Knowledge-Guided Disentangled Representation Learning for Recommender Systems

In recommender systems, it is essential to understand the underlying factors that affect user-item interaction. Recently, several studies have utilized disentangled representation learning to discover such hidden factors from user-item interaction data, which shows promising results. However, without any external guidance signal, the learned disentangled representations lack clear meanings, and are easy to suffer from the data sparsity issue. In light of these challenges, we study how to leverage knowledge graph (KG) to guide the disentangled representation learning in recommender systems. The purpose for incorporating KG is twofold, making the disentangled representations interpretable and resolving data sparsity issue. However, it is not straightforward to incorporate KG for improving disentangled representations, because KG has very different data characteristics compared with user-item interactions. We propose a novel K nowledge-guided D isentangled R epresentations approach ( KDR ) to utilizing KG to guide the disentangled representation learning in recommender systems. The basic idea, is to first learn more interpretable disentangled dimensions (explicit disentangled representations) based on structural KG, and then align implicit disentangled representations learned from user-item interaction with the explicit disentangled representations. We design a novel alignment strategy based on mutual information maximization. It enables the KG information to guide the implicit disentangled representation learning, and such learned disentangled representations will correspond to semantic information derived from KG. Finally, the fused disentangled representations are optimized to improve the recommendation performance. Extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed model in terms of both performance and interpretability.

Attention Neural Network for Biomedical Word Sense Disambiguation

In order to improve the disambiguation accuracy of biomedical words, this paper proposes a disambiguation method based on the attention neural network. The biomedical word is viewed as the center. Morphology, part of speech, and semantic information from 4 adjacent lexical units are extracted as disambiguation features. The attention layer is used to generate a feature matrix. Average asymmetric convolutional neural networks (Av-ACNN) and bidirectional long short-term memory (Bi-LSTM) networks are utilized to extract features. The softmax function is applied to determine the semantic category of the biomedical word. At the same time, CNN, LSTM, and Bi-LSTM are applied to biomedical WSD. MSH corpus is adopted to optimize CNN, LSTM, Bi-LSTM, and the proposed method and testify their disambiguation performance. Experimental results show that the average disambiguation accuracy of the proposed method is improved compared with CNN, LSTM, and Bi-LSTM. The average disambiguation accuracy of the proposed method achieves 91.38%.

3D Object Recognition and Localization with a Dense LiDAR Scanner

Dense scanning is an effective solution for refined geometrical modeling applications. The previous studies in dense environment modeling mostly focused on data acquisition techniques without emphasizing autonomous target recognition and accurate 3D localization. Therefore, they lacked the capability to output semantic information in the scenes. This article aims to make complementation in this aspect. The critical problems we solved are mainly in two aspects: (1) system calibration to ensure detail-fidelity for the 3D objects with fine structures, (2) fast outlier exclusion to improve 3D boxing accuracy. A lightweight fuzzy neural network is proposed to remove most background outliers, which was proven in experiments to be effective for various objects in different situations. With precise and clean data ensured by the two abovementioned techniques, our system can extract target objects from the original point clouds, and more importantly, accurately estimate their center locations and orientations.

Imprecision, personae, and pragmatic reasoning

Recent work at the interface of semantics and sociolinguistics showed that listeners reason about the semantic/pragmatic properties of linguistic utterances to draw social inferences about the speaker (Acton and Potts 2014; Beltrama 2018; Jeong 2021). These findings raise the question of whether reverse effects exist as well, i.e., whether (and how) social meanings can also impact the interpretation of semantic/pragmatic meanings. Using (im)precision as a case study, we provide experimental evidence that (i) numerals receive stricter interpretations when utteredbyNerdy(vs. Chill) speakers; and that (ii) this effect is stronger for comprehenders who don’t (strongly) identify with the speaker, suggesting that pragmatic reasoning is crucially shaped by social information about both the speaker and the comprehender. These findings suggest that different layers of meanings inform one another in a bi-directional fashion – i.e., semantic information can invite social inferences, and Misocial information can guide meaning interpretation.

Detection of Aerobics Action Based on Convolutional Neural Network

To further improve the accuracy of aerobics action detection, a method of aerobics action detection based on improving multiscale characteristics is proposed. In this method, based on faster R-CNN and aiming at the problems existing in faster R-CNN, the feature pyramid network (FPN) is used to extract aerobics action image features. So, the low-level semantic information in the images can be extracted, and it can be converted into high-resolution deep-level semantic information. Finally, the target detector is constructed by the above-extracted anchor points so as to realize the detection of aerobics action. The results show that the loss function of the neural network is reduced to 0.2 by using the proposed method, and the accuracy of the proposed method can reach 96.5% compared with other methods, which proves the feasibility of this study.

Context-Fused Guidance for Image Captioning Using Sequence-Level Training

Recent image captioning models based on the encoder-decoder framework have achieved remarkable success in humanlike sentence generation. However, an explicit separation between encoder and decoder brings out a disconnection between the image and sentence. It usually leads to a rough image description: the generated caption only contains main instances but neglects additional objects and scenes unexpectedly, which reduces the caption consistency of the image. To address this issue, we proposed an image captioning system within context-fused guidance in this paper. It incorporates regional and global image representation as the compositional visual features to learn the objects and attributes in images. To integrate image-level semantic information, the visual concept is employed. To avoid misleading decoding, a context fusion gate is introduced to calculate the textual context by selectively aggregating the information of visual concept and word embedding. Subsequently, the context-fused image guidance is formulated based on the compositional visual features and textual context. It provides the decoder with informative semantic knowledge. Finally, a captioner with a two-layer LSTM architecture is constructed to generate captions. Moreover, to overcome the exposure bias, we train the proposed model through sequence decision-making. The experiments conducted on the MS COCO dataset show the outstanding performance of our work. The linguistic analysis demonstrates that our model improves the caption consistency of the image.

Multi-Scale Feature Aggregation Network for Water Area Segmentation

Water area segmentation is an important branch of remote sensing image segmentation, but in reality, most water area images have complex and diverse backgrounds. Traditional detection methods cannot accurately identify small tributaries due to incomplete mining and insufficient utilization of semantic information, and the edge information of segmentation is rough. To solve the above problems, we propose a multi-scale feature aggregation network. In order to improve the ability of the network to process boundary information, we design a deep feature extraction module using a multi-scale pyramid to extract features, combined with the designed attention mechanism and strip convolution, extraction of multi-scale deep semantic information and enhancement of spatial and location information. Then, the multi-branch aggregation module is used to interact with different scale features to enhance the positioning information of the pixels. Finally, the two high-performance branches designed in the Feature Fusion Upsample module are used to deeply extract the semantic information of the image, and the deep information is fused with the shallow information generated by the multi-branch module to improve the ability of the network. Global and local features are used to determine the location distribution of each image category. The experimental results show that the accuracy of the segmentation method in this paper is better than that in the previous detection methods, and has important practical significance for the actual water area segmentation.