Named Entity Recognition (NER) is a machine learning task that traditionally relies on supervised learning and annotated data. Acquiring such data is often a challenge, particularly in specialized fields like medical, legal, and financial sectors. Those are commonly referred to as low-resource domains, which comprise long-tail entities, due to the scarcity of available data. To address this, data augmentation techniques are increasingly being employed to generate additional training instances from the original dataset. In this study, we evaluate the effectiveness of two prominent text augmentation techniques, Mention Replacement and Contextual Word Replacement, on two widely-used NER models, Bi-LSTM+CRF and BERT. We conduct experiments on four datasets from low-resource domains, and we explore the impact of various combinations of training subset sizes and number of augmented examples. We not only confirm that data augmentation is particularly beneficial for smaller datasets, but we also demonstrate that there is no universally optimal number of augmented examples, i.e., NER practitioners must experiment with different quantities in order to fine-tune their projects.

When human operators of cyber-physical systems encounter surprising behavior, they often consider multiple hypotheses that might explain it. In some cases, taking information-gathering actions such as additional measurements or control inputs given to the system can help resolve uncertainty and determine the most accurate hypothesis. The task of optimizing these actions can be formulated as a belief-space Markov decision process that we call a hypothesis-driven belief MDP. Unfortunately, this problem suffers from the curse of history similar to a partially observable Markov decision process (POMDP). To plan in continuous domains, an agent needs to reason over countlessly many possible action-observation histories, each resulting in a different belief over the unknown state. The problem is exacerbated in the hypothesis-driven context because each action-observation pair spawns a different belief for each hypothesis, leading to additional branching. This paper considers the case in which each hypothesis corresponds to a different dynamic model in an underlying POMDP. We present a new belief MDP formulation that: (i) enables reasoning over multiple hypotheses, (ii) balances the goals of determining the (most likely) correct hypothesis and performing well in the underlying POMDP, and (iii) can be solved with sparse tree search.

When designing correct-by-construction controllers for autonomous collectives, three key challenges are the task specification, the modelling, and its use at practical scale. In this paper, we focus on a simple yet useful abstraction for high-level controller synthesis for robot collectives with optimisation goals (e.g., maximum cleanliness, minimum energy consumption) and recurrence (e.g., re-establish contamination and charge thresholds) and safety (e.g., avoid full discharge, mutually exclusive room occupation) constraints. Due to technical limitations (related to scalability and using constraints in the synthesis), we simplify our graph-based setting from a stochastic two-player game into a single-player game on a partially observable Markov decision process (POMDP). Robustness against environmental uncertainty is encoded via partial observability. Linear-time correctness properties are verified separately after synthesising the POMDP strategy. We contribute at-scale guidance on POMDP modelling and controller synthesis for tasked robot collectives exemplified by the scenario of battery-driven robots responsible for cleaning public buildings with utilisation constraints.

Generating large-scale, domain-specific, multilingual multi-turn dialogue datasets remains a significant hurdle for training effective Multi-Turn Intent Classification models in chatbot systems. In this paper, we introduce Chain-of-Intent, a novel mechanism that combines Hidden Markov Models with Large Language Models (LLMs) to generate contextually aware, intent-driven conversations through self-play. By extracting domain-specific knowledge from e-commerce chat logs, we estimate conversation turns and intent transitions, which guide the generation of coherent dialogues. Leveraging LLMs to enhance emission probabilities, our approach produces natural and contextually consistent questions and answers. We also propose MINT-CL, a framework for multi-turn intent classification using multi-task contrastive learning, improving classification accuracy without the need for extensive annotated data. Evaluations show that our methods outperform baselines in dialogue quality and intent classification accuracy, especially in multilingual settings, while significantly reducing data generation efforts. Furthermore, we release MINT-E, a multilingual, intent-aware multi-turn e-commerce dialogue corpus to support future research in this area.

Recent advances in deep learning have brought attention to the possibility of creating advanced, general AI systems that outperform humans across many tasks. However, if these systems pursue unintended goals, there could be catastrophic consequences. A key prerequisite for AI systems pursuing unintended goals is whether they will behave in a coherent and goal-directed manner in the first place, optimizing for some unknown goal; there exists significant research trying to evaluate systems for said behaviors. However, the most rigorous definitions of goal-directedness we currently have are difficult to compute in real-world settings. Drawing upon this previous literature, we explore policy goal-directedness within reinforcement learning (RL) environments. In our findings, we propose a different family of definitions of the goal-directedness of a policy that analyze whether it is well-modeled as near-optimal for many (sparse) reward functions. We operationalize this preliminary definition of goal-directedness and test it in toy Markov decision process (MDP) environments. Furthermore, we explore how goal-directedness could be measured in frontier large-language models (LLMs). Our contribution is a definition of goal-directedness that is simpler and more easily computable in order to approach the question of whether AI systems could pursue dangerous goals. We recommend further exploration of measuring coherence and goal-directedness, based on our findings.

Partially Observable Markov Decision Processes (POMDPs) are a fundamental framework for decision-making under uncertainty and partial observability. Since in general optimal policies may require infinite memory, they are hard to implement and often render most problems undecidable. Consequently, finite-memory policies are mostly considered instead. However, the algorithms for computing them are typically very complex, and so are the resulting policies. Facing the need for their explainability, we provide a representation of such policies, both (i) in an interpretable formalism and (ii) typically of smaller size, together yielding higher explainability. To that end, we combine models of Mealy machines and decision trees; the latter describing simple, stationary parts of the policies and the former describing how to switch among them. We design a translation for policies of the finite-state-controller (FSC) form from standard literature and show how our method smoothly generalizes to other variants of finite-memory policies. Further, we identify specific properties of recently used "attractor-based" policies, which allow us to construct yet simpler and smaller representations. Finally, we illustrate the higher explainability in a few case studies.

The thesis proposes a generalized charging framework for multiple mobile chargers to maximize the network lifetime and ensure target coverage and connectivity in large scale WRSNs. Moreover, a multi-point charging model is leveraged to enhance charging efficiency, where the MC can charge multiple sensors simultaneously at each charging location. The thesis proposes an effective Decentralized Partially Observable Semi-Markov Decision Process (Dec POSMDP) model that promotes Mobile Chargers (MCs) cooperation and detects optimal charging locations based on realtime network information. Furthermore, the proposal allows reinforcement algorithms to be applied to different networks without requiring extensive retraining. To solve the Dec POSMDP model, the thesis proposes an Asynchronous Multi Agent Reinforcement Learning algorithm (AMAPPO) based on the Proximal Policy Optimization algorithm (PPO).

The proportion of elderly people is increasing worldwide, particularly those living alone in Japan. As elderly people get older, their risks of physical disabilities and health issues increase. To automatically discover these issues at a low cost in daily life, sensor-based detection in a smart home is promising. As part of the effort towards early detection of abnormal behaviors, we propose a simulator-based detection systems for six typical anomalies: being semi-bedridden, being housebound, forgetting, wandering, fall while walking and fall while standing. Our detection system can be customized for various room layout, sensor arrangement and resident's characteristics by training detection classifiers using the simulator with the parameters fitted to individual cases. Considering that the six anomalies that our system detects have various occurrence durations, such as being housebound for weeks or lying still for seconds after a fall, the detection classifiers of our system produce anomaly labels depending on each anomaly's occurrence duration, e.g., housebound per day and falls per second. We propose a method that standardizes the processing of sensor data, and uses a simple detection approach. Although the validity depends on the realism of the simulation, numerical evaluations using sensor data that includes a variety of resident behavior patterns over nine years as test data show that (1) the methods for detecting wandering and falls are comparable to previous methods, and (2) the methods for detecting being semi-bedridden, being housebound, and forgetting achieve a sensitivity of over 0.9 with fewer than one false alarm every 50 days.

Manipulating the interaction trajectories between the intelligent agent and the environment can control the agent's training and behavior, exposing the potential vulnerabilities of reinforcement learning (RL). For example, in Cyber-Physical Systems (CPS) controlled by RL, the attacker can manipulate the actions of the adopted RL to other actions during the training phase, which will lead to bad consequences. Existing work has studied action-manipulation attacks in tabular settings, where the states and actions are discrete. As seen in many up-and-coming RL applications, such as autonomous driving, continuous action space is widely accepted, however, its action-manipulation attacks have not been thoroughly investigated yet. In this paper, we consider this crucial problem in both white-box and black-box scenarios. Specifically, utilizing the knowledge derived exclusively from trajectories, we propose a black-box attack algorithm named LCBT, which uses the Monte Carlo tree search method for efficient action searching and manipulation. Additionally, we demonstrate that for an agent whose dynamic regret is sub-linearly related to the total number of steps, LCBT can teach the agent to converge to target policies with only sublinear attack cost, i.e., $O\left(\mathcal{R}(T) + MH^3K^E\log (MT)\right)(0

We present Asymmetric Dexterity (AsymDex), a novel reinforcement learning (RL) framework that can efficiently learn asymmetric bimanual skills for multi-fingered hands without relying on demonstrations, which can be cumbersome to collect. Two crucial ingredients enable AsymDex to reduce the observation and action space dimensions and improve sample efficiency. First, AsymDex leverages the natural asymmetry found in human bimanual manipulation and assigns specific and interdependent roles to each hand: a facilitating hand that moves and reorients the object, and a dominant hand that performs complex manipulations on said object. Second, AsymDex defines and operates over relative observation and action spaces, facilitating responsive coordination between the two hands. Further, AsymDex can be easily integrated with recent advances in grasp learning to handle both the object acquisition phase and the interaction phase of bimanual dexterity. Unlike existing RL-based methods for bimanual dexterity, which are tailored to a specific task, AsymDex can be used to learn a wide variety of bimanual tasks that exhibit asymmetry. Detailed experiments on four simulated asymmetric bimanual dexterous manipulation tasks reveal that AsymDex consistently outperforms strong baselines that challenge its design choices, in terms of success rate and sample efficiency. The project website is at https://sites.google.com/view/asymdex-2024/.