Conversational agents, or chatbots, providing question-answer assistance on smart devices, have proliferated in recent years and are poised to transform online customer services of corporate sectors.1,6 Implemented through dialogue management systems, chatbots converse through voice-based and textual dialogue, and harness natural language processing and artificial intelligence to recognize requests, provide responses, and predict user behavior.5,28 Market analysts concur on current adoption trends and the magnitude of growth and impact of chatbots anticipated in the next five years. According to a report by Grand View Research, for instance, already 45% of users prefer chatbots as the primary point of communications for customer service enquiries, translating into a global'chatbot' market of $1.23 billion by 2025, at a compounded annual growth rate (CAGR) of 24.3%.9 The strategy for conducting conversations using chatbots requires an efficient resolution of two key aspects. First, user queries or automatically perceived needs through user interactions have to be interpreted and mapped into categories, or user intents. This is based on historical processing of queries and needs, and the use of intent classification techniques.12 Second, conversations must be constructed for specific intents using frame-based dialogue management2 and neural response generation techniques.15 In frame-based dialogue management, the chatbot needs to converse with the user to have a fully filled frame (for example, flight information) in which all slot values are provided by the user (for example, airline carrier, departure time, departure location, and arrival location). The dialogue flow is constructed through an ordered sequence of frames.

This paper presents a novel approach to automated playtesting for the prediction of human player behavior and experience. It has previously been demonstrated that Deep Reinforcement Learning (DRL) game-playing agents can predict both game difficulty and player engagement, operationalized as average pass and churn rates. We improve this approach by enhancing DRL with Monte Carlo Tree Search (MCTS). We also motivate an enhanced selection strategy for predictor features, based on the observation that an AI agent's best-case performance can yield stronger correlations with human data than the agent's average performance. Both additions consistently improve the prediction accuracy, and the DRL-enhanced MCTS outperforms both DRL and vanilla MCTS in the hardest levels. We conclude that player modelling via automated playtesting can benefit from combining DRL and MCTS. Moreover, it can be worthwhile to investigate a subset of repeated best AI agent runs, if AI gameplay does not yield good predictions on average.

Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieved state-of-the-art performance. However, existing solutions heavily rely on the exploitation of lexical features and their distributional signatures on training data, while neglecting to strengthen the model's ability to adapt to new tasks. In this paper, we propose a novel meta-learning framework integrated with an adversarial domain adaptation network, aiming to improve the adaptive ability of the model and generate high-quality text embedding for new classes. Extensive experiments are conducted on four benchmark datasets and our method demonstrates clear superiority over the state-of-the-art models in all the datasets. In particular, the accuracy of 1-shot and 5-shot classification on the dataset of 20 Newsgroups is boosted from 52.1% to 59.6%, and from 68.3% to 77.8%, respectively.

When humans solve complex problems, they rarely come up with a decision right-away. Instead, they start with an intuitive decision, reflect upon it, spot mistakes, resolve contradictions and jump between different hypotheses. Thus, they create a sequence of ideas and follow a train of thought that ultimately reaches a conclusive decision. Contrary to this, today's neural classification models are mostly trained to map an input to one single and fixed output. In this paper, we investigate how we can give models the opportunity of a second, third and $k$-th thought. We take inspiration from Hegel's dialectics and propose a method that turns an existing classifier's class prediction (such as the image class forest) into a sequence of predictions (such as forest $\rightarrow$ tree $\rightarrow$ mushroom). Concretely, we propose a correction module that is trained to estimate the model's correctness as well as an iterative prediction update based on the prediction's gradient. Our approach results in a dynamic system over class probability distributions $\unicode{x2014}$ the thought flow. We evaluate our method on diverse datasets and tasks from computer vision and natural language processing. We observe surprisingly complex but intuitive behavior and demonstrate that our method (i) can correct misclassifications, (ii) strengthens model performance, (iii) is robust to high levels of adversarial attacks, (iv) can increase accuracy up to 4% in a label-distribution-shift setting and (iv) provides a tool for model interpretability that uncovers model knowledge which otherwise remains invisible in a single distribution prediction.

Despite the success of deep neural networks (DNNs) in enabling on-device voice assistants, increasing evidence of bias and discrimination in machine learning is raising the urgency of investigating the fairness of these systems. Speaker verification is a form of biometric identification that gives access to voice assistants. Due to a lack of fairness metrics and evaluation frameworks that are appropriate for testing the fairness of speaker verification components, little is known about how model performance varies across subgroups, and what factors influence performance variation. To tackle this emerging challenge, we design and develop SVEva Fair, an accessible, actionable and model-agnostic framework for evaluating the fairness of speaker verification components. The framework provides evaluation measures and visualisations to interrogate model performance across speaker subgroups and compare fairness between models. We demonstrate SVEva Fair in a case study with end-to-end DNNs trained on the VoxCeleb datasets to reveal potential bias in existing embedded speech recognition systems based on the demographic attributes of speakers. Our evaluation shows that publicly accessible benchmark models are not fair and consistently produce worse predictions for some nationalities, and for female speakers of most nationalities. To pave the way for fair and reliable embedded speaker verification, SVEva Fair has been implemented as an open-source python library and can be integrated into the embedded ML development pipeline to facilitate developers and researchers in troubleshooting unreliable speaker verification performance, and selecting high impact approaches for mitigating fairness challenges

Playtesting is an essential step in the game design process. Game designers use the feedback from playtests to refine their design. Game designers may employ procedural personas to automate the playtesting process. In this paper, we present two approaches to improve automated playtesting. First, we propose a goal-based persona model, which we call developing persona -- developing persona proposes a dynamic persona model, whereas the current persona models are static. Game designers can use the developing persona to model the changes that a player undergoes while playing a game. Additionally, a human playtester knows which paths she has tested before, and during the consequent tests, she may test different paths. However, RL agents disregard the previously generated trajectories. We propose a novel methodology that helps Reinforcement Learning (RL) agents to generate distinct trajectories than the previous trajectories. We refer to this methodology as Alternative Path Finder (APF). We present a generic APF framework that can be applied to all RL agents. APF is trained with the previous trajectories, and APF distinguishes the novel states from similar states. We use the General Video Game Artificial Intelligence (GVG-AI) and VizDoom frameworks to test our proposed methodologies. We use Proximal Policy Optimization (PPO) RL agent during experiments. First, we show that the playtest data generated by the developing persona cannot be generated using the procedural personas. Second, we present the alternative paths found using APF. We show that the APF penalizes the previous paths and rewards the distinct paths.

India lost two early wickets in the first session of the initial innings of the ICC Test Championship Final. There is already much history about him and England. This History was enough to create the hype around him. On the first note, the ground was the same where India loses their debut world cup winning chance in the captaincy of Kohli. Southampton has seen India losing enough times.

One of the difficulties in training dialogue systems is the lack of training data. We explore the possibility of creating dialogue data through the interaction between a dialogue system and a user simulator. Our goal is to develop a modelling framework that can incorporate new dialogue scenarios through self-play between the two agents. In this framework, we first pre-train the two agents on a collection of source domain dialogues, which equips the agents to converse with each other via natural language. With further fine-tuning on a small amount of target domain data, the agents continue to interact with the aim of improving their behaviors using reinforcement learning with structured reward functions. In experiments on the MultiWOZ dataset, two practical transfer learning problems are investigated: 1) domain adaptation and 2) single-to-multiple domain transfer. We demonstrate that the proposed framework is highly effective in bootstrapping the performance of the two agents in transfer learning. We also show that our method leads to improvements in dialogue system performance on complete datasets.

Deep generative models have recently achieved impressive performance in speech and music synthesis. However, compared to the generation of those domain-specific sounds, generating general sounds (such as siren, gunshots) has received less attention, despite their wide applications. In previous work, the SampleRNN method was considered for sound generation in the time domain. However, SampleRNN is potentially limited in capturing long-range dependencies within sounds as it only back-propagates through a limited number of samples. In this work, we propose a method for generating sounds via neural discrete time-frequency representation learning, conditioned on sound classes. This offers an advantage in efficiently modelling long-range dependencies and retaining local fine-grained structures within sound clips. We evaluate our approach on the UrbanSound8K dataset, compared to SampleRNN, with the performance metrics measuring the quality and diversity of generated sounds. Experimental results show that our method offers comparable performance in quality and significantly better performance in diversity.