scholarly journals A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots

2019 ◽  
Author(s):  
Xueliang Zhao ◽  
Chongyang Tao ◽  
Wei Wu ◽  
Can Xu ◽  
Dongyan Zhao ◽  
...  
Keyword(s):  
Response Selection ◽  
State Of The Art ◽  
Empirical Studies ◽  
Data Sets ◽  
Matching Network ◽  
Public Data ◽  
Art Methods ◽  
Hierarchical Interaction ◽  
Different Parts

We present a document-grounded matching network (DGMN) for response selection that can power a knowledge-aware retrieval-based chatbot system. The challenges of building such a model lie in how to ground conversation contexts with background documents and how to recognize important information in the documents for matching. To overcome the challenges, DGMN fuses information in a document and a context into representations of each other, and dynamically determines if grounding is necessary and importance of different parts of the document and the context through hierarchical interaction with a response at the matching step. Empirical studies on two public data sets indicate that DGMN can significantly improve upon state-of-the-art methods and at the same time enjoys good interpretability.

MULFE: Multi-Label Learning via Label-Specific Feature Space Ensemble

2021 ◽  
Vol 16 (1) ◽  
pp. 1-24
Author(s):  
Yaojin Lin ◽  
Qinghua Hu ◽  
Jinghua Liu ◽  
Xingquan Zhu ◽  
Xindong Wu
Keyword(s):  
Empirical Studies ◽  
Feature Space ◽  
Training Data ◽  
Data Sets ◽  
Learning Framework ◽  
Feature Spaces ◽  
Public Data ◽  
Margin Distribution ◽  
Label Correlations ◽  
Label Correlation

In multi-label learning, label correlations commonly exist in the data. Such correlation not only provides useful information, but also imposes significant challenges for multi-label learning. Recently, label-specific feature embedding has been proposed to explore label-specific features from the training data, and uses feature highly customized to the multi-label set for learning. While such feature embedding methods have demonstrated good performance, the creation of the feature embedding space is only based on a single label, without considering label correlations in the data. In this article, we propose to combine multiple label-specific feature spaces, using label correlation, for multi-label learning. The proposed algorithm, mu lti- l abel-specific f eature space e nsemble (MULFE), takes consideration label-specific features, label correlation, and weighted ensemble principle to form a learning framework. By conducting clustering analysis on each label’s negative and positive instances, MULFE first creates features customized to each label. After that, MULFE utilizes the label correlation to optimize the margin distribution of the base classifiers which are induced by the related label-specific feature spaces. By combining multiple label-specific features, label correlation based weighting, and ensemble learning, MULFE achieves maximum margin multi-label classification goal through the underlying optimization framework. Empirical studies on 10 public data sets manifest the effectiveness of MULFE.

scholarly journals 3D Convolutional Neural Networks for Remote Pulse Rate Measurement and Mapping from Facial Video

2019 ◽  
Vol 9 (20) ◽  
pp. 4364 ◽  
Author(s):  
Frédéric Bousefsaf ◽  
Alain Pruski ◽  
Choubeila Maaoui
Keyword(s):  
Pulse Rate ◽  
State Of The Art ◽  
Synthetic Data ◽  
Ground Truth ◽  
Large Set ◽  
Training Procedure ◽  
Rate Measurement ◽  
3D Network ◽  
Public Data ◽  
Art Methods

Remote pulse rate measurement from facial video has gained particular attention over the last few years. Research exhibits significant advancements and demonstrates that common video cameras correspond to reliable devices that can be employed to measure a large set of biomedical parameters without any contact with the subject. A new framework for measuring and mapping pulse rate from video is presented in this pilot study. The method, which relies on convolutional 3D networks, is fully automatic and does not require any special image preprocessing. In addition, the network ensures concurrent mapping by producing a prediction for each local group of pixels. A particular training procedure that employs only synthetic data is proposed. Preliminary results demonstrate that this convolutional 3D network can effectively extract pulse rate from video without the need for any processing of frames. The trained model was compared with other state-of-the-art methods on public data. Results exhibit significant agreement between estimated and ground-truth measurements: the root mean square error computed from pulse rate values assessed with the convolutional 3D network is equal to 8.64 bpm, which is superior to 10 bpm for the other state-of-the-art methods. The robustness of the method to natural motion and increases in performance correspond to the two main avenues that will be considered in future works.

Automatic fight detection in surveillance videos

2017 ◽  
Vol 13 (2) ◽  
pp. 130-156 ◽  
Author(s):  
Eugene Yujun Fu ◽  
Hong Va Leong ◽  
Grace Ngai ◽  
Stephen C.F. Chan
Keyword(s):  
Social Interaction ◽  
Signal Analysis ◽  
State Of The Art ◽  
The State ◽  
Data Sets ◽  
Bag Of Words ◽  
Content Type ◽  
Surveillance Videos ◽  
Motion Signal ◽  
Public Data

Purpose Social signal processing under affective computing aims at recognizing and extracting useful human social interaction patterns. Fight is a common social interaction in real life. A fight detection system finds wide applications. This paper aims to detect fights in a natural and low-cost manner. Design/methodology/approach Research works on fight detection are often based on visual features, demanding substantive computation and good video quality. In this paper, the authors propose an approach to detect fight events through motion analysis. Most existing works evaluated their algorithms on public data sets manifesting simulated fights, where the fights are acted out by actors. To evaluate real fights, the authors collected videos involving real fights to form a data set. Based on the two types of data sets, the authors evaluated the performance of their motion signal analysis algorithm, which was then compared with the state-of-the-art approach based on MoSIFT descriptors with Bag-of-Words mechanism, and basic motion signal analysis with Bag-of-Words. Findings The experimental results indicate that the proposed approach accurately detects fights in real scenarios and performs better than the MoSIFT approach. Originality/value By collecting and annotating real surveillance videos containing real fight events and augmenting with well-known data sets, the authors proposed, implemented and evaluated a low computation approach, comparing it with the state-of-the-art approach. The authors uncovered some fundamental differences between real and simulated fights and initiated a new study in discriminating real against simulated fight events, with very good performance.

scholarly journals A Sequential Matching Framework for Multi-Turn Response Selection in Retrieval-Based Chatbots

2019 ◽  
Vol 45 (1) ◽  
pp. 163-197 ◽  
Author(s):  
Yu Wu ◽  
Wei Wu ◽  
Chen Xing ◽  
Can Xu ◽  
Zhoujun Li ◽  
...  
Keyword(s):  
Response Selection ◽  
Data Sets ◽  
Unified Framework ◽  
Convolutional Network ◽  
Matching Methods ◽  
Public Data ◽  
Selection For ◽  
Hidden States ◽  
Sequential Matching ◽  
New Framework

We study the problem of response selection for multi-turn conversation in retrieval-based chatbots. The task involves matching a response candidate with a conversation context, the challenges for which include how to recognize important parts of the context, and how to model the relationships among utterances in the context. Existing matching methods may lose important information in contexts as we can interpret them with a unified framework in which contexts are transformed to fixed-length vectors without any interaction with responses before matching. This motivates us to propose a new matching framework that can sufficiently carry important information in contexts to matching and model relationships among utterances at the same time. The new framework, which we call a sequential matching framework (SMF), lets each utterance in a context interact with a response candidate at the first step and transforms the pair to a matching vector. The matching vectors are then accumulated following the order of the utterances in the context with a recurrent neural network (RNN) that models relationships among utterances. Context-response matching is then calculated with the hidden states of the RNN. Under SMF, we propose a sequential convolutional network and sequential attention network and conduct experiments on two public data sets to test their performance. Experiment results show that both models can significantly outperform state-of-the-art matching methods. We also show that the models are interpretable with visualizations that provide us insights on how they capture and leverage important information in contexts for matching.

scholarly journals ROBUST FEATURES FOR LEG DETECTION IN 2D LASER RANGE DATA

2018 ◽  
Vol XLII-4 ◽  
pp. 351-358
Author(s):  
D. Li ◽  
L. Li ◽  
M. Zhou ◽  
X. Zuo
Keyword(s):  
State Of The Art ◽  
Smart Cities ◽  
Data Sets ◽  
Range Data ◽  
People Detection ◽  
Laser Range ◽  
Adaboost Algorithm ◽  
Below The Knee ◽  
Knee Height ◽  
Art Methods

<p><strong>Abstract.</strong> People detection in 2D laser range data is widely used in many application, such as robotics, smart cities or regions, and intelligent driving. For most current methods on people detection based on a single laser range finder are actually leg detectors as the sensor are always established below the knee height. Current state-of-the-art methods share similar steps including segmentation, feature extraction and a machine learning-based classification, but use different features which have good performance on their own experimental data. For researchers, it is important and desirable to know which features are more robust. In this paper, taking advantage of the fact that effective features can be selected by AdaBoost and assembled into a strong classifier, a set of features presented in state-of-the-art methods is combined with a set of features presented by us to train a leg detector by the AdaBoost algorithm. This detector is assembling by effective features and can classify segments into leg and non-leg. Three open source data sets including simple and complex scenarios are used for the experiments to test the features and extracted the important ones. To reduce the effect of segmentation on the final results, three segmentation methods are simultaneously used for experiments and analysis to ensure the reliability and credibility of our conclusion. Finally, 10 robust features for leg detection in 2D laser range data are presented based on the results.</p>

scholarly journals Skin Cancer Classification using Convolutional Neural Networks: Systematic Review (Preprint)

2018 ◽  
Author(s):  
Titus Josef Brinker ◽  
Achim Hekler ◽  
Jochen Sven Utikal ◽  
Dirk Schadendorf ◽  
Carola Berking ◽  
...  
Keyword(s):  
Systematic Review ◽  
Neural Networks ◽  
Skin Lesion ◽  
Convolutional Neural Networks ◽  
State Of The Art ◽  
Skin Lesions ◽  
Data Sets ◽  
Classification Methods ◽  
Public Data

BACKGROUND State-of-the-art classifiers based on convolutional neural networks (CNNs) generally outperform the diagnosis of dermatologists and could enable life-saving and fast diagnoses, even outside the hospital via installation on mobile devices. To our knowledge, at present, there is no review of the current work in this research area. OBJECTIVE This study presents the first systematic review of the state-of-the-art research on classifying skin lesions with CNNs. We limit our review to skin lesion classifiers. In particular, methods that apply a CNN only for segmentation or for the classification of dermoscopic patterns are not considered here. Furthermore, this study discusses why the comparability of the presented procedures is very difficult and which challenges must be addressed in the future. METHODS We searched the Google Scholar, PubMed, Medline, Science Direct, and Web of Science databases for systematic reviews and original research articles published in English. Only papers that reported sufficient scientific proceedings are included in this review. RESULTS We found 13 papers that classified skin lesions using CNNs. In principle, classification methods can be differentiated according to three principles. Approaches that use a CNN already trained by means of another large data set and then optimize its parameters to the classification of skin lesions are both the most common methods as well as display the best performance with the currently available limited data sets. CONCLUSIONS CNNs display a high performance as state-of-the-art skin lesion classifiers. Unfortunately, it is difficult to compare different classification methods because some approaches use non-public data sets for training and/or testing, thereby making reproducibility difficult.

scholarly journals AKT: Ancestry and Kinship Toolkit

2016 ◽  
Author(s):  
Rudy Arthur ◽  
Ole Schulz-Trieglaff ◽  
Anthony J. Cox ◽  
Jared Michael O’Connell
Keyword(s):  
Data Clustering ◽  
State Of The Art ◽  
Source Code ◽  
Statistical Genetics ◽  
Data Sets ◽  
Whole Genome ◽  
Link Type ◽  
Art Methods ◽  
Invaluable Tool

AbstractAncestry and Kinship Toolkit (AKT) is a statistical genetics tool for analysing large cohorts of whole-genome sequenced samples. It can rapidly detect related samples, characterise sample ancestry, calculate correlation between variants, check Mendel consistency and perform data clustering. AKT brings together the functionality of many state-of-the-art methods, with a focus on speed and a unified interface. We believe it will be an invaluable tool for the curation of large WGS data-sets.AvailabilityThe source code is available at https://illumina.github.io/[email protected], [email protected]

scholarly journals Towards a Hierarchical Bayesian Model of Multi-View Anomaly Detection

2020 ◽  
Author(s):  
Zhen Wang ◽  
Chao Lan
Keyword(s):  
Latent Variables ◽  
Bayesian Model ◽  
State Of The Art ◽  
Bayesian Estimator ◽  
Data Sets ◽  
Hierarchical Bayesian ◽  
Hierarchical Bayesian Model ◽  
Single View ◽  
Public Data ◽  
Anomaly Detector

Traditional anomaly detectors examine a single view of instances and cannot discover multi-view anomalies, i.e., instances that exhibit inconsistent behaviors across different views. To tackle the problem, several multi-view anomaly detectors have been developed recently, but they are all transductive and unsupervised thus may suffer some challenges. In this paper, we propose a novel inductive semi-supervised Bayesian multi-view anomaly detector. Specifically, we first present a generative model for normal data. Then, we build a hierarchical Bayesian model, by first assigning priors to all parameters and latent variables, and then assigning priors over the priors. Finally, we employ variational inference to approximate the posterior of the model and evaluate anomalous scores of multi-view instances. In the experiment, we show the proposed Bayesian detector consistently outperforms state-of-the-art counterparts across several public data sets and three well-known types of multi-view anomalies. In theory, we prove the inferred Bayesian estimator is consistent and derive a proximate sample complexity for the proposed anomaly detector.

TrustSVD: A Novel Trust-Based Matrix Factorization Model with User Trust and Item Ratings

2017 ◽  
Vol 7 (11) ◽  
pp. 7 ◽  
Author(s):  
K Sobha Rani
Keyword(s):  
Matrix Factorization ◽  
Social Trust ◽  
State Of The Art ◽  
Data Sets ◽  
Real World Data ◽  
Recommendation Algorithm ◽  
Active User ◽  
Factorization Model ◽  
The Social ◽  
Matrix Factorization Technique

Collaborative filtering suffers from the problems of data sparsity and cold start, which dramatically degrade recommendation performance. To help resolve these issues, we propose TrustSVD, a trust-based matrix factorization technique. By analyzing the social trust data from four real-world data sets, we conclude that not only the explicit but also the implicit influence of both ratings and trust should be taken into consideration in a recommendation model. Hence, we build on top of a state-of-the-art recommendation algorithm SVD++ which inherently involves the explicit and implicit influence of rated items, by further incorporating both the explicit and implicit influence of trusted users on the prediction of items for an active user. To our knowledge, the work reported is the first to extend SVD++ with social trust information. Experimental results on the four data sets demonstrate that our approach TrustSVD achieves better accuracy than other ten counterparts, and can better handle the concerned issues.

Sign in / Sign up

Export Citation Format

Share Document