다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

비만아 부모의 돌봄 경험: q 방법론

A review on the attention mechanism of deep learning

Bidirectional LSTM with attention mechanism and convolutional layer for text classification

Emotion cause analysis has been a key topic in natural language processing. Existing methods ignore the contexts around the emotion word which can provide an emotion cause clue. Meanwhile, the clauses in a document play different roles on stimulating a certain emotion, depending on their content relevance. Therefore, we propose a co-attention neural network model for emotion cause analysis with emotional context awareness. The method encodes the clauses with a co-attention based bi-directional long short-term memory into high-level input representations, which are further fed into a convolutional layer for emotion cause analysis. Experimental results show that our approach outperforms the state-of-the-art baseline methods.

A Co-Attention Neural Network Model for Emotion Cause Analysis with Emotional Context Awareness

Emotion cause analysis has elicited wide interest in both academia and industry, and aims to identify the reasons behind certain emotions expressed in text. Most of the current studies on emotion cause analysis do not consider two types of information: i) the context of the emotional word, which can provide rich emotional details, and ii) the interaction between the candidate clause and the emotional clause (containing the emotional word). The above information is able to provide important clues in emotion cause analysis. In this paper, we propose a multi-attention-based neural network model to address this issue. First, our model encodes the clause via bidirectional long short-term memory, which can incorporate the contextual information of the word. Second, a multi-attention mechanism is designed to capture the mutual influences between the emotion clause and each candidate clause, and then generate the representations for the above two clauses separately. With this design, our model creates better-distributed representations of the emotion expressions and clauses. Finally, these representations are fed into a convolutional neural network to model the emotion cause clause. The experimental results show that our proposed approach outperforms the state-of-the-art baseline methods by a significant margin.

Context-aware emotion cause analysis with multi-attention-based neural network

Compared with single-modal content, multimodal data can express users’ feelings and sentiments more vividly and interestingly. Therefore, multimodal sentiment analysis has become a popular research topic. However, most existing methods either learn modal sentiment feature independently, without considering their correlations, or they simply integrate multimodal features. In addition, most publicly available multimodal datasets are labeled by sentiment polarities, while the emotions expressed by users are specific. Based on this observation, in this paper, we build a large-scale image-text emotion dataset (i.e., labeled by different emotions), called TumEmo, with more than 190,000 instances from Tumblr.1 We further propose a novel multimodal emotion analysis model based on the Multi-view Attentional Network (MVAN), which utilizes a memory network that is continually updated to obtain the deep semantic features of image-text. The model includes three stages: feature mapping, interactive learning, and feature fusion. In the feature mapping stage, we leverage image features from an object viewpoint and a scene viewpoint to capture effective information for multimodal emotion analysis. Then, an interactive learning mechanism is adopted that uses the memory network; this mechanism extracts single-modal emotion features and interactively models the cross-view dependencies between the image and text. In the feature fusion stage, multiple features are deeply fused using a multilayer perceptron and a stacking-pooling module. The experimental results on the MVSA-Single, MVSA-Multiple, and TumEmo datasets show that the proposed MVAN outperforms strong baseline models by large margins.

Image-Text Multimodal Emotion Classification via Multi-View Attentional Network

Recently, analyzing people’s sentiments in microblogs has attracted more and more attentions from both academic and industrial communities. The traditional methods usually treat the sentiment analysis as a kind of single-label supervised learning problem that classifies the microblog according to sentiment orientation or single-labeled emotion. However, in fact multiple fine-grained emotions may be coexisting in just one tweet or even one sentence of the microblog. In this paper, we regard the emotion detection in microblogs as a multi-label classification problem. We leverage the skip-gram language model to learn distributed word representations as input features, and utilize a Convolutional Neural Network (CNN) based method to solve multi-label emotion classification problem in the Chinese microblog sentences without any manually designed features. Extensive experiments are conducted on two public short text datasets. The experimental results demonstrate that the proposed method outperforms strong baselines by a large margin and achieves excellent performance in terms of multi-label classification metrics.

Multi-label Chinese Microblog Emotion Classification via Convolutional Neural Network

With the growing popularity of multimodal data on the Web, cross-modal retrieval on large-scale multimedia databases has become an important research topic. Cross-modal retrieval methods based on hashing assume that there is a latent space shared by multimodal features. To model the relationship among heterogeneous data, most existing methods embed the data into a joint abstraction space by linear projections. However, these approaches are sensitive to noise in the data and are unable to make use of unlabeled data and multimodal data with missing values in real-world applications. To address these challenges, we proposed a novel multimodal deep-learning-based hash (MDLH) algorithm. In particular, MDLH uses a deep neural network to encode heterogeneous features into a compact common representation and learns the hash functions based on the common representation. The parameters of the whole model are fine-tuned in a supervised training stage. Experiments on two standard datasets show that the method achieves more effective results than other methods in cross-modal retrieval.

Yifei Zhang

Papers

A Co-Attention Neural Network Model for Emotion Cause Analysis with Emotional Context Awareness

Context-aware emotion cause analysis with multi-attention-based neural network

Image-Text Multimodal Emotion Classification via Multi-View Attentional Network

Multi-label Chinese Microblog Emotion Classification via Convolutional Neural Network

A novel cross-modal hashing algorithm based on multimodal deep learning