scholarly journals Zero-Shot Object Detection with Textual Descriptions

2019 ◽  
Vol 33 ◽  
pp. 8690-8697 ◽  
Author(s):  
Zhihui Li ◽  
Lina Yao ◽  
Xiaoqin Zhang ◽  
Xianzhi Wang ◽  
Salil Kanhere ◽  
...  
Keyword(s):  
Object Detection ◽  
Training Data ◽  
Challenging Problem ◽  
Learning Framework ◽  
Word Level ◽  
Proposed Model ◽  
Real World Applications ◽  
Fair Comparison ◽  
Benchmark Datasets ◽  
Novel Concept

Object detection is important in real-world applications. Existing methods mainly focus on object detection with sufficient labelled training data or zero-shot object detection with only concept names. In this paper, we address the challenging problem of zero-shot object detection with natural language description, which aims to simultaneously detect and recognize novel concept instances with textual descriptions. We propose a novel deep learning framework to jointly learn visual units, visual-unit attention and word-level attention, which are combined to achieve word-proposal affinity by an element-wise multiplication. To the best of our knowledge, this is the first work on zero-shot object detection with textual descriptions. Since there is no directly related work in the literature, we investigate plausible solutions based on existing zero-shot object detection for a fair comparison. We conduct extensive experiments on three challenging benchmark datasets. The extensive experimental results confirm the superiority of the proposed model.

Semi-Supervised Aspect-Based Sentiment Analysis for Case-Related Microblog Reviews Using Case Knowledge Graph Embedding

2021 ◽  
pp. 2050012
Author(s):  
Peilian Zhao ◽  
Cunli Mao ◽  
Zhengtao Yu
Keyword(s):  
Sentiment Analysis ◽  
Domain Knowledge ◽  
Opinion Mining ◽  
Data Augmentation ◽  
Training Data ◽  
Knowledge Graph ◽  
Fine Grained ◽  
Learning Framework ◽  
Proposed Model ◽  
Real World Applications

Aspect-Based Sentiment Analysis (ABSA), a fine-grained task of opinion mining, which aims to extract sentiment of specific target from text, is an important task in many real-world applications, especially in the legal field. Therefore, in this paper, we study the problem of limitation of labeled training data required and ignorance of in-domain knowledge representation for End-to-End Aspect-Based Sentiment Analysis (E2E-ABSA) in legal field. We proposed a new method under deep learning framework, named Semi-ETEKGs, which applied E2E framework using knowledge graph (KG) embedding in legal field after data augmentation (DA). Specifically, we pre-trained the BERT embedding and in-domain KG embedding for unlabeled data and labeled data with case elements after DA, and then we put two embeddings into the E2E framework to classify the polarity of target-entity. Finally, we built a case-related dataset based on a popular benchmark for ABSA to prove the efficiency of Semi-ETEKGs, and experiments on case-related dataset from microblog comments show that our proposed model outperforms the other compared methods significantly.

scholarly journals A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency

2020 ◽  
Vol 34 (05) ◽  
pp. 9098-9105
Author(s):  
Amir Veyseh ◽  
Franck Dernoncourt ◽  
Dejing Dou ◽  
Thien Nguyen
Keyword(s):  
Prior Work ◽  
Semantic Consistency ◽  
Learning Framework ◽  
Local Structures ◽  
Joint Inference ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Sequential Labeling ◽  
Sentence Classification ◽  
Model Features

Definition Extraction (DE) is one of the well-known topics in Information Extraction that aims to identify terms and their corresponding definitions in unstructured texts. This task can be formalized either as a sentence classification task (i.e., containing term-definition pairs or not) or a sequential labeling task (i.e., identifying the boundaries of the terms and definitions). The previous works for DE have only focused on one of the two approaches, failing to model the inter-dependencies between the two tasks. In this work, we propose a novel model for DE that simultaneously performs the two tasks in a single framework to benefit from their inter-dependencies. Our model features deep learning architectures to exploit the global structures of the input sentences as well as the semantic consistencies between the terms and the definitions, thereby improving the quality of the representation vectors for DE. Besides the joint inference between sentence classification and sequential labeling, the proposed model is fundamentally different from the prior work for DE in that the prior work has only employed the local structures of the input sentences (i.e., word-to-word relations), and not yet considered the semantic consistencies between terms and definitions. In order to implement these novel ideas, our model presents a multi-task learning framework that employs graph convolutional neural networks and predicts the dependency paths between the terms and the definitions. We also seek to enforce the consistency between the representations of the terms and definitions both globally (i.e., increasing semantic consistency between the representations of the entire sentences and the terms/definitions) and locally (i.e., promoting the similarity between the representations of the terms and the definitions). The extensive experiments on three benchmark datasets demonstrate the effectiveness of our approach.1

Object Detection using Feature Mining in a Distributed Machine Learning Framework

2017 ◽  
Author(s):  
Arne Ehlers
Keyword(s):  
Machine Learning ◽  
Object Detection ◽  
Training Data ◽  
Visual Object ◽  
Ensemble Classifiers ◽  
Adaptive Boosting ◽  
Learning Framework ◽  
Theory Of Evidence ◽  
Feature Mining ◽  
Distributed Machine Learning

This dissertation addresses the problem of visual object detection based on machine-learned classifiers. A distributed machine learning framework is developed to learn detectors for several object classes creating cascaded ensemble classifiers by the Adaptive Boosting algorithm. Methods are proposed that enhance several components of an object detection framework: At first, the thesis deals with augmenting the training data in order to improve the performance of object detectors learned from sparse training sets. Secondly, feature mining strategies are introduced to create feature sets that are customized to the object class to be detected. Furthermore, a novel class of fractal features is proposed that allows to represent a wide variety of shapes. Thirdly, a method is introduced that models and combines internal confidences and uncertainties of the cascaded detector using Dempster’s theory of evidence in order to increase the quality of the post-processing. ...

scholarly journals Robust Auto-Weighted Multi-View Clustering

2018 ◽  
Author(s):  
Pengzhen Ren ◽  
Yun Xiao ◽  
Pengfei Xu ◽  
Jun Guo ◽  
Xiaojiang Chen ◽  
...  
Keyword(s):  
Cluster Structure ◽  
Vital Role ◽  
Connected Components ◽  
Multiple Views ◽  
Challenging Problem ◽  
Complementary Information ◽  
Proposed Model ◽  
Real World Applications ◽  
Data Points ◽  
Optimal Graph

Multi-view clustering has played a vital role in real-world applications. It aims to cluster the data points into different groups by exploring complementary information of multi-view. A major challenge of this problem is how to learn the explicit cluster structure with multiple views when there is considerable noise. To solve this challenging problem, we propose a novel Robust Auto-weighted Multi-view Clustering (RAMC), which aims to learn an optimal graph with exactly k connected components, where k is the number of clusters. ℓ1-norm is employed for robustness of the proposed algorithm. We have validated this in the later experiment. The new graph learned by the proposed model approximates the original graphs of each individual view but maintains an explicit cluster structure. With this optimal graph, we can immediately achieve the clustering results without any further post-processing. We conduct extensive experiments to confirm the superiority and robustness of the proposed algorithm.

scholarly journals Few-Shot Image and Sentence Matching via Gated Visual-Semantic Embedding

2019 ◽  
Vol 33 ◽  
pp. 8489-8496 ◽  
Author(s):  
Yan Huang ◽  
Yang Long ◽  
Liang Wang
Keyword(s):  
Performance Improvement ◽  
State Of The Art ◽  
Similarity Metrics ◽  
Relative Importance ◽  
Challenging Problem ◽  
Semantic Embedding ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
The Common ◽  
Sentence Matching

Although image and sentence matching has been widely studied, its intrinsic few-shot problem is commonly ignored, which has become a bottleneck for further performance improvement. In this work, we focus on this challenging problem of few-shot image and sentence matching, and propose a Gated Visual-Semantic Embedding (GVSE) model to deal with it. The model consists of three corporative modules in terms of uncommon VSE, common VSE, and gated metric fusion. The uncommon VSE exploits external auxiliary resources to extract generic features for representing uncommon instances and words in images and sentences, and then integrates them by modeling their semantic relation to obtain global representations for association analysis. To better model other common instances and words in rest content of images and sentences, the common VSE learns their discriminative representations directly from scratch. After obtaining two similarity metrics from the two VSE modules with different advantages, the gated metric fusion module adaptively fuses them by automatically balancing their relative importance. Based on the fused metric, we perform extensive experiments in terms of few-shot and conventional image and sentence matching, and demonstrate the effectiveness of the proposed model by achieving the state-of-the-art results on two public benchmark datasets.

scholarly journals A multitask transfer learning framework for novel virus-human protein interactions

2021 ◽  
Author(s):  
Ngan Thi Dong ◽  
Megha Khosla
Keyword(s):  
Protein Interactions ◽  
Viral Proteins ◽  
Underlying Mechanism ◽  
Training Data ◽  
Interaction Patterns ◽  
Learning Problem ◽  
Learning Framework ◽  
Human Proteins ◽  
Benchmark Datasets ◽  
Novel Virus

AbstractUnderstanding the interaction patterns between a particular virus and human proteins plays a crucial role in unveiling the underlying mechanism of viral infection. This could further help in developing treatments of viral diseases. The main issues in tackling it as a machine learning problem is the scarcity of training data as well input information of the viral proteins. We overcome these limitations by exploiting powerful statistical protein representations derived from a corpus of around 24 Million protein sequences in a multi task framework. Our experiments on 7 varied benchmark datasets support the superiority of our approach.

scholarly journals Adaptive Semi-Supervised Learning with Discriminative Least Squares Regression

2017 ◽  
Author(s):  
Minnan Luo ◽  
Lingling Zhang ◽  
Feiping Nie ◽  
Xiaojun Chang ◽  
Buyue Qian ◽  
...  
Keyword(s):  
Least Squares ◽  
Supervised Learning ◽  
Closed Form Solution ◽  
Form Solution ◽  
Training Data ◽  
Least Squares Regression ◽  
Adaptive Parameter ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Multi Class Classification

Semi-supervised learning plays a significant role in multi-class classification, where a small number of labeled data are more deterministic while substantial unlabeled data might cause large uncertainties and potential threats. In this paper, we distinguish the label fitting of labeled and unlabeled training data through a probabilistic vector with an adaptive parameter, which always ensures the significant importance of labeled data and characterizes the contribution of unlabeled instance according to its uncertainty. Instead of using traditional least squares regression (LSR) for classification, we develop a new discriminative LSR by equipping each label with an adjustment vector. This strategy avoids incorrect penalization on samples that are far away from the boundary and simultaneously facilitates multi-class classification by enlarging the geometrical distance of instances belonging to different classes. An efficient alternative algorithm is exploited to solve the proposed model with closed form solution for each updating rule. We also analyze the convergence and complexity of the proposed algorithm theoretically. Experimental results on several benchmark datasets demonstrate the effectiveness and superiority of the proposed model for multi-class classification tasks.

scholarly journals Bayesian Learning of Latent Representations of Language Structures

2019 ◽  
Vol 45 (2) ◽  
pp. 199-228
Author(s):  
Yugo Murawaki
Keyword(s):  
Latent Variables ◽  
Bayesian Learning ◽  
Missing Values ◽  
Representation Learning ◽  
Model Parameters ◽  
Challenging Problem ◽  
Learning Framework ◽  
Proposed Model ◽  
Latent Space ◽  
Latent Representations

We borrow the concept of representation learning from deep learning research, and we argue that the quest for Greenbergian implicational universals can be reformulated as the learning of good latent representations of languages, or sequences of surface typological features. By projecting languages into latent representations and performing inference in the latent space, we can handle complex dependencies among features in an implicit manner. The most challenging problem in turning the idea into a concrete computational model is the alarmingly large number of missing values in existing typological databases. To address this problem, we keep the number of model parameters relatively small to avoid overfitting, adopt the Bayesian learning framework for its robustness, and exploit phylogenetically and/or spatially related languages as additional clues. Experiments show that the proposed model recovers missing values more accurately than others and that some latent variables exhibit phylogenetic and spatial signals comparable to those of surface features.

Decision making based on intuitionistic fuzzy preference relations with additive approximate consistency

2020 ◽  
Vol 39 (3) ◽  
pp. 4041-4058
Author(s):  
Fang Liu ◽  
Xu Tan ◽  
Hui Yang ◽  
Hui Zhao
Keyword(s):  
Decision Making ◽  
Decision Makers ◽  
Real Interval ◽  
Preference Relations ◽  
Intuitionistic Fuzzy ◽  
Proposed Model ◽  
Fuzzy Preference Relations ◽  
Novel Concept ◽  
Fuzzy Weights ◽  
Fuzzy Preference

Intuitionistic fuzzy preference relations (IFPRs) have the natural ability to reflect the positive, the negative and the non-determinative judgements of decision makers. A decision making model is proposed by considering the inherent property of IFPRs in this study, where the main novelty comes with the introduction of the concept of additive approximate consistency. First, the consistency definitions of IFPRs are reviewed and the underlying ideas are analyzed. Second, by considering the allocation of the non-determinacy degree of decision makers’ opinions, the novel concept of approximate consistency for IFPRs is proposed. Then the additive approximate consistency of IFPRs is defined and the properties are studied. Third, the priorities of alternatives are derived from IFPRs with additive approximate consistency by considering the effects of the permutations of alternatives and the allocation of the non-determinacy degree. The rankings of alternatives based on real, interval and intuitionistic fuzzy weights are investigated, respectively. Finally, some comparisons are reported by carrying out numerical examples to show the novelty and advantage of the proposed model. It is found that the proposed model can offer various decision schemes due to the allocation of the non-determinacy degree of IFPRs.

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

2018 ◽  
Author(s):  
Roman Zubatyuk ◽  
Justin S. Smith ◽  
Jerzy Leszczynski ◽  
Olexandr Isayev
Keyword(s):  
Neural Network ◽  
Molecular System ◽  
Computational Cost ◽  
Chemical Properties ◽  
The State ◽  
Molecular Properties ◽  
Training Data ◽  
Dft Methods ◽  
Benchmark Datasets ◽  
Quantum Phenomena

<p>Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena. Here we present AIMNet, a modular and chemically inspired deep neural network potential. We used AIMNet with multitarget training to learn multiple modalities of the state of the atom in a molecular system. The resulting model shows on several benchmark datasets the state-of-the-art accuracy, comparable to the results of orders of magnitude more expensive DFT methods. It can simultaneously predict several atomic and molecular properties without an increase in computational cost. With AIMNet we show a new dimension of transferability: the ability to learn new targets utilizing multimodal information from previous training. The model can learn implicit solvation energy (like SMD) utilizing only a fraction of original training data, and archive MAD error of 1.1 kcal/mol compared to experimental solvation free energies in MNSol database.</p>

Sign in / Sign up

Export Citation Format

Share Document