Learning to Seek: Multi-Agent Online Source Seeking Against Non-Stochastic Disturbances

This paper proposes to leverage the emerging~learning techniques and devise a multi-agent online source {seeking} algorithm under unknown environment. Of particular significance in our problem setups are: i) the underlying environment is not only unknown, but dynamically changing and also perturbed by two types of non-stochastic disturbances; and ii) a group of agents is deployed and expected to cooperatively seek as many sources as possible. Correspondingly, a new technique of discounted Kalman filter is developed to tackle with the non-stochastic disturbances, and a notion of confidence bound in polytope nature is utilized~to aid the computation-efficient cooperation among~multiple agents. With standard assumptions on the unknown environment as well as the disturbances, our algorithm is shown to achieve sub-linear regrets under the two~types of non-stochastic disturbances; both results are comparable to the state-of-the-art. Numerical examples on a real-world pollution monitoring application are provided to demonstrate the effectiveness of our algorithm.

User Adaptive Language Learning Chatbots with a Curriculum

Along with the development of systems for natural language understanding and generation, dialog systems have been widely adopted for language learning and practicing. Many current educational dialog systems perform chitchat, where the generated content and vocabulary are not constrained. However, for learners in a school setting, practice through dialog is more effective if it aligns with students' curriculum and focuses on textbook vocabulary. Therefore, we adapt lexically constrained decoding to a dialog system, which urges the dialog system to include curriculum-aligned words and phrases in its generated utterances. We adopt a generative dialog system, BlenderBot3, as our backbone model and evaluate our curriculum-based dialog system with middle school students learning English as their second language. The constrained words and phrases are derived from their textbooks, suggested by their English teachers. The evaluation result demonstrates that the dialog system with curriculum infusion improves students' understanding of target words and increases their interest in practicing English.

Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking

Prompt-based methods with large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks. These models improve even further with the addition of a few labeled in-context exemplars to guide output generation. However, for more complex tasks such as dialogue state tracking (DST), designing prompts that reliably convey the desired intent is nontrivial, leading to unstable results. Furthermore, building in-context exemplars for dialogue tasks is difficult because conversational contexts are long while model input lengths are relatively short. To overcome these issues we first adapt a meta-learning scheme to the dialogue domain which stabilizes the ability of the model to perform well under various prompts. We additionally design a novel training method to improve upon vanilla retrieval mechanisms to find ideal in-context examples. Finally, we introduce a saliency model to limit dialogue text length, allowing us to include more exemplars per query. In effect, we are able to achieve highly competitive results for few-shot DST on MultiWOZ.

A Comprehensive Survey on Heart Sound Analysis in the Deep Learning Era

Heart sound auscultation has been demonstrated to be beneficial in clinical usage for early screening of cardiovascular diseases. Due to the high requirement of well-trained professionals for auscultation, automatic auscultation benefiting from signal processing and machine learning can help auxiliary diagnosis and reduce the burdens of training professional clinicians. Nevertheless, classic machine learning is limited to performance improvement in the era of big data. Deep learning has achieved better performance than classic machine learning in many research fields, as it employs more complex model architectures with stronger capability of extracting effective representations. Deep learning has been successfully applied to heart sound analysis in the past years. As most review works about heart sound analysis were given before 2017, the present survey is the first to work on a comprehensive overview to summarise papers on heart sound analysis with deep learning in the past six years 2017--2022. We introduce both classic machine learning and deep learning for comparison, and further offer insights about the advances and future research directions in deep learning for heart sound analysis.

KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning

In task-oriented dialogs, an informative and successful system response needs to include key information such as the phone number of a hotel. Therefore, we hypothesize that a model can achieve better overall performance by focusing on correctly generating key quantities. In this paper, we propose a new training algorithm, Keywords Reinforcement Learning with Next-word Sampling (KRLS), that utilizes Reinforcement Learning but avoids the time-consuming auto-regressive generation, and a fine-grained per-token reward function to help the model learn keywords generation more robustly. Empirical results show that the KRLS algorithm can achieve state-of-the-art performance on the inform, success, and combined score on the MultiWoZ benchmark dataset.

Keywords Reinforcement LM: Improving End-to-End Response Generation in Task Oriented Dialog

In task-oriented dialogs such as MultiWoZ (Budzianowski et al., 2018), an informative and successful system response needs to include key information such as the phone number of a hotel. Therefore, we hypothesize that by asking the model to focus on generating more key quantities correctly, it can achieve better overall performance. In this paper, we propose a new training algorithm, Keywords Reinforcement Language Modeling (KRLM), that aims to use a fine-grained reward function for each token and a new per-token Reinforcement Learning procedure to help the model learn keywords generation more robustly during inference. Empirical results show that our proposed KRLM training algorithm can achieve state-of-the-art performance on the inform rate, success rate, and combined score in the MultiWoZ benchmark dataset.

Reinforced Language Modeling for End-to-End Task Oriented Dialog

In task-oriented dialogs such as MultiWoZ (Budzianowski et al., 2018), an informative and/or successful system response needs to include necessary key information such as the phone number of a hotel. Therefore, we hypothesize that by helping the model to focus more on learning key quantities in the dialog, the model can generative more informative and helpful responses. In this paper, we propose a new training algorithm, Reinforced Language Modeling (RLM), that aims to use a fine-grained reward function and reinforcement learning to help the model focus more on generating key quantities correctly during test time. Empirical results show our proposed RLM achieves state-of-the-art performance on the inform rate, success rate, and combined score in MultiWoZ.

Boosting Personalised Musculoskeletal Modelling with Physics-informed Knowledge Transfer

Data-driven methods have become increasingly more prominent for musculoskeletal modelling due to their conceptually intuitive simple and fast implementation. However, the performance of a pre-trained data-driven model using the data from specific subject(s) may be seriously degraded when validated using the data from a new subject, hindering the utility of the personalised musculoskeletal model in clinical applications. This paper develops an active physics-informed deep transfer learning framework to enhance the dynamic tracking capability of the musculoskeletal model on the unseen data. The salient advantages of the proposed framework are twofold: 1) For the generic model, physics-based domain knowledge is embedded into the loss function of the data-driven model as soft constraints to penalise/regularise the data-driven model. 2) For the personalised model, the parameters relating to the feature extraction will be directly inherited from the generic model, and only the parameters relating to the subject-specific inference will be finetuned by jointly minimising the conventional data prediction loss and the modified physics-based loss. In this paper, we use the synchronous muscle forces and joint kinematics prediction from surface electromyogram (sEMG) as the exemplar to illustrate the proposed framework. Moreover, convolutional neural network (CNN) is employed as the deep neural network to implement the proposed framework, and the physics law between muscle forces and joint kinematics is utilised as the soft constraints. Results of comprehensive experiments on a self-collected dataset from eight healthy subjects indicate the effectiveness and great generalization of the proposed framework.

Knowledge Transfer For On-Device Speech Emotion Recognition with Neural Structured Learning

Speech emotion recognition (SER) has been a popular research topic in human-computer interaction (HCI). As edge devices are rapidly springing up, applying SER to edge devices is promising for a huge number of HCI applications. Although deep learning has been investigated to improve the performance of SER by training complex models, the memory space and computational capability of edge devices represents a constraint for embedding deep learning models. We propose a neural structured learning (NSL) framework through building synthesized graphs. An SER model is trained on a source dataset and used to build graphs on a target dataset. A lightweight model is then trained with the speech samples and graphs together as the input. Our experiments demonstrate that training a lightweight SER model on the target dataset with speech samples and graphs can not only produce small SER models, but also enhance the model performance over models with speech samples only.

Learning a Better Initialization for Soft Prompts via Meta-Learning

Prompt tuning (PT) is an effective approach to adapting pre-trained language models to downstream tasks. Without a good initialization, prompt tuning doesn't perform well under few-shot settings. So pre-trained prompt tuning (PPT) is proposed to initialize prompts by leveraging pre-training data. We propose MetaPT (Meta-learned Prompt Tuning) to further improve PPT's initialization by considering latent structure within the pre-training data. Specifically, we introduce the structure by first clustering pre-training data into different auxiliary tasks with unsupervised methods. Then we use these tasks to pre-train prompts with a meta-learning algorithm. Such a process can make prompts learn a better initialization by discovering commonalities among these auxiliary tasks. We evaluate our method on seven downstream tasks. Our MetaPT achieves better and more stable performance than the state-of-the-art method.