Automatic Speech Recognition (ASR) systems are pivotal in transcribing speech into text, yet the errors they introduce can significantly degrade the performance of downstream tasks like summarization. This issue is particularly pronounced in clinical dialogue summarization, a low-resource domain where supervised data for fine-tuning is scarce, necessitating the use of ASR models as black-box solutions. Employing conventional data augmentation for enhancing the noise robustness of summarization models is not feasible either due to the unavailability of sufficient medical dialogue audio recordings and corresponding ASR transcripts. To address this challenge, we propose MEDSAGE, an approach for generating synthetic samples for data augmentation using Large Language Models (LLMs). Specifically, we leverage the in-context learning capabilities of LLMs and instruct them to generate ASR-like errors based on a few available medical dialogue examples with audio recordings. Experimental results show that LLMs can effectively model ASR noise, and incorporating this noisy data into the training process significantly improves the robustness and accuracy of medical dialogue summarization systems. This approach addresses the challenges of noisy ASR outputs in critical applications, offering a robust solution to enhance the reliability of clinical dialogue summarization.

With the rapid proliferation of the Internet of Things, video analytics has become a cornerstone application in wireless multimedia sensor networks. To support such applications under bandwidth constraints, learning-based adaptive quantization for video compression has demonstrated strong potential in reducing bitrate while maintaining analytical accuracy. However, existing frameworks often fail to fully exploit the fine-grained quality control enabled by modern blockbased video codecs, leaving significant compression efficiency untapped.

Edge Video Analytics (EVA) has become a major application of pervasive computing, enabling real-time visual processing. EVA pipelines, composed of deep neural networks (DNNs), typically demand efficient inference serving under stringent latency requirements, which is challenging due to the dynamic Edge environments (e.g., workload variability and network instability). Moreover, EVA pipelines face significant resource contention due to resource (e.g., GPU) constraints at the Edge. In this paper, we introduce OctopInf, a novel resource-efficient and workload-aware inference serving system designed for real-time EVA. OctopInf tackles the unique challenges of dynamic edge environments through fine-grained resource allocation, adaptive batching, and workload balancing between edge devices and servers. Furthermore, we propose a spatiotemporal scheduling algorithm that optimizes the co-location of inference tasks on GPUs, improving performance and ensuring service-level objectives (SLOs) compliance. Extensive evaluations on a real-world testbed demonstrate the effectiveness of our approach. It achieves an effective throughput increase of up to 10× compared to the baselines and shows better robustness in challenging scenarios. OctopInf can be used for any DNN-based EVA inference task with minimal adaptation and is available at https://github.com/tungngreen/PipelineScheduler.

Abhinav Ramesh Kashyap, Thanh-Tung Nguyen, Viktor Schlegel, Stefan Winkler, See-Kiong Ng, Soujanya Poria. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Cross-camera real-time object tracking is one of the important, yet challenging applications of video analytics in edge computing environments. To provide accurate and efficient real-time tracking, a tracking target's future movements need to be predicted. Particularly, the destination camera and travel time of the target object are to be identified so that tracking duties can be handover-ed seamlessly. In this paper, we propose a collaborative cross-camera tracking system, called PreActo, with two key features: (1) ResNet-based trajectory learning to exploit the rich spatio-temporal information embedded within objects' moving patterns, which has not been utilized by the existing literature, and (2) collaboration between the edge server and the edge device for real-time trajectory prediction and tracking handover. To prove the validity of our proposed system, we evaluate PreActo on a video dataset leveraging real-world trajectories. Evaluation results show that the proposed system reduces up to$7\times$the number of processed frames for handover, with$2\times$lower latency while providing$1.5\times$tracking precision improvement compared to the state-of-the-art.

Thanh-Tung Nguyen, Xuan-Phi Nguyen, Shafiq Joty, Xiaoli Li. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Recent unsupervised machine translation (UMT) systems usually employ three main principles: initialization, language modeling and iterative back-translation, though they may apply them differently. Crucially, iterative back-translation and denoising auto-encoding for language modeling provide data diversity to train the UMT systems. However, the gains from these diversification processes has seemed to plateau. We introduce a novel component to the standard UMT framework called Cross-model Back-translated Distillation (CBD), that is aimed to induce another level of data diversification that existing principles lack. CBD is applicable to all previous UMT approaches. In our experiments, CBD achieves the state of the art in the WMT’14 English-French, WMT’16 English-German and English-Romanian bilingual unsupervised translation tasks, with 38.2, 30.1, and 36.3 BLEU respectively. It also yields 1.5–3.3 BLEU improvements in IWSLT English-French and English-German tasks. Through extensive experimental analyses, we show that CBD is effective because it embraces data diversity while other similar variants do not.

We introduce a novel top-down end-to-end formulation of document level discourse parsing in the Rhetorical Structure Theory (RST) framework. In this formulation, we consider discourse parsing as a sequence of splitting decisions at token boundaries and use a seq2seq network to model the splitting decisions. Our framework facilitates discourse parsing from scratch without requiring discourse segmentation as a prerequisite; rather, it yields segmentation as part of the parsing process. Our unified parsing model adopts a beam search to decode the best tree structure by searching through a space of high scoring trees. With extensive experiments on the standard RST discourse treebank, we demonstrate that our parser outperforms existing methods by a good margin in both end-to-end parsing and parsing with gold segmentation. More importantly, it does so without using any handcrafted features, making it faster and easily adaptable to new languages and domains.

We propose a novel constituency parsing model that casts the parsing problem into a series of pointing tasks.Specifically, our model estimates the likelihood of a span being a legitimate tree constituent via the pointing score corresponding to the boundary words of the span.Our parsing model supports efficient top-down decoding and our learning objective is able to enforce structural consistency without resorting to the expensive CKY inference.The experiments on the standard English Penn Treebank parsing task show that our method achieves 92.78 F1 without using pre-trained models, which is higher than all the existing methods with similar time complexity.Using pre-trained BERT, our model achieves 95.48 F1, which is competitive with the state-of-theart while being faster.Our approach also establishes new state-of-the-art in Basque and Swedish in the SPMRL shared tasks on multilingual constituency parsing.

We propose Differentiable Window, a new neural module and general purpose component for dynamic window selection.While universally applicable, we demonstrate a compelling use case of utilizing Differentiable Window to improve standard attention modules by enabling more focused attentions over the input regions.We propose two variants of Differentiable Window, and integrate them within the Transformer architecture in two novel ways.We evaluate our proposed approach on a myriad of NLP tasks, including machine translation, sentiment analysis, subject-verb agreement and language modeling.Our experimental results demonstrate consistent and sizable improvements across all tasks.

TDMA protocols can provide a reliable, collision-free data-transferring mechanism for wireless sensor networks. However, it requires an effective scheduling (time slot assignment)algorithm, which is a challenging issue, especially in wireless multi-hop networks due to random-based competition. In this paper, we propose DSTO, a distributed TDMA scheduling algorithm using Topological Ordering (TO). DSTO aims to reduce conflict of scheduling time among neighbor nodes by creating a Topological Order with local neighborhood size as the main priority factor. We implemented DSTO on OPNET Network Simulator and proved its effectiveness compared to DRAND in terms of running time and message overheads.