scholarly journals Capturing Sentence Relations for Answer Sentence Selection with Multi-Perspective Graph Encoding

2020 ◽  
Vol 34 (05) ◽  
pp. 9032-9039
Author(s):  
Zhixing Tian ◽  
Yuanzhe Zhang ◽  
Xinwei Feng ◽  
Wenbin Jiang ◽  
Yajuan Lyu ◽  
...  
Keyword(s):  
State Of The Art ◽  
The State ◽  
Selection Task ◽  
Multiple Perspectives ◽  
Selection Models ◽  
Proposed Model ◽  
Adversarial Examples ◽  
Overall Performance ◽  
Traditional Representation

This paper focuses on the answer sentence selection task. Unlike previous work, which only models the relation between the question and each candidate sentence, we propose Multi-Perspective Graph Encoder (MPGE) to take the relations among the candidate sentences into account and capture the relations from multiple perspectives. By utilizing MPGE as a module, we construct two answer sentence selection models which are based on traditional representation and pre-trained representation, respectively. We conduct extensive experiments on two datasets, WikiQA and SQuAD. The results show that the proposed MPGE is effective for both types of representation. Moreover, the overall performance of our proposed model surpasses the state-of-the-art on both datasets. Additionally, we further validate the robustness of our method by the adversarial examples of AddSent and AddOneSent.

Feature Selection of Interval Valued Data Through Interval K-Means Clustering

2017 ◽  
Vol 7 (2) ◽  
pp. 64-80 ◽  
Author(s):  
D. S. Guru ◽  
N. Vinay Kumar ◽  
Mahamad Suhil
Keyword(s):  
Feature Selection ◽  
Comparative Analysis ◽  
State Of The Art ◽  
The State ◽  
Selection Model ◽  
Selection Models ◽  
Feature Clustering ◽  
Proposed Model ◽  
Interval Valued ◽  
Selection Of

This paper introduces a novel feature selection model for supervised interval valued data based on interval K-Means clustering. The proposed model explores two kinds of feature selection through feature clustering viz., class independent feature selection and class dependent feature selection. The former one clusters the features spread across all the samples belonging to all the classes, whereas the latter one clusters the features spread across only the samples belonging to the respective classes. Both feature selection models are demonstrated to explore the generosity of clustering in selecting the interval valued features. For clustering, the kernel of the K-means clustering has been altered to operate on interval valued data. For experimentation purpose four standard benchmarking datasets and three symbolic classifiers have been used. To corroborate the effectiveness of the proposed model, a comparative analysis against the state-of-the-art models is given and results show the superiority of the proposed model.

scholarly journals Appearance and Motion Enhancement for Video-Based Person Re-Identification

2020 ◽  
Vol 34 (07) ◽  
pp. 11394-11401
Author(s):  
Shuzhao Li ◽  
Huimin Yu ◽  
Haoji Hu
Keyword(s):  
Semantic Information ◽  
State Of The Art ◽  
Complex Model ◽  
The State ◽  
Final Model ◽  
Backbone Network ◽  
Proposed Model ◽  
Art Performance ◽  
Attribute Recognition

In this paper, we propose an Appearance and Motion Enhancement Model (AMEM) for video-based person re-identification to enrich the two kinds of information contained in the backbone network in a more interpretable way. Concretely, human attribute recognition under the supervision of pseudo labels is exploited in an Appearance Enhancement Module (AEM) to help enrich the appearance and semantic information. A Motion Enhancement Module (MEM) is designed to capture the identity-discriminative walking patterns through predicting future frames. Despite a complex model with several auxiliary modules during training, only the backbone model plus two small branches are kept for similarity evaluation which constitute a simple but effective final model. Extensive experiments conducted on three popular video-based person ReID benchmarks demonstrate the effectiveness of our proposed model and the state-of-the-art performance compared with existing methods.

scholarly journals Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning

2019 ◽  
Vol 33 ◽  
pp. 6722-6729 ◽  
Author(s):  
Ziming Li ◽  
Julia Kiseleva ◽  
Maarten De Rijke
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
The State ◽  
Experimental Results ◽  
Imitation Learning ◽  
Local Optimum ◽  
Inverse Reinforcement Learning ◽  
High Quality ◽  
Overall Performance

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to fall into a local optimum or to produce nonsense replies. To alleviate the first problem, we first extend a recently proposed adversarial dialogue generation method to an adversarial imitation learning solution. Then, in the framework of adversarial inverse reinforcement learning, we propose a new reward model for dialogue generation that can provide a more accurate and precise reward signal for generator training. We evaluate the performance of the resulting model with automatic metrics and human evaluations in two annotation settings. Our experimental results demonstrate that our model can generate more high-quality responses and achieve higher overall performance than the state-of-the-art.

scholarly journals Bilateral Multi-Perspective Matching for Natural Language Sentences

2017 ◽  
Author(s):  
Zhiguo Wang ◽  
Wael Hamza ◽  
Radu Florian
Keyword(s):  
Natural Language ◽  
State Of The Art ◽  
The State ◽  
Experimental Results ◽  
The Other ◽  
Multiple Perspectives ◽  
Time Step ◽  
Benchmark Datasets ◽  
Sentence Matching ◽  
Fully Connected

Natural language sentence matching is a fundamental technology for a variety of tasks. Previous approaches either match sentences from a single direction or only apply single granular (word-by-word or sentence-by-sentence) matching. In this work, we propose a bilateral multi-perspective matching (BiMPM) model. Given two sentences P and Q, our model first encodes them with a BiLSTM encoder. Next, we match the two encoded sentences in two directions P against Q and P against Q. In each matching direction, each time step of one sentence is matched against all time-steps of the other sentence from multiple perspectives. Then, another BiLSTM layer is utilized to aggregate the matching results into a fix-length matching vector. Finally, based on the matching vector, a decision is made through a fully connected layer. We evaluate our model on three tasks: paraphrase identification, natural language inference and answer sentence selection. Experimental results on standard benchmark datasets show that our model achieves the state-of-the-art performance on all tasks.

scholarly journals Spoofing Speaker Verification System by Adversarial Examples Leveraging the Generalized Speaker Difference

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Hongwei Luo ◽  
Yijie Shen ◽  
Feng Lin ◽  
Guoai Xu
Keyword(s):  
Neural Networks ◽  
Loss Function ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Speaker Verification ◽  
Signal To Noise Ratio ◽  
The State ◽  
Verification System ◽  
Adversarial Examples ◽  
Human Hearing

Speaker verification system has gained great popularity in recent years, especially with the development of deep neural networks and Internet of Things. However, the security of speaker verification system based on deep neural networks has not been well investigated. In this paper, we propose an attack to spoof the state-of-the-art speaker verification system based on generalized end-to-end (GE2E) loss function for misclassifying illegal users into the authentic user. Specifically, we design a novel loss function to deploy a generator for generating effective adversarial examples with slight perturbation and then spoof the system with these adversarial examples to achieve our goals. The success rate of our attack can reach 82% when cosine similarity is adopted to deploy the deep-learning-based speaker verification system. Beyond that, our experiments also reported the signal-to-noise ratio at 76 dB, which proves that our attack has higher imperceptibility than previous works. In summary, the results show that our attack not only can spoof the state-of-the-art neural-network-based speaker verification system but also more importantly has the ability to hide from human hearing or machine discrimination.

scholarly journals Depthwise Convolution Is All You Need for Learning Multiple Visual Domains

2019 ◽  
Vol 33 ◽  
pp. 8368-8375 ◽  
Author(s):  
Yunhui Guo ◽  
Yandong Li ◽  
Liqiang Wang ◽  
Tajana Rosing
Keyword(s):  
State Of The Art ◽  
The State ◽  
Spatial Correlations ◽  
Single Model ◽  
Domain Specific ◽  
Gating Mechanism ◽  
Proposed Model ◽  
Domain Learning ◽  
Domain Models ◽  
Universal Structure

There is a growing interest in designing models that can deal with images from different visual domains. If there exists a universal structure in different visual domains that can be captured via a common parameterization, then we can use a single model for all domains rather than one model per domain. A model aware of the relationships between different domains can also be trained to work on new domains with less resources. However, to identify the reusable structure in a model is not easy. In this paper, we propose a multi-domain learning architecture based on depthwise separable convolution. The proposed approach is based on the assumption that images from different domains share cross-channel correlations but have domain-specific spatial correlations. The proposed model is compact and has minimal overhead when being applied to new domains. Additionally, we introduce a gating mechanism to promote soft sharing between different domains. We evaluate our approach on Visual Decathlon Challenge, a benchmark for testing the ability of multi-domain models. The experiments show that our approach can achieve the highest score while only requiring 50% of the parameters compared with the state-of-the-art approaches.

scholarly journals Improving the Quantification of DNA Sequences Using Evolutionary Information Based on Deep Learning

Cells ◽  
2019 ◽  
Vol 8 (12) ◽  
pp. 1635 ◽  
Author(s):  
Hilal Tayara ◽  
Kil To Chong
Keyword(s):  
Dna Sequences ◽  
Multiple Scales ◽  
State Of The Art ◽  
Characteristic Curve ◽  
The State ◽  
Evolutionary Information ◽  
Functional Variants ◽  
Proposed Model ◽  
Precision Recall Curve

It is known that over 98% of the human genome is non-coding, and 93% of disease associated variants are located in these regions. Therefore, understanding the function of these regions is important. However, this task is challenging as most of these regions are not well understood in terms of their functions. In this paper, we introduce a novel computational model based on deep neural networks, called DQDNN, for quantifying the function of non-coding DNA regions. This model combines convolution layers for capturing regularity motifs at multiple scales and recurrent layers for capturing long term dependencies between the captured motifs. In addition, we show that integrating evolutionary information with raw genomic sequences improves the performance of the predictor significantly. The proposed model outperforms the state-of-the-art ones using raw genomics sequences only and also by integrating evolutionary information with raw genomics sequences. More specifically, the proposed model improves 96.9% and 98% of the targets in terms of area under the receiver operating characteristic curve and the precision-recall curve, respectively. In addition, the proposed model improved the prioritization of functional variants of expression quantitative trait loci (eQTLs) compared with the state-of-the-art models.

scholarly journals Convolver Design and Convolve-Accumulate Unit Design for Low-Power Edge Computing

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5081
Author(s):  
Hsu-Yu Kao ◽  
Xin-Jia Chen ◽  
Shih-Hsu Huang
Keyword(s):  
Power Consumption ◽  
Low Power ◽  
State Of The Art ◽  
Clock Cycle ◽  
The State ◽  
Edge Computing ◽  
Convolution Operation ◽  
Product Matrix ◽  
Unit Design ◽  
Overall Performance

Convolution operations have a significant influence on the overall performance of a convolutional neural network, especially in edge-computing hardware design. In this paper, we propose a low-power signed convolver hardware architecture that is well suited for low-power edge computing. The basic idea of the proposed convolver design is to combine all multipliers’ final additions and their corresponding adder tree to form a partial product matrix (PPM) and then to use the reduction tree algorithm to reduce this PPM. As a result, compared with the state-of-the-art approach, our convolver design not only saves a lot of carry propagation adders but also saves one clock cycle per convolution operation. Moreover, the proposed convolver design can be adapted for different dataflows (including input stationary dataflow, weight stationary dataflow, and output stationary dataflow). According to dataflows, two types of convolve-accumulate units are proposed to perform the accumulation of convolution results. The results show that, compared with the state-of-the-art approach, the proposed convolver design can save 15.6% power consumption. Furthermore, compared with the state-of-the-art approach, on average, the proposed convolve-accumulate units can reduce 15.7% power consumption.

scholarly journals M[eye]cro

2021 ◽  
Vol 5 (EICS) ◽  
pp. 1-22
Author(s):  
Jérémy Wambecke ◽  
Alix Goguey ◽  
Laurence Nigay ◽  
Lauren Dargent ◽  
Daniel Hauret ◽  
...  
Keyword(s):  
State Of The Art ◽  
Eye Gaze ◽  
The State ◽  
Controlled Experiment ◽  
Selection Task ◽  
Interaction Technique ◽  
Time Performance ◽  
Free Interaction

We present M[eye]cro an interaction technique to select on-screen objects and navigate menus through the synergistic use of eye-gaze and thumb-to-finger microgestures. Thumb-to-finger microgestures are gestures performed with the thumb of a hand onto the fingers of the same hand. The active body of research on microgestures highlights expected properties including speed, availability and eye-free interaction. Such properties make microgestures a good candidate for multitasking. However, while praised, the state-of-the-art hypothesis stating that microgestures could be beneficial for multitasking has never been quantitatively verified. We study and compare M[eye]cro to a baseline, i.e., a technique based on physical controllers, in a cockpit-based context. This context allows us to design a controlled experiment involving multitasking with low- and high-priority tasks in parallel. Our results show that performances of the two techniques are similar when participants only perform the selection task. However, M[eye]cro tends to yield better time performance when participants additionally need to treat high-priority tasks in parallel. Results also show that M[eye]cro induces less fatigue and is mostly preferred.

Sign in / Sign up

Export Citation Format

Share Document