scholarly journals Aspect Term Extraction with History Attention and Selective Transformation

2018 ◽  
Author(s):  
Xin Li ◽  
Lidong Bing ◽  
Piji Li ◽  
Wai Lam ◽  
Zhimou Yang
Keyword(s):  
State Of The Art ◽  
The Other ◽  
Coordinate Structure ◽  
Selective Transformation ◽  
Term Extraction ◽  
History Information ◽  
Online User Reviews ◽  
Benchmark Datasets ◽  
Input Sentence ◽  
New Framework

Aspect Term Extraction (ATE), a key sub-task in Aspect-Based Sentiment Analysis, aims to extract explicit aspect expressions from online user reviews. We present a new framework for tackling ATE. It can exploit two useful clues, namely opinion summary and aspect detection history. Opinion summary is distilled from the whole input sentence, conditioned on each current token for aspect prediction, and thus the tailor-made summary can help aspect prediction on this token. On the other hand, the aspect detection history information is distilled from the previous aspect predictions, and it can leverage the coordinate structure and tagging schema constraints to upgrade the aspect prediction. Experimental results over four benchmark datasets clearly demonstrate that our framework can outperform all state-of-the-art methods. 

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 Color-Sensitive Person Re-Identification

2019 ◽  
Author(s):  
Guan'an Wang ◽  
Yang Yang ◽  
Jian Cheng ◽  
Jinqiao Wang ◽  
Zengguang Hou
Keyword(s):  
Full Advantage ◽  
State Of The Art ◽  
Color Difference ◽  
The Other ◽  
Semantic Features ◽  
Color Information ◽  
Benchmark Datasets ◽  
Identity Consistency ◽  
High Level ◽  
Sensitive Person

Recent deep Re-ID models mainly focus on learning high-level semantic features, while failing to explicitly explore color information which is one of the most important cues for person Re-ID. In this paper, we propose a novel Color-Sensitive Re-ID to take full advantage of color information. On one hand, we train our model with real and fake images. By using the extra fake images, more color information can be exploited and it can avoid overfitting during training. On the other hand, we also train our model with images of the same person with different colors. By doing so, features can be forced to focus on the color difference in regions. To generate fake images with specified colors, we propose a novel Color Translation GAN (CTGAN) to learn mappings between different clothing colors and preserve identity consistency among the same clothing color. Extensive evaluations on two benchmark datasets show that our approach significantly outperforms state-of-the-art  Re-ID models.

scholarly journals Motion Guided Spatial Attention for Video Captioning

2019 ◽  
Vol 33 ◽  
pp. 8191-8198 ◽  
Author(s):  
Shaoxiang Chen ◽  
Yu-Gang Jiang
Keyword(s):  
Spatial Attention ◽  
Apparent Motion ◽  
State Of The Art ◽  
Human Perception ◽  
The Other ◽  
Motion Information ◽  
Video Captioning ◽  
Video Frames ◽  
Benchmark Datasets ◽  
Rich Information

Sequence-to-sequence models incorporated with attention mechanism have shown promising improvements on video captioning. While there is rich information both inside and between frames, spatial attention is rarely explored and motion information is usually handled by 3D-CNNs as just another modality for fusion. On the other hand, researches about human perception suggest that apparent motion can attract attention. Motivated by this, we aim to learn spatial attention on video frames under the guidance of motion information for caption generation. We present a novel video captioning framework by utilizing Motion Guided Spatial Attention (MGSA). The proposed MGSA exploits the motion between video frames by learning spatial attention from stacked optical flow images with a custom CNN. To further relate the spatial attention maps of video frames, we designed a Gated Attention Recurrent Unit (GARU) to adaptively incorporate previous attention maps. The whole framework can be trained in an end-to-end manner. We evaluate our approach on two benchmark datasets, MSVD and MSR-VTT. The experiments show that our designed model can generate better video representation and state of the art results are obtained under popular evaluation metrics such as BLEU@4, CIDEr, and METEOR.

scholarly journals Ensemble Soft-Margin Softmax Loss for Image Classification

2018 ◽  
Author(s):  
Xiaobo Wang ◽  
Shifeng Zhang ◽  
Zhen Lei ◽  
Si Liu ◽  
Xiaojie Guo ◽  
...  
Keyword(s):  
Image Classification ◽  
State Of The Art ◽  
The Other ◽  
Other Hand ◽  
Soft Margin ◽  
Benchmark Datasets ◽  
The One ◽  
Independence Criterion

Softmax loss is arguably one of the most popular losses to train CNN models for image classification. However, recent works have exposed its limitation on feature discriminability. This paper casts a new viewpoint on the weakness of softmax loss. On the one hand, the CNN features learned using the softmax loss are often inadequately discriminative. We hence introduce a soft-margin softmax function to explicitly encourage the discrmination between different classes. On the other hand, the learned classifier of softmax loss is weak. We propose to assemble multiple these weak classifiers to a strong one, inspired by the recognition that the diversity among weak classifiers is critical to a good ensemble. To achieve the diversity, we adopt the Hilbert-Schmidt Independence Criterion (HSIC). Considering these two aspects in one framework, we design a novel loss, named as Ensemble Soft-Margin Softmax (EM-Softmax). Extensive experiments on benchmark datasets are conducted to show the superiority of our design over the baseline softmax loss and several state-of-the-art alternatives.

Computer Vision and robotics in postal automation

1999 ◽  
Vol 18 (3-4) ◽  
pp. 265-273
Author(s):  
Giovanni B. Garibotto
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Pattern Recognition ◽  
Material Handling ◽  
State Of The Art ◽  
Short Description ◽  
The Other ◽  
Functional Requirements ◽  
Postal Automation ◽  
And Robotics

The paper is intended to provide an overview of advanced robotic technologies within the context of Postal Automation services. The main functional requirements of the application are briefly referred, as well as the state of the art and new emerging solutions. Image Processing and Pattern Recognition have always played a fundamental role in Address Interpretation and Mail sorting and the new challenging objective is now off-line handwritten cursive recognition, in order to be able to handle all kind of addresses in a uniform way. On the other hand, advanced electromechanical and robotic solutions are extremely important to solve the problems of mail storage, transportation and distribution, as well as for material handling and logistics. Finally a short description of new services of Postal Automation is referred, by considering new emerging services of hybrid mail and paper to electronic conversion.

BiLabel-Specific Features for Multi-Label Classification

2021 ◽  
Vol 16 (1) ◽  
pp. 1-23
Author(s):  
Min-Ling Zhang ◽  
Jun-Peng Fang ◽  
Yi-Bo Wang
Keyword(s):  
Predictive Models ◽  
Comparative Studies ◽  
State Of The Art ◽  
Classification Model ◽  
Generation Process ◽  
Prototype Selection ◽  
Class Label ◽  
Benchmark Datasets ◽  
Label Correlations ◽  
Class Labels

In multi-label classification, the task is to induce predictive models which can assign a set of relevant labels for the unseen instance. The strategy of label-specific features has been widely employed in learning from multi-label examples, where the classification model for predicting the relevancy of each class label is induced based on its tailored features rather than the original features. Existing approaches work by generating a group of tailored features for each class label independently, where label correlations are not fully considered in the label-specific features generation process. In this article, we extend existing strategy by proposing a simple yet effective approach based on BiLabel-specific features. Specifically, a group of tailored features is generated for a pair of class labels with heuristic prototype selection and embedding. Thereafter, predictions of classifiers induced by BiLabel-specific features are ensembled to determine the relevancy of each class label for unseen instance. To thoroughly evaluate the BiLabel-specific features strategy, extensive experiments are conducted over a total of 35 benchmark datasets. Comparative studies against state-of-the-art label-specific features techniques clearly validate the superiority of utilizing BiLabel-specific features to yield stronger generalization performance for multi-label classification.

Occupant pre-crash kinematics in rotated seat arrangements

2021 ◽  
pp. 095440702110045
Author(s):  
Alexander Diederich ◽  
Christophe Bastien ◽  
Karthikeyan Ekambaram ◽  
Alexis Wilson
Keyword(s):  
State Of The Art ◽  
The Other ◽  
Human Model ◽  
Multi Objective ◽  
Emergency Braking ◽  
Seating Arrangement ◽  
Current State ◽  
Occupant Comfort ◽  
Occupant Kinematics ◽  
Belt System

The introduction of automated L5 driving technologies will revolutionise the design of vehicle interiors and seating configurations, improving occupant comfort and experience. It is foreseen that pre-crash emergency braking and swerving manoeuvres will affect occupant posture, which could lead to an interaction with a deploying airbag. This research addresses the urgent safety need of defining the occupant’s kinematics envelope during that pre-crash phase, considering rotated seat arrangements and different seatbelt configurations. The research used two different sets of volunteer tests experiencing L5 vehicle manoeuvres, based in the first instance on 22 50th percentile fit males wearing a lap-belt (OM4IS), while the other dataset is based on 87 volunteers with a BMI range of 19 to 67 kg/m2 wearing a 3-point belt (UMTRI). Unique biomechanics kinematics corridors were then defined, as a function of belt configuration and vehicle manoeuvre, to calibrate an Active Human Model (AHM) using a multi-objective optimisation coupled with a Correlation and Analysis (CORA) rating. The research improved the AHM omnidirectional kinematics response over current state of the art in a generic lap-belted environment. The AHM was then tested in a rotated seating arrangement under extreme braking, highlighting that maximum lateral and frontal motions are comparable, independent of the belt system, while the asymmetry of the 3-point belt increased the occupant’s motion towards the seatbelt buckle. It was observed that the frontal occupant kinematics decrease by 200 mm compared to a lap-belted configuration. This improved omnidirectional AHM is the first step towards designing safer future L5 vehicle interiors.

scholarly journals An All-Batch Loss for Constructing Prediction Intervals

2021 ◽  
Vol 11 (4) ◽  
pp. 1728
Author(s):  
Hua Zhong ◽  
Li Xu
Keyword(s):  
Gradient Descent ◽  
State Of The Art ◽  
Prediction Interval ◽  
Feedforward Neural Networks ◽  
Important Research ◽  
Likelihood Principle ◽  
High Quality ◽  
Construction Methods ◽  
Important Research Topic ◽  
Benchmark Datasets

The prediction interval (PI) is an important research topic in reliability analyses and decision support systems. Data size and computation costs are two of the issues which may hamper the construction of PIs. This paper proposes an all-batch (AB) loss function for constructing high quality PIs. Taking the full advantage of the likelihood principle, the proposed loss makes it possible to train PI generation models using the gradient descent (GD) method for both small and large batches of samples. With the structure of dual feedforward neural networks (FNNs), a high-quality PI generation framework is introduced, which can be adapted to a variety of problems including regression analysis. Numerical experiments were conducted on the benchmark datasets; the results show that higher-quality PIs were achieved using the proposed scheme. Its reliability and stability were also verified in comparison with various state-of-the-art PI construction methods.

scholarly journals All-gather Algorithms Resilient to Imbalanced Process Arrival Patterns

2021 ◽  
Vol 18 (4) ◽  
pp. 1-22
Author(s):  
Jerzy Proficz
Keyword(s):  
Experimental Evaluation ◽  
Data Exchange ◽  
State Of The Art ◽  
Monitoring And Evaluation ◽  
The Other ◽  
Early Data ◽  
Cluster Architecture ◽  
Novel Algorithms

Two novel algorithms for the all-gather operation resilient to imbalanced process arrival patterns (PATs) are presented. The first one, Background Disseminated Ring (BDR), is based on the regular parallel ring algorithm often supplied in MPI implementations and exploits an auxiliary background thread for early data exchange from faster processes to accelerate the performed all-gather operation. The other algorithm, Background Sorted Linear synchronized tree with Broadcast (BSLB), is built upon the already existing PAP-aware gather algorithm, that is, Background Sorted Linear Synchronized tree (BSLS), followed by a regular broadcast distributing gathered data to all participating processes. The background of the imbalanced PAP subject is described, along with the PAP monitoring and evaluation topics. An experimental evaluation of the algorithms based on a proposed mini-benchmark is presented. The mini-benchmark was performed over 2,000 times in a typical HPC cluster architecture with homogeneous compute nodes. The obtained results are analyzed according to different PATs, data sizes, and process numbers, showing that the proposed optimization works well for various configurations, is scalable, and can significantly reduce the all-gather elapsed times, in our case, up to factor 1.9 or 47% in comparison with the best state-of-the-art solution.

Towards corpus and model: Hierarchical structured-attention-based features for Indonesian named entity recognition

2021 ◽  
pp. 1-12
Author(s):  
Yingwen Fu ◽  
Nankai Lin ◽  
Xiaotian Lin ◽  
Shengyi Jiang
Keyword(s):  
Language Processing ◽  
State Of The Art ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Language Models ◽  
Neural Models ◽  
Performance Models ◽  
Named Entity ◽  
High Resource ◽  
Benchmark Datasets

Named entity recognition (NER) is fundamental to natural language processing (NLP). Most state-of-the-art researches on NER are based on pre-trained language models (PLMs) or classic neural models. However, these researches are mainly oriented to high-resource languages such as English. While for Indonesian, related resources (both in dataset and technology) are not yet well-developed. Besides, affix is an important word composition for Indonesian language, indicating the essentiality of character and token features for token-wise Indonesian NLP tasks. However, features extracted by currently top-performance models are insufficient. Aiming at Indonesian NER task, in this paper, we build an Indonesian NER dataset (IDNER) comprising over 50 thousand sentences (over 670 thousand tokens) to alleviate the shortage of labeled resources in Indonesian. Furthermore, we construct a hierarchical structured-attention-based model (HSA) for Indonesian NER to extract sequence features from different perspectives. Specifically, we use an enhanced convolutional structure as well as an enhanced attention structure to extract deeper features from characters and tokens. Experimental results show that HSA establishes competitive performance on IDNER and three benchmark datasets.

Sign in / Sign up

Export Citation Format

Share Document