Previous research on multi-party dialogue generation has predominantly leveraged structural information inherent in dialogues to directly inform the generation process.However, the prevalence of colloquial expressions and incomplete utterances in dialogues often impedes comprehension and weakens the fidelity of dialogue structure representations, which is particularly pronounced in multi-party dialogues.In this work, we propose a novel framework DRCR (Discourse coherence and Responseguided Context Rewriting) to improve multiparty dialogue generation through dialogue context rewriting.Specifically, DRCR employs two complementary feedback signals, discourse coherence and response quality, to construct preference data for both context rewriting and response generation.Moreover, we propose a dynamic self-evolution learning method that allows the rewriter and responder to continuously enhance their capabilities through mutual interaction in an iterative training loop.Comprehensive experiments conducted on four multi-party dialogue datasets substantiate the effectiveness of DRCR.

Previous work on Incomplete Utterance Rewriting (IUR) has primarily focused on generating rewritten utterances based solely on dialogue context, ignoring the widespread phenomenon of coreference and ellipsis in dialogues. To address this issue, we propose a novel framework called TEO (Two-stage approach on Editing Operation) for IUR, in which the first stage generates editing operations and the second stage rewrites incomplete utterances utilizing the generated editing operations and the dialogue context. Furthermore, an adversarial perturbation strategy is proposed to mitigate cascading errors and exposure bias caused by the inconsistency between training and inference in the second stage. Experimental results on three IUR datasets show that our TEO outperforms the SOTA models significantly.

Most previous work on Conversational QueryRewriting employs an end-to-end rewriting paradigm.However, this approach is hindered by the issue of multiple fuzzy expressions within the query, which complicates the simultaneous identification and rewriting of multiple positions.To address this issue, we propose a novel framework ICR (Iterative Clarification and Rewriting), an iterative rewriting scheme that pivots on clarification questions.Within this framework, the model alternates between generating clarification questions and rewritten queries.The experimental results show that our ICR can continuously improve retrieval performance in the clarification-rewriting iterative process, thereby achieving state-of-the-art performance on two popular datasets.

Seismic data preprocessing significantly benefits from advanced sparse representation and domain transformation techniques to enhance denoising, wavefield separation, and data reconstruction. This study introduces a novel approach utilizing a deep learning framework for discrete sparse representation of seismic data. Our method utilizes a Swin Transformer-based encoding-decoding framework, which combines the hierarchical structures of CNNs with the self-attention mechanism of Transformers, to model both local and global information efficiently. This integration enables the precise characterization of seismic reflection events and the reconstruction of seismic records from a constructed sparse feature space. The proposed model has been rigorously tested on both simulated and field datasets, demonstrating its robustness, and potential provides superior decomposition of seismic data.

The least-squares reverse time migration (LSRTM), through iterative minimization of residuals between seismic observational and simulated data, can produce high-quality imaging results. However, it comes at the expense of high computational costs due to many wave-equation simulations in each iteration. To enhance the inversion efficiency of LSRTM, we embraced the source encoding strategy, merging multiple seismic shot gathers into several supergather shots, thereby reducing the scale of the seismic imaging problem. This, however, introduced severe crosstalk noise in imaging results. To mitigate the issue of crosstalk noise in source-encoded LSRTM, we proposed an improved multisource LSRTM method with a nonsubsampled Shearlet transform (NSST) scheme based on the regularization by denoising (RED) framework, which was named as RED-LSRTM. Employing the RED strategy, the NSST denoising engine can be flexibly integrated into the inversion process. Specifically, an NSST denoising operator is integrated into the gradient update step to optimize the solution of the inverse problem, effectively combining gradient optimization with inversion denoising, and enabling the suppression of crosstalk noise throughout the iteration. Numerical tests on the Layer model, the Salt model, and the Marmousi model validated that NSST-based RED-LSRTM effectively enhanced the imaging quality of simultaneous-sources inversion by alleviating more migration artifacts and suppressing more crosstalk noise when compared with standard LSRTM. Owing to its simplicity, flexibility, and effectiveness, our proposed method provides a reliable choice for mitigating crosstalk noise in an inversion of the simultaneous source or blended seismic data.

This study explores the innovative use of Large Language Models (LLMs) as analytical tools for interpreting complex financial regulations. The primary objective is to design effective prompts that guide LLMs in distilling verbose and intricate regulatory texts, such as the Basel III capital requirement regulations, into a concise mathematical framework that can be subsequently translated into actionable code. This novel approach aims to streamline the implementation of regulatory mandates within the financial reporting and risk management systems of global banking institutions. A case study was conducted to assess the performance of various LLMs, demonstrating that GPT-4 outperforms other models in processing and collecting necessary information, as well as executing mathematical calculations. The case study utilized numerical simulations with asset holdings - including fixed income, equities, currency pairs, and commodities - to demonstrate how LLMs can effectively implement the Basel III capital adequacy requirements.

Although existing fashionable generation methods on Incomplete Utterance Rewriting (IUR) can generate coherent utterances, they often result in the inclusion of irrelevant and redundant tokens in rewritten utterances due to their inability to focus on critical tokens in dialogue context.Furthermore, the limited size of the training datasets also contributes to the insufficient training of the IUR model.To address the first issue, we propose a multi-task learning framework EO-IUR (Editing Operation-guided Incomplete Utterance Rewriting) that introduces the editing operation labels generated by sequence labeling module to guide generation model to focus on critical tokens.Furthermore, we introduce a token-level heterogeneous graph to represent dialogues.To address the second issue, we propose a two-dimensional utterance augmentation strategy, namely editing operation-based incomplete utterance augmentation and LLM-based historical utterance augmentation.The experimental results on three datasets demonstrate that our EO-IUR outperforms previous state-of-the-art (SOTA) baselines in both open-domain and task-oriented dialogue.

Abstract Deep learning‐based single view 3D reconstruction is a hot topic in computer vision. However, predicting a more realistic 3D point cloud from a single image is an ill‐posed problem. In recent years, most of the 3D point cloud prediction methods based on single view are straight‐through structure, which will cause the loss of part of feature information and the loss of part of detail information of the resulting point clouds, which will lead to the unsatisfactory visual effect of reconstructed point clouds. In this paper, a Feature‐Enhanced 3D point clouds generation Network (3D‐FENet) from a single image is proposed. In order to enhance the feature information of RGB image, edge extraction module is adopted. In the process of point cloud generation, a point cloud pyramid is designed, which combines low resolution point cloud with high resolution point cloud to enhance the local details of the generated point clouds. In the fine‐tuning stage, the differential projection module is used to fine‐tune the whole network by 2D projection of reconstructed point clouds. Experimental results show that the performance of the authors’ proposed method is better than the state‐of‐the‐art studies.

The orthogonal-projection-based band selection (OPBS) algorithm is one of the newly proposed band selection methods. In this letter, we present a nonlinear version of the OPBS method, which is denoted as the Kernel-OPBS method. The OPBS method selects the desired bands one by one, and in each round of lookup, it chooses the band that has the maximum distance to the hyperplane spanned by the currently selected bands. Extending this algorithm to a feature space associated with the original input space through a certain nonlinear mapping function can provide a nonlinear version of the OPBS algorithm. Although it is basically intractable to compute the mapped bands due to the high dimensionality of the feature space produced by the nonlinear mapping function, the selection criterion of the Kernel-OPBS method is actually related to only the inner products of the mapped bands; thus, the kernel function can be applied and it is unnecessary to define the nonlinear mapping function. Experimental results on different data sets demonstrate that the selected bands obtained by the Kernel-OPBS method can achieve higher pixel classification performances than that by the OPBS method.

In this contribution the frequency-domain modeling techniques for resonant converters under optimized modulation are reviewed. As a general modeling technique, the standard AC fundamental harmonic approach is suitable for all resonant converter topologies. However, it becomes inaccurate if the current or voltage of the resonant tank is distorted from sinusoidal waveform. The extended AC fundamental harmonic approach provides a much higher modeling accuracy, but it lacks generality. In order to overcome these drawbacks a general, systematic time-domain modeling procedure with high modeling accuracy is introduced and demonstrated by a series-parallel resonant converter with LC output-filter under optimized modulation. Verification with experimental results is given.