Search

In this paper we implement and compare 7 different data augmentation strategies for the task of automatic scoring of children's ability to understand others' thoughts, feelings, and desires (or "mindreading"). We recruit in-domain experts to re-annotate augmented samples and determine to what extent each strategy preserves the original rating. We also carry out multiple experiments to measure how much each augmentation strategy improves the performance of automatic scoring systems. To determine the capabilities of automatic systems to generalize to unseen data, we create UK-MIND-20 - a new corpus of children's performance on tests of mindreading, consisting of 10,320 question-answer pairs. We obtain a new state-of-the-art performance on the MIND-CA corpus, improving macro-F1-score by 6 points. Results indicate that both the number of training examples and the quality of the augmentation strategies affect the performance of the systems. The task-specific augmentations generally outperform task-agnostic augmentations. Automatic augmentations based on vectors (GloVe, FastText) perform the worst. We find that systems trained on MIND-CA generalize well to UK-MIND-20. We demonstrate that data augmentation strategies also improve the performance on unseen data., Comment: The paper will be presented at ACL-IJCNLP 2021

In this paper we present the first work on the automated scoring of mindreading ability in middle childhood and early adolescence. We create MIND-CA, a new corpus of 11,311 question-answer pairs in English from 1,066 children aged 7 to 14. We perform machine learning experiments and carry out extensive quantitative and qualitative evaluation. We obtain promising results, demonstrating the applicability of state-of-the-art NLP solutions to a new domain and task., Comment: Accepted in COLING 2020

We present in this paper an exertion of our previous work by increasing the robustness and coverage of the evolution search via hybridisation with a state-of-the-art novelty search and accelerate the individual agent behaviour searches via a novel behaviour-component sharing technique. Via these improvements, we present Swarm Learning Classifier System 2.0 (SLCS2), a behaviour evolving algorithm which is robust to complex environments, and seen to out-perform a human behaviour designer in challenging cases of the data-transfer task in a range of environmental conditions. Additionally, we examine the impact of tailoring the SLCS2 rule generator for specific environmental conditions. We find this leads to over-fitting, as might be expected, and thus conclude that for greatest environment flexibility a general rule generator should be utilised.

This paper explores the use of a novel form of Hierarchical Graph Neurons (HGN) for in-operation behaviour selection in a swarm of robotic agents. This new HGN is called Robotic-HGN (R-HGN), as it matches robot environment observations to environment labels via fusion of match probabilities from both temporal and intra-swarm collections. This approach is novel for HGN as it addresses robotic observations being pseudo-continuous numbers, rather than categorical values. Additionally, the proposed approach is memory and computation-power conservative and thus is acceptable for use in mobile devices such as single-board computers, which are often used in mobile robotic agents. This R-HGN approach is validated against individual behaviour implementation and random behaviour selection. This contrast is made in two sets of simulated environments: environments designed to challenge the held behaviours of the R-HGN, and randomly generated environments which are more challenging for the robotic swarm than R-HGN training conditions. R-HGN has been found to enable appropriate behaviour selection in both these sets, allowing significant swarm performance in pre-trained and unexpected environment conditions.

Software-defined radios (SDRs) are often used in the experimental evaluation of next-generation wireless technologies. While crowd-sourced spectrum monitoring is an important component of future spectrum-agile technologies, there is no clear way to test it in the real world, i.e., with hundreds of users each with an SDR in their pocket participating in RF experiments controlled by, and data uploaded to, the cloud. Current fully functional SDRs are bulky, with components connected via wires, and last at most hours on a single battery charge. To address the needs of such experiments, we design and develop a compact, portable, untethered, and inexpensive SDR we call Sitara. Our SDR interfaces with a mobile device over Bluetooth 5 and can function standalone or as a client to a central command and control server. The Sitara offers true portability: it operates up to one week on battery power, requires no external wired connections and occupies a footprint smaller than a credit card. It transmits and receives common waveforms, uploads IQ samples or processed receiver data through a mobile device to a server for remote processing and performs spectrum sensing functions. Multiple Sitaras form a distributed system capable of conducting experiments in wireless networking and communication in addition to RF monitoring and sensing activities. In this paper, we describe our design, evaluate our solution, present experimental results from multi-sensor deployments and discuss the value of this system in future experimentation., Comment: 13 pages, 13 figures, 3 tables; For additional documentation and source code refer to https://github.com/SPAN-UofU