Linking named entities occurring in text to their corresponding entity in a Knowledge Base (KB) is challenging, especially when dealing with historical texts. In this work, we introduce Musical Heritage named Entities Recognition, Classification and Linking (MHERCL), a novel benchmark consisting of manually annotated sentences extrapolated from historical periodicals of the music domain. MHERCL contains named entities under-represented or absent in the most famous KBs. We experiment with several State-of-the-Art models on the Entity Linking (EL) task and show that MHERCL is a challenging dataset for all of them. We propose a novel unsupervised EL model and a method to extend supervised entity linkers by using Knowledge Graphs (KGs) to tackle the main difficulties posed by historical documents. Our experiments reveal that relying on unsupervised techniques and improving models with logical constraints based on KGs and heuristics to predict NIL entities (entities not represented in the KB of reference) results in better EL performance on historical documents.

The rapid evolution of large language models (LLMs) has transformed conversational agents, enabling complex human-machine interactions. However, evaluation frameworks often focus on single tasks, failing to capture the dynamic nature of multi-turn dialogues. This paper introduces a dynamic benchmarking framework to assess LLM-based conversational agents through interactions with synthetic users. The framework integrates generative agent simulation to evaluate performance on key dimensions: information extraction, context awareness, and adaptive engagement. By simulating various aspects of user behavior, our work provides a scalable, automated, and flexible benchmarking approach. Experimental evaluation - within a loan application use case - demonstrates the framework's effectiveness under one-shot and few-shot extraction conditions. Results show that adaptive strategies improve data extraction accuracy, especially when handling ambiguous responses. Future work will extend its applicability to broader domains and incorporate additional metrics (e.g., conversational coherence, user engagement). This study contributes a structured, scalable approach to evaluating LLM-based conversational agents, facilitating real-world deployment.

This paper proposes a neural network-based user simulator that can provide a multimodal interactive environment for training Reinforcement Learning (RL) agents in collaborative tasks involving multiple modes of communication. The simulator is trained on the existing ELDERLY-AT-HOME corpus and accommodates multiple modalities such as language, pointing gestures, and haptic-ostensive actions. The paper also presents a novel multimodal data augmentation approach, which addresses the challenge of using a limited dataset due to the expensive and time-consuming nature of collecting human demonstrations. Overall, the study highlights the potential for using RL and multimodal user simulators in developing and improving domestic assistive robots.

Robot assistants for older adults and people with disabilities need to interact with their users in collaborative tasks. The core component of these systems is an interaction manager whose job is to observe and assess the task, and infer the state of the human and their intent to choose the best course of action for the robot. Due to the sparseness of the data in this domain, the policy for such multi-modal systems is often crafted by hand; as the complexity of interactions grows this process is not scalable. In this paper, we propose a reinforcement learning (RL) approach to learn the robot policy. In contrast to the dialog systems, our agent is trained with a simulator developed by using human data and can deal with multiple modalities such as language and physical actions. We conducted a human study to evaluate the performance of the system in the interaction with a user. Our designed system shows promising preliminary results when it is used by a real user.

We introduce a simple and fast method for comparing graphs of different sizes. Existing approaches are often either limited to comparing graphs with the same number of vertices or are computationally unscalable. We propose the Embedded Laplacian Distance (ELD) for comparing graphs of potentially vastly different sizes. Our approach first projects the graphs onto a common, low-dimensional Laplacian embedding space that respects graphical structure. This reduces the problem to that of comparing point clouds in a Euclidean space. A distance can then be computed efficiently via a natural sliced Wasserstein approach. We show that the ELD is a pseudo-metric and is invariant under graph isomorphism. We provide intuitive interpretations of the ELD using tools from spectral graph theory. We test the efficacy of the ELD approach extensively on both simulated and real data. Results obtained are excellent.

"Examples of artificial intelligence (AI) can be found in various areas of the insurance industry today – for example in underwriting and claims", says Wolfgang Hauner, Chief Data Officer at Munich Re. "AI can support consultants in their work, helping with fact-checking and recommending courses of action, for instance." By contrast, processes in underwriting are becoming smarter: "All the available data and sources are called upon here, improving processes and the customer experience." According to Wolfgang Hauner, things are also getting smarter in claims. "Reaction times are getting shorter and insurers can more glean more information – which in turn leads to efficiency gains and better decisions." For example, big data and analytics allow the efficient processing of losses with low volumes and high demand rates.

A large volume of collated information alone does not guarantee deeper insights. To gain these and use raw data economically, complex analytical methods and intelligent processing are required. Munich Re employs data analytics in many areas and has developed applications from which insurers and insured persons benefit equally. "Examples of artificial intelligence (AI) can be found in various areas of the insurance industry today – for example in underwriting and claims", says Wolfgang Hauner, Chief Data Officer at Munich Re. "AI can support consultants in their work, helping with fact-checking and recommending courses of action, for instance." By contrast, processes in underwriting are becoming smarter: "All the available data and sources are called upon here, improving processes and the customer experience."

In this position paper, we describe the RoboHelper project, its findings and our vision for its future. The long-term goal of RoboHelper is to develop assistive robots for the elderly. The main thesis of our work is that such robots must crucially be able to participate in multimodal dialogues. Contributions of our work to date include the ELDERLY-AT-HOME corpus that we collected and annotated. It consists of 20 task-oriented human-human dialogues between a helper and an elderly person in a fully functional apartment. The unique feature of the corpus is that in addition to video and audio, it includes recordings of physical interaction. Based on this data, we have demonstrated the crucial role that Haptic-Ostensive (H-O) actions play in interpreting language and uncovering a person's intentions. H-O actions manipulate objects, but they also often perform a referring function. Our models were derived on the basis of manually annotated categories. Additional experiments show that we can identify H-O actions using the physical interaction data measured through an unobtrusive sensory glove developed as part of the project. In future work, we will derive models for the robot to decide what to do next (as opposed to interpreting what the interlocutor did); explore other types of physical interactions; and refine preliminary implementations of our models on the Nao robotic platform.

Our goal is to develop an interface for older people to effectively communicate with a robotic assistant so that they can safely remain living in their home. We are devising a multimodal interface since people communicate with one another using a variety of verbal and non-verbal signals, including haptics, i.e., physical interactions. We view haptics as an integral component of communication, which in some cases drives the interaction between the user and the robot, and we study its relation to speech and gestures. We illustrate features of interactions between an elderly person and an assistant via excerpts from our ongoing data collection. We also describe the architecture of our interface and ongoing research to bring this interface to fruition.

Selected quotes:"The Science Research Council has been receiving an increasing number of applications for research support in the rather broad field with mathematical engineering and biological aspects which often goes under the general description Articial Intelligence (Al). The research support applied for is sufficient in volume, and in variety of discipline involved, to demand that a general view of the field be taken by the Council itself.""To supplement the important mass of specialist and detailed information available to the Science Research Council its Chairman decided to commission an independent report by someone outside the Al field but with substantial general experience of research work in multidisciplinary fields including fields with mathematical, engineering and biological aspects."-----"Most workers in Al research and in related elds confess to a pro nounced feeling of disappointment in what has been achieved in the past twenty-five years. Workers entered the feld around 1950, and even around 1960, with high hopes that are very far from having been realised in 1972. In no part of the field have the discoveries made so far produced the major impact that was then promised.""In the meantime, claims and predictions regarding the potential results of Al research had been publicised which went even farther than the expectations of the majority of workers in the field whose embarrassments have been added to by the lamentable failure of such inflated predictions.""These general statements are expanded in a little more detail in the rest of section 3, which has been influenced by the views of large numbers of people listed in section 1 but which like the whole of this report represents in the last analysis only the personal view of the author. Before going into such detail he is inclined, as a mathematician, to single out one rather general cause for the disappointments that have been experienced: failure to recognise the implications of the 'combinatorial explosion'."See also: BBC TV - June 1973 - Lighthill Controversy Debate at the Royal Institution with Professor Sir James Lighthill, Professor Donald Michie, Professor Richard Gregory and Professor John McCarthy.Also in Lighthill, J., Sutherland, N. S., Needham, R. M., Longuet-Higgins, H. C., and Michie, D. (Eds.), Artificial Intelligence: A Paper Symposium. Science Research Council of Great Britain.