scholarly journals Cross-Genre and Cross-Domain Detection of Semantic Uncertainty

2012 ◽  
Vol 38 (2) ◽  
pp. 335-367 ◽  
Author(s):  
György Szarvas ◽  
Veronika Vincze ◽  
Richárd Farkas ◽  
György Móra ◽  
Iryna Gurevych
Keyword(s):  
Language Processing ◽  
Domain Adaptation ◽  
Recognition Task ◽  
Data Set ◽  
Fine Grained ◽  
Cross Domain ◽  
Cue Recognition ◽  
Annotation Costs ◽  
Key Steps ◽  
Lexical Cues

Uncertainty is an important linguistic phenomenon that is relevant in various Natural Language Processing applications, in diverse genres from medical to community generated, newswire or scientific discourse, and domains from science to humanities. The semantic uncertainty of a proposition can be identified in most cases by using a finite dictionary (i.e., lexical cues) and the key steps of uncertainty detection in an application include the steps of locating the (genre- and domain-specific) lexical cues, disambiguating them, and linking them with the units of interest for the particular application (e.g., identified events in information extraction). In this study, we focus on the genre and domain differences of the context-dependent semantic uncertainty cue recognition task. We introduce a unified subcategorization of semantic uncertainty as different domain applications can apply different uncertainty categories. Based on this categorization, we normalized the annotation of three corpora and present results with a state-of-the-art uncertainty cue recognition model for four fine-grained categories of semantic uncertainty. Our results reveal the domain and genre dependence of the problem; nevertheless, we also show that even a distant source domain data set can contribute to the recognition and disambiguation of uncertainty cues, efficiently reducing the annotation costs needed to cover a new domain. Thus, the unified subcategorization and domain adaptation for training the models offer an efficient solution for cross-domain and cross-genre semantic uncertainty recognition.

scholarly journals WiGR: A Practical Wi-Fi-Based Gesture Recognition System with a Lightweight Few-Shot Network

2021 ◽  
Vol 11 (8) ◽  
pp. 3329
Author(s):  
Pengli Hu ◽  
Chengpei Tang ◽  
Kang Yin ◽  
Xie Zhang
Keyword(s):  
Computational Complexity ◽  
Gesture Recognition ◽  
Channel State Information ◽  
Domain Adaptation ◽  
Recognition Performance ◽  
Recognition System ◽  
Channel State ◽  
Data Set ◽  
State Information ◽  
Cross Domain

Wi-Fi sensing technology based on deep learning has contributed many breakthroughs in gesture recognition tasks. However, most methods concentrate on single domain recognition with high computational complexity while rarely investigating cross-domain recognition with lightweight performance, which cannot meet the requirements of high recognition performance and low computational complexity in an actual gesture recognition system. Inspired by the few-shot learning methods, we propose WiGR, a Wi-Fi-based gesture recognition system. The key structure of WiGR is a lightweight few-shot learning network that introduces some lightweight blocks to achieve lower computational complexity. Moreover, the network can learn a transferable similarity evaluation ability from the training set and apply the learned knowledge to the new domain to address domain shift problems. In addition, we made a channel state information (CSI)-Domain Adaptation (CSIDA) data set that includes channel state information (CSI) traces with various domain factors (i.e., environment, users, and locations) and conducted extensive experiments on two data sets (CSIDA and SignFi). The evaluation results show that WiGR can reach 87.8%–94.8% cross-domain accuracy, and the parameters and the calculations are reduced by more than 50%. Extensive experiments demonstrate that WiGR can achieve excellent recognition performance using only a few samples and is thus a lightweight and practical gesture recognition system compared with state-of-the-art methods.

scholarly journals Cross-Domain End-To-End Aspect-Based Sentiment Analysis with Domain-Dependent Embeddings

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Yingjie Tian ◽  
Linrui Yang ◽  
Yunchuan Sun ◽  
Dalian. Liu
Keyword(s):  
Sentiment Analysis ◽  
Opinion Mining ◽  
Learning Strategy ◽  
Domain Adaptation ◽  
Online Reviews ◽  
Domain Model ◽  
Fine Grained ◽  
Cross Domain ◽  
End To End ◽  
Public Datasets

With the development of sentiment analysis, studies have been gradually classified based on different researched candidates. Among them, aspect-based sentiment analysis plays an important role in subtle opinion mining for online reviews. It used to be treated as a group of pipeline tasks but has been proved to be analysed well in an end-to-end model recently. Due to less labelled resources, the need for cross-domain aspect-based sentiment analysis has started to get attention. However, challenges exist when seeking domain-invariant features and keeping domain-dependent features to achieve domain adaptation within a fine-grained task. This paper utilizes the domain-dependent embeddings and designs the model CD-E2EABSA to achieve cross-domain aspect-based sentiment analysis in an end-to-end fashion. The proposed model utilizes the domain-dependent embeddings with a multitask learning strategy to capture both domain-invariant and domain-dependent knowledge. Various experiments are conducted and show the effectiveness of all components on two public datasets. Also, it is also proved that as a cross-domain model, CD-E2EABSA can perform better than most of the in-domain ABSA methods.

scholarly journals Instance Weighting with Applications to Cross-domain Text Classification via Trading off Sample Selection Bias and Variance

2018 ◽  
Author(s):  
Rui Xia ◽  
Zhenchun Pan ◽  
Feng Xu
Keyword(s):  
Selection Bias ◽  
Language Processing ◽  
Text Classification ◽  
Performance Optimization ◽  
Domain Adaptation ◽  
Sample Selection ◽  
Density Ratio ◽  
Sample Selection Bias ◽  
Cross Domain ◽  
Instance Weighting

Domain adaptation is an important problem in natural language processing (NLP) due to the distributional difference between the labeled source domain and the target domain. In this paper, we study the domain adaptation problem from the instance weighting perspective. By using density ratio as the instance weight, the traditional instance weighting approaches can potentially correct the sample selection bias in domain adaptation. However, researchers often failed to achieve good performance when applying instance weighting to domain adaptation in NLP and many negative results were reported in the literature. In this work, we conduct an in-depth study on the causes of the failure, and find that previous work only focused on reducing the sample selection bias, but ignored another important factor, sample selection variance, in domain adaptation. On this basis, we propose a new instance weighting framework by trading off two factors in instance weight learning. We evaluate our approach on two cross-domain text classification tasks and compare it with eight instance weighting methods. The results prove our approach's advantages in domain adaptation performance, optimization efficiency and parameter stability.

scholarly journals A Secure and Efficient Multi Authority Encryption Scheme in Cross Domain Data Sharing

2020 ◽  
Vol 9 (4) ◽  
pp. 1289-1293
Keyword(s):  
Current System ◽  
Data Set ◽  
Customer Data ◽  
Fine Grained ◽  
Computational Overhead ◽  
Cross Domain ◽  
Attribute Based Encryption ◽  
Dynamic Modification ◽  
Structure Flexibility ◽  
Cryptographic Techniques

Attribute Based Encryption (ABE) in light of the fact that the rule locals to make sure about the patient data set aside on a semi-trusted. In ABE plot, each patient is regularly recognized by name which fuses the patient attributes. At the reason when Patient re-proper the delicate data for sharing on cloud system on cloud structures. Taking care of the patient records on suspicious limit makes secure transfer of data to be a test issue. To remain tricky customer data mystery against suspicious cloud structure. the current system when in doubt apply cryptographic techniques by revealing data unscrambling keys just to affirmed customer. the basic troubles for cryptographic technique fuse at a proportional time achieving structure flexibility and fine-grained data get the opportunity to manage, gainful key or customer the load up, data security, computational overhead then forward. To manage these issues, promptly applied and maintaining access approaches snared in to attributes and sanctioning the information owner to designate most count genuine assignments to customer disavowal to untrusted server without uncovering data substance to around then. We achieve this target by introducing multi authority characteristic based encryption. Our proposed plot in like manner has momentous features of customer get the chance to benefit characterization, dynamic modification of access game plans or archive properties and customer puzzle key duty, supports capable on-demand customer or trademark denial and break-glass access under emergency circumstances.

A Review and evaluation of Machine Translation methods for Lumasaaba

2020 ◽  
pp. 3-17
Author(s):  
Peter Nabende
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Language Processing ◽  
Research Area ◽  
Data Driven ◽  
East African ◽  
Data Set ◽  
African Languages ◽  
Translation Methods

Natural Language Processing for under-resourced languages is now a mainstream research area. However, there are limited studies on Natural Language Processing applications for many indigenous East African languages. As a contribution to covering the current gap of knowledge, this paper focuses on evaluating the application of well-established machine translation methods for one heavily under-resourced indigenous East African language called Lumasaaba. Specifically, we review the most common machine translation methods in the context of Lumasaaba including both rule-based and data-driven methods. Then we apply a state of the art data-driven machine translation method to learn models for automating translation between Lumasaaba and English using a very limited data set of parallel sentences. Automatic evaluation results show that a transformer-based Neural Machine Translation model architecture leads to consistently better BLEU scores than the recurrent neural network-based models. Moreover, the automatically generated translations can be comprehended to a reasonable extent and are usually associated with the source language input.

Neural Mechanisms of Music and Language

2019 ◽  
pp. 906-952
Author(s):  
Mattson Ogg ◽  
L. Robert Slevc
Keyword(s):  
Auditory Cortex ◽  
Language Processing ◽  
Auditory Processing ◽  
Cortical Plasticity ◽  
Speaker Identification ◽  
Auditory Pathway ◽  
Cognitive Mechanisms ◽  
Cross Domain ◽  
Music And Language ◽  
Cortical Regions

Music and language are uniquely human forms of communication. What neural structures facilitate these abilities? This chapter conducts a review of music and language processing that follows these acoustic signals as they ascend the auditory pathway from the brainstem to auditory cortex and on to more specialized cortical regions. Acoustic, neural, and cognitive mechanisms are identified where processing demands from both domains might overlap, with an eye to examples of experience-dependent cortical plasticity, which are taken as strong evidence for common neural substrates. Following an introduction describing how understanding musical processing informs linguistic or auditory processing more generally, findings regarding the major components (and parallels) of music and language research are reviewed: pitch perception, syntax and harmonic structural processing, semantics, timbre and speaker identification, attending in auditory scenes, and rhythm. Overall, the strongest evidence that currently exists for neural overlap (and cross-domain, experience-dependent plasticity) is in the brainstem, followed by auditory cortex, with evidence and the potential for overlap becoming less apparent as the mechanisms involved in music and speech perception become more specialized and distinct at higher levels of processing.

scholarly journals A Novel Domain Adaptation-Based Intelligent Fault Diagnosis Model to Handle Sample Class Imbalanced Problem

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3382
Author(s):  
Zhongwei Zhang ◽  
Mingyu Shao ◽  
Liping Wang ◽  
Sujuan Shao ◽  
Chicheng Ma
Keyword(s):  
Fault Diagnosis ◽  
Domain Adaptation ◽  
Class Imbalance ◽  
Rolling Bearing ◽  
Industrial Applications ◽  
Mechanical Equipment ◽  
Reliable Operation ◽  
Cross Domain ◽  
Geometric Difference ◽  
Model Generalization

As the key component to transmit power and torque, the fault diagnosis of rotating machinery is crucial to guarantee the reliable operation of mechanical equipment. Regrettably, sample class imbalance is a common phenomenon in industrial applications, which causes large cross-domain distribution discrepancies for domain adaptation (DA) and results in performance degradation for most of the existing mechanical fault diagnosis approaches. To address this issue, a novel DA approach that simultaneously reduces the cross-domain distribution difference and the geometric difference is proposed, which is defined as MRMI. This work contains three parts to improve the sample class imbalance issue: (1) A novel distance metric method (MVD) is proposed and applied to improve the performance of marginal distribution adaptation. (2) Manifold regularization is combined with instance reweighting to simultaneously explore the intrinsic manifold structure and remove irrelevant source-domain samples adaptively. (3) The ℓ2-norm regularization is applied as the data preprocessing tool to improve the model generalization performance. The gear and rolling bearing datasets with class imbalanced samples are applied to validate the reliability of MRMI. According to the fault diagnosis results, MRMI can significantly outperform competitive approaches under the condition of sample class imbalance.

Sign in / Sign up

Export Citation Format

Share Document