scholarly journals Multiple Interactive Attention Networks for Aspect-Based Sentiment Classification

2020 ◽  
Vol 10 (6) ◽  
pp. 2052
Author(s):  
Dianyuan Zhang ◽  
Zhenfang Zhu ◽  
Qiang Lu ◽  
Hongli Pei ◽  
Wenqing Wu ◽  
...  
Keyword(s):  
Target Word ◽  
Sentiment Classification ◽  
Experimental Results ◽  
Context Word ◽  
Attention Network ◽  
Attention Networks ◽  
The Core

Aspect-Based (also known as aspect-level) Sentiment Classification (ABSC) aims at determining the sentimental tendency of a particular target in a sentence. With the successful application of the attention network in multiple fields, attention-based ABSC has aroused great interest. However, most of the previous methods are difficult to parallelize, insufficiently obtain, and fuse the interactive information. In this paper, we proposed a Multiple Interactive Attention Network (MIN). First, we used the Bidirectional Encoder Representations from Transformers (BERT) model to pre-process the data. Then, we used the partial transformer to obtain a hidden state in parallel. Finally, we took the target word and the context word as the core to obtain and fuse the interactive information. Experimental results on the different datasets showed that our model was much more effective.

scholarly journals Reinforcement Learning with Self-Attention Networks for Cryptocurrency Trading

2021 ◽  
Vol 11 (16) ◽  
pp. 7377
Author(s):  
Carlos Betancourt ◽  
Wen-Hui Chen
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
Experimental Results ◽  
Financial Assets ◽  
Trading System ◽  
Attention Network ◽  
Attention Networks ◽  
High Frequencies ◽  
Transaction Fees ◽  
Using Data

This work presents an application of self-attention networks for cryptocurrency trading. Cryptocurrencies are extremely volatile and unpredictable. Thus, cryptocurrency trading is challenging and involves higher risks than trading traditional financial assets such as stocks. To overcome the aforementioned problems, we propose a deep reinforcement learning (DRL) approach for cryptocurrency trading. The proposed trading system contains a self-attention network trained using an actor-critic DRL algorithm. Cryptocurrency markets contain hundreds of assets, allowing greater investment diversification, which can be accomplished if all the assets are analyzed against one another. Self-attention networks are suitable for dealing with the problem because the attention mechanism can process long sequences of data and focus on the most relevant parts of the inputs. Transaction fees are also considered in formulating the studied problem. Systems that perform trades in high frequencies cannot overlook this issue, since, after many trades, small fees can add up to significant expenses. To validate the proposed approach, a DRL environment is built using data from an important cryptocurrency market. We test our method against a state-of-the-art baseline in two different experiments. The experimental results show the proposed approach can obtain higher daily profits and has several advantages over existing methods.

scholarly journals Aspect Sentiment Classification with both Word-level and Clause-level Attention Networks

2018 ◽  
Author(s):  
Jingjing Wang ◽  
Jie Li ◽  
Shoushan Li ◽  
Yangyang Kang ◽  
Min Zhang ◽  
...  
Keyword(s):  
Sentiment Analysis ◽  
Sentiment Classification ◽  
Experimental Results ◽  
Hierarchical Network ◽  
Attention Networks ◽  
Word Level ◽  
Sentence Level

Aspect sentiment classification, a challenging task in sentiment analysis, has been attracting more and more attention in recent years. In this paper, we highlight the need for incorporating the importance degrees of both words and clauses inside a sentence and propose a hierarchical network with both word-level and clause-level attentions to aspect sentiment classification. Specifically, we first adopt sentence-level discourse segmentation to segment a sentence into several clauses. Then, we leverage multiple Bi-directional LSTM layers to encode all clauses and propose a word-level attention layer to capture the importance degrees of words in each clause. Third and finally, we leverage another Bi-directional LSTM layer to encode the outputs from the former layers and propose a clause-level attention layer to capture the importance degrees of all the clauses inside a sentence. Experimental results on the laptop and restaurant datasets from SemEval-2015 demonstrate the effectiveness of our proposed approach to aspect sentiment classification.

scholarly journals A Multi-Attention Network for Aspect-Level Sentiment Analysis

2019 ◽  
Vol 11 (7) ◽  
pp. 157 ◽  
Author(s):  
Qiuyue Zhang ◽  
Ran Lu
Keyword(s):  
Neural Networks ◽  
Sentiment Analysis ◽  
Specific Aspect ◽  
Experimental Results ◽  
Sequence Information ◽  
Attention Network ◽  
Attention Networks ◽  
Recent Advances ◽  
Proposed Model ◽  
The Impact

Aspect-level sentiment analysis (ASA) aims at determining the sentiment polarity of specific aspect term with a given sentence. Recent advances in attention mechanisms suggest that attention models are useful in ASA tasks and can help identify focus words. Or combining attention mechanisms with neural networks are also common methods. However, according to the latest research, they often fail to extract text representations efficiently and to achieve interaction between aspect terms and contexts. In order to solve the complete task of ASA, this paper proposes a Multi-Attention Network (MAN) model which adopts several attention networks. This model not only preprocesses data by Bidirectional Encoder Representations from Transformers (BERT), but a number of measures have been taken. First, the MAN model utilizes the partial Transformer after transformation to obtain hidden sequence information. Second, because words in different location have different effects on aspect terms, we introduce location encoding to analyze the impact on distance from ASA tasks, then we obtain the influence of different words with aspect terms through the bidirectional attention network. From the experimental results of three datasets, we could find that the proposed model could achieve consistently superior results.

scholarly journals Interactive Attention Networks for Aspect-Level Sentiment Classification

2017 ◽  
Author(s):  
Dehong Ma ◽  
Sujian Li ◽  
Xiaodong Zhang ◽  
Houfeng Wang
Keyword(s):  
Interactive Learning ◽  
Sentiment Classification ◽  
Experimental Results ◽  
Special Treatment ◽  
Attention Networks ◽  
Specific Target

Aspect-level sentiment classification aims at identifying the sentiment polarity of specific target in its context. Previous approaches have realized the importance of targets in sentiment classification and developed various methods with the goal of precisely modeling thier contexts via generating target-specific representations. However, these studies always ignore the separate modeling of targets. In this paper, we argue that both targets and contexts deserve special treatment and need to be learned their own representations via interactive learning. Then, we propose the interactive attention networks (IAN) to interactively learn attentions in the contexts and targets, and generate the representations for targets and contexts separately. With this design, the IAN model can well represent a target and its collocative context, which is helpful to sentiment classification. Experimental results on SemEval 2014 Datasets demonstrate the effectiveness of our model.

Spatial Social Choice

2019 ◽  
pp. 207-244
Author(s):  
Norman Schofield
Keyword(s):  
United States ◽  
Stochastic Model ◽  
Social Choice ◽  
Spatial Models ◽  
The United States ◽  
Multinomial Logit ◽  
Experimental Results ◽  
The Core ◽  
Voting Game ◽  
Voter Choice

A key concept of social choice is the idea of the Condorcet point or core. For example, consider a voting game with four participants so any three will win. If voters have Euclidean preferences, then the point at the center will be unbeaten. Earlier spatial models of social choice focused on deterministic voter choice. However, it is clear that voter choice is intrinsically stochastic. This chapter employs a stochastic model based on multinomial logit to examine whether parties in electoral competition tend to converge toward the electoral center or respond to activist pressure to adopt more polarized policies. The chapter discusses experimental results of the idea of the core explores empirical analyses of elections in Israel and the United States.

scholarly journals Social exclusion increases the executive function of attention networks

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Huoyin Zhang ◽  
Shiyunmeng Zhang ◽  
Jiachen Lu ◽  
Yi Lei ◽  
Hong Li
Keyword(s):  
Social Exclusion ◽  
Executive Control ◽  
Brain Regions ◽  
Negative Influence ◽  
Future Research ◽  
Research Attention ◽  
Attention Network ◽  
Attention Networks ◽  
The Social ◽  
And Control

AbstractPrevious studies in humans have shown that brain regions activating social exclusion overlap with those related to attention. However, in the context of social exclusion, how does behavioral monitoring affect individual behavior? In this study, we used the Cyberball game to induce the social exclusion effect in a group of participants. To explore the influence of social exclusion on the attention network, we administered the Attention Network Test (ANT) and compared results for the three subsystems of the attention network (orienting, alerting, and executive control) between exclusion (N = 60) and inclusion (N = 60) groups. Compared with the inclusion group, the exclusion group showed shorter overall response time and better executive control performance, but no significant differences in orienting or alerting. The excluded individuals showed a stronger ability to detect and control conflicts. It appears that social exclusion does not always exert a negative influence on individuals. In future research, attention to network can be used as indicators of social exclusion. This may further reveal how social exclusion affects individuals' psychosomatic mechanisms.

A Novel Locality Sensitive K-Means Clustering Algorithm based on Core Clusters

2013 ◽  
Vol 321-324 ◽  
pp. 1939-1942
Author(s):  
Lei Gu
Keyword(s):  
Clustering Algorithm ◽  
Experimental Results ◽  
Clustering Method ◽  
Neighborhood Graph ◽  
The Core ◽  
Random Samples

The locality sensitive k-means clustering method has been presented recently. Although this approach can improve the clustering accuracies, it often gains the unstable clustering results because some random samples are employed for the initial centers. In this paper, an initialization method based on the core clusters is used for the locality sensitive k-means clustering. The core clusters can be formed by constructing the σ-neighborhood graph and their centers are regarded as the initial centers of the locality sensitive k-means clustering. To investigate the effectiveness of our approach, several experiments are done on three datasets. Experimental results show that our proposed method can improve the clustering performance compared to the previous locality sensitive k-means clustering.

Attentional load modulates large-scale functional brain connectivity beyond the core attention networks

NeuroImage ◽  
2015 ◽  
Vol 109 ◽  
pp. 260-272 ◽  
Author(s):  
Dag Alnæs ◽  
Tobias Kaufmann ◽  
Geneviève Richard ◽  
Eugene P. Duff ◽  
Markus H. Sneve ◽  
...  
Keyword(s):  
Large Scale ◽  
Brain Connectivity ◽  
Attention Networks ◽  
Functional Brain ◽  
The Core ◽  
Attentional Load

scholarly journals Expanded Microchannel Heat Exchanger: Finite Difference Modeling

Designs ◽  
2021 ◽  
Vol 5 (4) ◽  
pp. 58
Author(s):  
David Denkenberger ◽  
Joshua M. Pearce ◽  
Michael Brandemuehl ◽  
Mitchell Alverts ◽  
John Zhai
Keyword(s):  
Heat Transfer ◽  
Heat Exchanger ◽  
Finite Difference ◽  
Flow Rate ◽  
Experimental Results ◽  
Low Flow ◽  
Difference Model ◽  
The Core ◽  
Finite Difference Model ◽  
Flow Maldistribution

A finite difference model of a heat exchanger (HX) considered maldistribution, axial conduction, heat leak, and the edge effect, all of which are needed to model a high effectiveness HX. An HX prototype was developed, and channel height data were obtained using a computerized tomography (CT) scan from previous work along with experimental results. This study used the core geometry data to model results with the finite difference model, and compared the modeled and experimental results to help improve the expanded microchannel HX (EMHX) prototype design. The root mean square (RMS) error was 3.8%. Manifold geometries were not put into the model because the data were not available, so impacts of the manifold were investigated by varying the temperature conditions at the inlet and exit of the core. Previous studies have not considered the influence of heat transfer in the manifold on the HX effectiveness when maldistribution is present. With no flow maldistribution, manifold heat transfer increases overall effectiveness roughly as would be expected by the greater heat transfer area in the manifolds. Manifold heat transfer coupled with flow maldistribution for the prototype, however, causes a decrease in the effectiveness at high flow rate, and an increase in effectiveness at low flow rate.

Sign in / Sign up

Export Citation Format

Share Document