Short videos are an effective tool for promoting contents and improving knowledge accessibility. While existing extractive video summarization methods struggle to produce a coherent narrative, existing abstractive methods cannot `quote' from the input videos, i.e., inserting short video clips in their outputs. In this work, we explore novel video editing models for generating shorts that feature a coherent narrative with embedded video insertions extracted from a long input video. We propose a novel retrieval-embedded generation framework that allows a large language model to quote multimodal resources while maintaining a coherent narrative. Our proposed REGen system first generates the output story script with quote placeholders using a finetuned large language model, and then uses a novel retrieval model to replace the quote placeholders by selecting a video clip that best supports the narrative from a pool of candidate quotable video clips. We examine the proposed method on the task of documentary teaser generation, where short interview insertions are commonly used to support the narrative of a documentary. Our objective evaluations show that the proposed method can effectively insert short video clips while maintaining a coherent narrative. In a subjective survey, we show that our proposed method outperforms existing abstractive and extractive approaches in terms of coherence, alignment, and realism in teaser generation.

The integration of mobile edge computing (MEC) and air-ground integrated network is viewed as a crucial technology for Internet of Remote Things (IoRT) devices. It provides widespread service coverage and allows the tasks of IoRT devices to be executed by the uncrewed aerial vehicles (UAVs) and the high altitude platforms (HAPs). In this article, we investigate a joint partial task offloading, resource allocation, and UAV trajectory design problem to minimize the total task offloading delay of all IoRT devices in the air-ground integrated MEC network. Given that the problem is nonconvex and hard to solve by the traditional methods, we convert it into a Markov decision process (MDP) and leverage the deep reinforcement learning method to address it. Considering the complexity of the MDP grows with the number of the IoRT devices and the UAVs increasing, the primal problem is decomposed into two subproblems: 1) the UAV trajectory design and IoRT device power control subproblem, and 2) the partial task offloading and resource allocation subproblem. To address these two subproblems, we apply the basic concepts of the multiagent deep deterministic policy gradient (MADDPG) and the independent proximal policy optimization (IPPO) methods, respectively. Additionally, we introduce the enhanced prioritized experience replay and noise value to improve both the convergence performance and rate. This leads to the development of the MADDPG-improved prioritized experience replay (MADDPG-IPER) algorithm and noise value-IPPO (NV-IPPO) algorithm. Based on the solution of these two subproblems, a joint partial task offloading, resource allocation, and UAV trajectory design (JPTORAUTD) algorithm is proposed. Simulation results present that the proposed JPTORAUTD algorithm outperforms other benchmark algorithms in terms of reducing the total task offloading delay.

This study investigates text keyword and phrase extraction methods based on the GPT-3.5 model,and validates their effectiveness through comparative analysis. Initially, researchers employ the GPT-3.5 model for extracting keywords and phrases from text to uncover crucial information within the text. Subsequently, the extracted data from GPT-3.5 is compared with the key text from the original dataset to assess extraction performance and consistency. Lastly, extracted keywords are utilized for sentiment analysis, conducting comparative experiments with the BERT-TextCNN model, and validation across diverse datasets. The research findings demonstrate the GPT-3.5 model's capability to efficiently extract crucial textual information and significantly enhance sentiment classification precision. This enhancement contributes to improved performance and interpretability in text analysis, thereby providing substantial support for the field of natural language processing.

Entity typing aims to assign types to the entity mentions in given texts.The traditional classification-based entity typing paradigm has two unignorable drawbacks: 1) it fails to assign an entity to the types beyond the predefined type set, and 2) it can hardly handle few-shot and zero-shot situations where many long-tail types only have few or even no training instances.To overcome these drawbacks, we propose a novel generative entity typing (GET) paradigm: given a text with an entity mention, the multiple types for the role that the entity plays in the text are generated with a pre-trained language model (PLM).However, PLMs tend to generate coarse-grained types after finetuning upon the entity typing dataset.In addition, only the heterogeneous training data consisting of a small portion of human-annotated data and a large portion of auto-generated but low-quality data are provided for model training.To tackle these problems, we employ curriculum learning (CL) to train our GET model on heterogeneous data, where the curriculum could be self-adjusted with the self-paced learning according to its comprehension of the type granularity and data heterogeneity.Our extensive experiments upon the datasets of different languages and downstream tasks justify the superiority of our GET model over the state-ofthe-art entity typing models.The code has been released on https://github.com/siyuyuan/GET.

Textbook Question Answering (TQA) is the task of answering diagram and non-diagram questions given large multi-modal contexts consisting of abundant text and diagrams. Deep text understandings and effective learning of diagram semantics are important for this task due to its specificity. In this paper, we propose a Weakly Supervised learning method for TQA (WSTQ), which regards the incompletely accurate results of essential intermediate procedures for this task as supervision to develop Text Matching (TM) and Relation Detection (RD) tasks and then employs the tasks to motivate itself to learn strong text comprehension and excellent diagram semantics respectively. Specifically, we apply the result of text retrieval to build positive as well as negative text pairs. In order to learn deep text understandings, we first pre-train the text understanding module of WSTQ on TM and then fine-tune it on TQA. We build positive as well as negative relation pairs by checking whether there is any overlap between the items/regions detected from diagrams using object detection. The RD task forces our method to learn the relationships between regions, which are crucial to express the diagram semantics. We train WSTQ on RD and TQA simultaneously, i.e., multitask learning, to obtain effective diagram semantics and then improve the TQA performance. Extensive experiments are carried out on CK12-QA and AI2D to verify the effectiveness of WSTQ. Experimental results show that our method achieves significant accuracy improvements of 5.02% and 4.12% on test splits of the above datasets respectively than the current state-of-the-art baseline. We have released our code on https://github.com/dr-majie/WSTQ.

This paper considers the channel estimation problem in millimeter-wave (mmWave) systems where a single-antenna user communicates with a massive multiple-input multiple-output (MIMO) base station (BS) in the uplink. Unlike many existing works which estimate the channel gain under the assumption that the number of channel paths is given a priori, we address first the problem of path-number identification. By taking the weighted discrete Fourier transform (WDFT) of the received noisy signal, we formulate an optimization problem to determine the optimum combination of DFT components in this weighted spectrum that leads to a time-domain reconstructed signal (the channel vector) that is at the minimum Euclidean distance from the received signal. Our algorithm, called SWISS (Spectrum Weighted Identification of Signal Sources), is an accurate and computationally efficient means for identifying the paths in the channel vector, providing the information needed for BS beamforming. Once the paths are identified, their individual directions-of-arrival (DoAs) and complex fading gains can be obtained easily. Simulation results for the case of no power leakage in the DFT are presented to demonstrate the effectiveness of SWISS.

This paper studies multi-group multicast beamforming with a hybrid large-scale antenna array in millimeter wave (mmWave) communication systems. A low-complexity hybrid structure is adopted, where each RF chain is only connected to part of the antenna elements. We formulate a hybrid analog and digital beamforming design problem for multi-group multicast transmission with the objective of minimizing the total transmit power at the base station, subject to an individual signal-to-interference-plus-noise ratio constraint for each multicast group. The problem is very challenging and its global optimal solution is difficult to obtain. We first adopt alternating minimization method to design the analog and digital beamformer alternatively. Then we solve each of the analog and digital subproblems through solving a sequence of convex problems via concave-convex procedure (CCP). Each convex CCP subproblem is reformulated as a novel alternating direction method of multipliers (ADMM) form. Our ADMM reformulation enables that each updating step can be decomposed into multiple subproblems with much smaller size, which can be solved optimally in parallel with closed-form expressions. Simulation results show that our algorithm can achieve favorable performance with very low complexity compared with the state-of-art methods.