This paper investigates the problem of a robust diffusion Kalman filter in a nonlinear system within multi-sensor networks. To address the challenge of model mismatch caused by unmodeled dynamics or external disturbances, a novel robust diffusion Kalman filter (RDKF) algorithm is proposed. Conventional DKF algorithms typically suffer from significant performance degradation when system models deviate from actual dynamics, due to their reliance on accurate model assumptions. To overcome this limitation, a model mismatch compensation mechanism is incorporated into the proposed RDKF, which actively corrects estimation failures induced by inaccurate models. Furthermore, to release the additional network communication burden introduced by the compensation mechanism, two selective neighbor communication strategies are developed, which are the Round-Robin-inspired (RR-inspired) periodic selection strategy and the optimal selection strategy preserving estimation quality. In addition, the theoretical analysis about the mean and mean-square stability is established, and the equivalence between local and global estimation stability is demonstrated, which guarantees the effectiveness of the designed global compensation mechanism for both global and local estimates. Finally, two simulation examples on target tracking are presented to demonstrate the performance comparison between the proposed RDKFs and the conventional DKF approaches in both linear and nonlinear systems.

This paper investigates the robust state estimation problem for non-cooperative target tracking to overcome the limitations of conventional tracking algorithms under model uncertainty and noise uncertainty. Although some existing algorithms employ the maximum correntropy criterion (MCC) to handle non-Gaussian noise, most of them generally assume precise state-space models and neglect the effect of uncertain noise parameters as well. To deal with this limitation, a robust fuzzy adaptive MCC-based unscented Kalman filter (UKF) algorithm is proposed, which enhances robustness through the simultaneous state and unknown input estimation (SSUIE), and adjusts the noise covariance via a fuzzy inference system (FIS) adaptively. First, an unknown input (UI) estimator is integrated into the MCC-based UKF to tackle the challenge of model uncertainty, thereby eliminating the reliance on a precise state-space model. Then, an FIS is employed to adjust noise covariance, which explicitly accounts for uncertain noise statistics, improving adaptability in challenging conditions. Notably, the FIS-based adjustment is a more efficient and flexible method compared to the interacting multiple model (IMM) and variational Bayesian (VB) methods, as it avoids the need for precise prior knowledge and high computational complexity. Finally, the simulation results demonstrate that our proposed algorithm can enable effective tracking of non-cooperative targets, even during orbital maneuvers and under uncertain noise conditions. This work provides an adaptive solution for enhancing estimation robustness against uncertain target behaviors and dynamic environments, with potential applications in autonomous systems and security defense systems.

In recent years, Internet memes have been widely used in online chatting. Compared with text-based communication, conversations become more expressive and attractive when Internet memes are incorporated. This article presents our solutions for the Meme incorporated Open-domain Dialogue (MOD) Challenge of DSTC10, where three tasks are involved: text response modeling, meme retrieval, and meme emotion classification. Firstly, we leverage a large-scale pre-trained dialogue model for coherent and informative response generation. Secondly, based on interaction-based text-matching, our approach can retrieve appropriate memes with good generalization ability. Thirdly, we propose to model the emotion flow (EF) in conversations and introduce an auxiliary task of emotion description prediction (EDP) to boost the performance of meme emotion classification. Experimental results on the MOD dataset demonstrate that our methods can incorporate Internet memes into dialogue systems effectively.

This article addresses an enhanced distributed outlier-resilient fusion estimation problem using an interval type-2 (IT-2) Takagi–Sugeno (T–S) fuzzy model, integrating outlier detection schemes and dimensionality reduction (DR) strategies. First, the IT-2 T–S fuzzy model is employed to handle system uncertainty and nonlinearity effectively. Then, the outlier-resilient local estimator is proposed using the zonotope-based set-membership filters (ZSMFs), where the outlier detection scheme only relies on the intersection between the predicted set and the measurement set. Furthermore, the compressed local estimate (LE) are designed when there are bandwidth constraints in sensor networks, and a novel DR strategy is proposed to design this compressed LE, where the compression matrix is determined by the Round–Robin protocol (RRP). After this, based on the compressed LEs, a distributed resilient zonotopic fusion estimator (DRZFE) is derived by the matrix-weighted fusion method. Note that the computational load of the DRZFE is reduced effectively due to the zonotope order reduction and the RRP-based DR independent of the online optimization. Moreover, the compensation of outliers and the compensating state estimate of RRP-based DR may improve the resilience of the algorithm and reduce information loss. Finally, two numerical examples are provided to validate the advantages and effectiveness of the proposed methods, and we use root-mean-square-error as the indicator to assess the estimation accuracy.

Aspects are opinion targets to extract in aspect-based sentiment analysis. While existing methods can already produce satisfactory extraction results, they suffer when faced with compound aspect terms, typically phrase-level aspect terms that have inner structure and occur infrequently in the training set. This issue can be mainly attributed to the scarcity of training examples targeting compound aspect terms and by the neglect of the syntactic structure of a sentence in the modeling process. In this article, we aim to cope with compound aspect extraction by a two-stage hybrid approach. First, we introduce a conditional generation method for data augmentation in a masked sequence-to-sequence framework, which is controllable to preserve original aspects while generating a new sentence. Second, we propose a constituency lattice structure that is induced from the constituency-based parse tree of a sentence. Experimental results on two review datasets show that this approach can greatly improve the effect of compound aspect extraction.

This paper presents our task-oriented dialog system UBAR which models task-oriented dialogs on a dialog session level. Specifically, UBAR is acquired by fine-tuning the large pre-trained unidirectional language model GPT-2 on the sequence of the entire dialog session which is composed of user utterance, belief state, database result, system act, and system response of every dialog turn. Additionally, UBAR is evaluated in a more realistic setting, where its dialog context has access to user utterances and all content it generated such as belief states, system acts, and system responses. Experimental results on the MultiWOZ datasets show that UBAR achieves state-of-the-art performances in multiple settings, improving the combined score of response generation, policy optimization, and end-to-end modeling by 4.7, 3.5, and 9.4 points respectively. Thorough analyses demonstrate that the session-level training sequence formulation and the generated dialog context are essential for UBAR to operate as a fully end-to-end task-oriented dialog system in real life. We also examine the transfer ability of UBAR to new domains with limited data and provide visualization and a case study to illustrate the advantages of UBAR in modeling on a dialog session level.

Personality detection aims to identify the personality traits implied in social media posts. The core of this task is to put together information in multiple scattered posts to depict an overall personality profile for each user. Existing approaches either encode each post individually or assemble posts arbitrarily into a new document that can be encoded sequentially or hierarchically. While the first approach ignores the connection between posts, the second tends to introduce unnecessary post-order bias into posts. In this paper, we propose a multi-document Transformer, namely Transformer-MD, to tackle the above issues. When encoding each post, Transformer-MD allows access to information in the other posts of the user through Transformer-XL’s memory tokens which share the same position embedding.Besides, personality is usually defined along different traits and each trait may need to attend to different post information, which has rarely been touched by existing research. To address this concern, we propose a dimension attention mechanism on top of Transformer-MD to obtain trait-specific representations for multi-trait personality detection. We evaluate the proposed model on the Kaggle and Pandora MBTI datasets and the experimental results show that it compares favorably with baseline methods.

Weizhou Shen, Siyue Wu, Yunyi Yang, Xiaojun Quan. 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.

Aspect-based sentiment analysis aims to determine the sentiment polarity towards a specific aspect in online reviews.Most recent efforts adopt attention-based neural network models to implicitly connect aspects with opinion words.However, due to the complexity of language and the existence of multiple aspects in a single sentence, these models often confuse the connections.In this paper, we address this problem by means of effective encoding of syntax information.Firstly, we define a unified aspect-oriented dependency tree structure rooted at a target aspect by reshaping and pruning an ordinary dependency parse tree.Then, we propose a relational graph attention network (R-GAT) to encode the new tree structure for sentiment prediction.Extensive experiments are conducted on the SemEval 2014 and Twitter datasets, and the experimental results confirm that the connections between aspects and opinion words can be better established with our approach, and the performance of the graph attention network (GAT) is significantly improved as a consequence.

One of the remaining challenges for aspect term extraction in sentiment analysis resides in the extraction of phrase-level aspect terms, which is non-trivial to determine the boundaries of such terms. In this paper, we aim to address this issue by incorporating the span annotations of constituents of a sentence to leverage the syntactic information in neural network models. To this end, we first construct a constituency lattice structure based on the constituents of a constituency tree. Then, we present two approaches to encoding the constituency lattice using BiLSTM-CRF and BERT as the base models, respectively. We experimented on two benchmark datasets to evaluate the two models, and the results confirm their superiority with respective 3.17 and 1.35 points gained in F1-Measure over the current state of the art. The improvements justify the effectiveness of the constituency lattice for aspect term extraction.

Recently, research works have attempted the joint prediction of scene semantics and optical flow estimation, which demonstrate the mutual improvement between both tasks. Besides, the depth information is also indispensable for the scene understanding, and disparity estimation is necessary for outputting dense depth maps. Such task shares a great similarity with the optical flow estimation since they can all be cast into a problem of capturing the difference at a location of two image frames. However, as far as we know, currently there are few networks for the joint learning of semantic and disparity. Moreover, since deep semantic information and disparity feature maps can learn from each other, we find it unnecessary with two independent encoding modules to separately extract semantic and disparity features. Therefore, we propose a unified multi-tasking architecture DSNet, for the simultaneous estimation of semantic and disparity information. In our model, semantic features, extracted by the encoding module ResNet from the left and right images, are used to obtain the deep disparity features via a novel matching module which performs pixel-to-pixel matching. In addition, we also use the disparity map to perform warp operation on deep features of the right image to deal with the problem of lacking of semantic labels. The effectiveness of our method is demonstrated by extensive experiments.