increase the size of our data-set for model fine-tuning. We report our findings on an Environmental, Social and Governance (ESG) controversies data-set and demonstrate that both approaches are beneficial to accuracy in classification tasks.

In this half-day tutorial, we will review the basic concepts of, methods for, and applications of geographic information retrieval, also showing some possible applications in fields such as the digital humanities. The tutorial is organized in four parts. First we introduce some basic ideas about geography, and demonstrate why text is a powerful way of exploring relevant questions. We then introduce a basic end-to-end pipeline discussing geographic information in documents, spatial and multi-dimensional indexing [19], and spatial retrieval and spatial filtering. After showing a range of possible applications, we conclude with suggestions for future work in the area.