In the field of Human-Robot Interaction (HRI), a fundamental challenge is to facilitate human understanding of robots. The emerging domain of eXplainable HRI (XHRI) investigates methods to generate explanations and evaluate their impact on human-robot interactions. Previous works have highlighted the need to personalise the level of detail of these explanations to enhance usability and comprehension. Our paper presents a framework designed to update and retrieve user knowledge-memory models, allowing for adapting the explanations' level of detail while referencing previously acquired concepts. Three architectures based on our proposed framework that use Large Language Models (LLMs) are evaluated in two distinct scenarios: a hospital patrolling robot and a kitchen assistant robot. Experimental results demonstrate that a two-stage architecture, which first generates an explanation and then personalises it, is the framework architecture that effectively reduces the level of detail only when there is related user knowledge.

Spoken language understanding (SLU) systems in conversational AI agents often experience errors in the form of misrecognitions by automatic speech recognition (ASR) or semantic gaps in natural language understanding (NLU). These errors easily translate to user frustrations, particularly so in recurrent events e.g. regularly toggling an appliance, calling a frequent contact, etc. In this work, we propose a query rewriting approach by leveraging users' historically successful interactions as a form of memory. We present a neural retrieval model and a pointer-generator network with hierarchical attention and show that they perform significantly better at the query rewriting task with the aforementioned user memories than without. We also highlight how our approach with the proposed models leverages the structural and semantic diversity in ASR's output towards recovering users' intents.

For the past year or so I've been trying to learn German, and the most difficult part in language learning is certainly vocabulary learning. The existing apps do a pretty good job at helping with vocabulary learning, with the only issue that creating the flashcards is a big time sink. Initially the idea was to have a pool of words one wants to learn, and then the app would just quiz the user and try to maximize the learning of the user. Context: When learning new vocabulary, it is very useful to learn words in context, for example pictures and related words. If we could group related words and pictures together, the learning would (ideally) be more efficient.

The Scoring Engine does a weighted learning from all different events giving higher scores to deeper interactions. In order to score the event property inside user memory, we either increase or decrease the magnitude of features variable of brand, category, collection, price-ranges with certain criteria. To score these property attributes, we have used FyndRank algorithm created by #Reco-team (inspired from EdgeRank of Facebook). Scoring ensures the features value stays within predefined ranges otherwise we normalize the score with the min-max method. Along with generating user memory, Stream Mapper also computes the similarity between brands and collections that can also recommended to users.