Domain-dependent Features Research Articles

Research on Named Entity Recognition for Spoken Language Understanding Using Adversarial Transfer Learning

In this paper, we propose an adversarial transfer learning method to solve the lack of data resources for named entity recognition (NER) tasks in spoken language understanding. In the framework, we use bi-directional long short-term memory with self-attention and conditional random field (BiLSTM-Attention-CRF) model which combines character and word information as the baseline model to train source domain and target domain corpus jointly. Shared features between domains are extracted by a shared feature extractor. This paper uses two different sharing patterns simultaneously: full sharing mode and private sharing mode. On this basis, an adversarial discriminator is added to the shared feature extractor to simulate generative adversarial networks (GAN) and eliminate domain-dependent features. This paper compares ordinary adversarial discriminator (OAD) and generalized resource-adversarial discriminator (GRAD) through experiments. The experimental results show that the transfer effect of GRAD is better than other methods. The F1 score reaches 92.99% at the highest, with a relative increase of 12.89%. It can effectively improve the performance of NER tasks in resource shortage fields and solve the problem of negative transfer.

A Privacy-Preserving Cross-Domain Healthcare Wearables Recommendation Algorithm Based on Domain-Dependent and Domain-Independent Feature Fusion.

Recently, recommender systems are applied to provide personalized recomendation for healthcare wearables. However, due to the sparsity problem, traditional recommendation algorithms are difficult to achieve desired performance. Considering that consumers often buy and rate other types of items on E-commerce platforms, we can leverage significant information in the auxiliary domains to improve the recommendation performance of healthcare wearables, which can be regarded as cross-domain recommendation. However, traditional cross-domain recommendation model cannot fully represent user's characteristics and fail to consider the leaks of original auxiliary domain ratings during the information transfer process. To overcome the two shortcomings, this paper proposes a Privacy-Preserving Cross-Domain Healthcare Wearables Recommendation algorithm (PPCDHWRec). Firstly, user's characteristics are divided into domain-dependent features and domain-independent features, which complement each other and fully depict the user's characteristics. Secondly, inspired by the latent factor model, we factorize the original rating information of each auxiliary domain by Funk-SVD and Orthogonal Nonnegative Matrix Tri-Factorization (ONMTF) model, to obtain user's domain-dependent and domain-independent features, respectively. Finally, the Factorization Machine algorithm is used to fuse the obtained user's features with the target domain information to provide the recommendation results. By hiding the item latent factors obtained in the factorization process, PPCDHWRec ensures that the original information cannot be inferred from the transferred user hidden vector. Hence, PPCDHWRec is a privacy-preserving recommendation model. Experiments on two groups of auxiliary domains, having high and low correlations with target domain, show the effectiveness of PPCDHWRec.

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

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.

Classifying MOOC forum posts using corpora semantic similarities: a study on transferability across different courses

Information overload in MOOC discussion forums is a major problem that hinders the effectiveness of learner facilitation by the course staff. To address this issue, supervised classification models have been studied and developed in order to assist course facilitators in detecting forum discussions that seek for their intervention. A key issue studied by the literature refers to the transferability of these models to domains other than the domain in which they were initially trained. Typically these models employ domain-dependent features, and therefore they fail to transfer to other subject matters. In this study, we propose and evaluate an alternative way of building supervised models in this context, by using the semantic similarities of the forum transcripts with the dynamically created corpora from the MOOC environment as training features. Specifically, in this study, we analyze the case of two MOOCs, in which the models that we built are classifying forum discussions into three categories, course logistics, content-related and no action required. Furthermore, we evaluate the transferability of the derived models and interpret which features can be effectively transferred to other unseen courses. The findings of this study reveal the main benefits and trade-offs of the proposed approach and provide MOOC developers with insights about the main issues that inhibit the transferability of these models.

Domain-adversarial Network Alignment

Network alignment is a critical task in a wide variety of fields. Many existing works leverage on representation learning to accomplish this task without eliminating domain representation bias induced by domain-dependent features, which yield inferior alignment performance. This paper proposes a unified deep architecture ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DANA</i> ) to obtain a domain-invariant representation for network alignment via an adversarial domain classifier. Specifically, we employ the graph convolutional networks to perform network embedding under the domain adversarial principle, given a small set of observed anchors. Then, the semi-supervised learning framework is optimized by maximizing a posterior probability distribution of observed anchors and the loss of a domain classifier simultaneously. We also develop a few variants of our model, such as, direction-aware network alignment, weight-sharing for directed networks and simplification of parameter space. Experiments on three real-world social network datasets demonstrate that our proposed approaches achieve state-of-the-art alignment results.

A neural network for semantic labelling of structured information

Intelligent systems rely on rich sources of information to make informed decisions. Using information from external sources requires establishing correspondences between the information and known information classes. This can be achieved with semantic labelling, which assigns known labels to structured information by classifying it according to computed features. The existing proposals have explored different sets of features, without focusing on what classification techniques are used. In this paper we present three contributions: first, insights on architectural issues that arise when using neural networks for semantic labelling; second, a novel implementation of semantic labelling that uses a state-of-the-art neural network classifier which achieves significantly better results than other four traditional classifiers; third, a comparison of the results obtained by the former network when using different subsets of features, comparing textual features to structural ones, and domain-dependent features to domain-independent ones. The experiments were carried away with datasets from three real world sources. Our results show that there is a need to develop more semantic labelling proposals with sophisticated classification techniques and large features catalogues.

Fusion of Domain-Specific and Trainable Features for Gender Recognition From Face Images

The popularity and the appeal of systems which are able to automatically determine the gender from face images are growing rapidly. Such a great interest arises from the wide variety of applications, especially in the fields of retail and video surveillance. In recent years, there have been several attempts to address this challenge, but a definitive solution has not yet been found. In this paper, we propose a novel approach that fuses domain-specific and trainable features to recognize the gender from face images. In particular, we use the SURF descriptors extracted from 51 facial landmarks related to eyes, nose, and mouth as domain-dependent features, and the COSFIRE filters as trainable features. The proposed approach turns out to be very robust with respect to the well-known face variations, including different poses, expressions, and illumination conditions. It achieves state-of-the-art recognition rates on the GENDER-FERET (94.7%) and on the labeled faces in the wild (99.4%) data sets, which are two of the most popular benchmarks for gender recognition. We further evaluated the method on a new data set acquired in real scenarios, the UNISA-Public, recently made publicly available. It consists of 206 training (144 male, 62 female) and 200 test (139 male, 61 female) images that are acquired with a real-time indoor camera capturing people in regular walking motion. Such experiment has the aim to assess the capability of the algorithm to deal with face images extracted from videos, which are definitely more challenging than the still images available in the standard data sets. Also for this data set, we achieved a high recognition rate of 91.5%, that confirms the generalization capabilities of the proposed approach. Of the two types of features, the trainable COSFIRE filters are the most effective and, given their trainable character, they can be applied in any visual pattern recognition problem.

Cell mitosis detection using deep neural networks

Quantitative analysis of cell mitosis, the process by which cells regenerate, is important in cell biology. Automatic cell mitosis detection can greatly facilitate the investigation of cell life cycle. However, cell-type diversity, cell non-rigid deformation and high cell density pose difficulties on handcrafting visual features for traditional approaches. Aided by massively captured microscopy image sequences, deep neural networks have recently become available for automatic cell mitosis detection. This paper proposes an end-to-end framework named as F3D-CNN for mitosis detection, and F3D-CNN is directly trained from data without requiring designing domain dependent features. Well-trained F3D-CNN first filters out potential mitosis events based on the static information in each individual image, and further discriminates candidates by incorporating the spatiotemporal information from image sequences. The state-of-the-art performance of F3D-CNN was confirmed in experiments on two public datasets (multipotent C3H10T1/2 mesenchymal stem cells and C2C12 myoblastic stem cells).

An influence diagram based multi-criteria decision making framework for multirobot coalition formation

Novel systems allocating coalitions of humans and unmanned heterogeneous vehicles will act as force multipliers for future real-world missions. Conventional coalition formation architectures seek to compute efficient robot coalitions by leveraging either a single greedy, approximation, or market-based algorithm, which renders such architectures inapplicable to a variety of real-world mission scenarios. A novel, intelligent multi-criteria decision making framework is presented that reasons over a library of coalition formation algorithms for selecting the most appropriate subset of algorithm(s) to apply to a wide spectrum of complex missions. The framework is based on influence diagrams in order to handle uncertainties in dynamic real-world environments. An existing taxonomy comprised of multiple mission and domain dependent features is leveraged to classify the coalition formation algorithms. Dimensionality reduction is achieved via principal component analysis, which extracts the most significant taxonomy features crucial for decision making. A link analysis technique provides the mission specific utility values of each feature-value pair and algorithm in the library. Experimental results demonstrate that the presented framework accurately selects the most appropriate subset of coalition formation algorithm(s) based on multiple mission criteria, when applied to a number of simulated real-world mission scenarios.

Feature generation and representations for protein–protein interaction classification

Automatic detecting protein–protein interaction (PPI) relevant articles is a crucial step for large-scale biological database curation. The previous work adopted POS tagging, shallow parsing and sentence splitting techniques, but they achieved worse performance than the simple bag-of-words representation. In this paper, we generated and investigated multiple types of feature representations in order to further improve the performance of PPI text classification task. Besides the traditional domain-independent bag-of-words approach and the term weighting methods, we also explored other domain-dependent features, i.e. protein–protein interaction trigger keywords, protein named entities and the advanced ways of incorporating Natural Language Processing (NLP) output. The integration of these multiple features has been evaluated on the BioCreAtIvE II corpus. The experimental results showed that both the advanced way of using NLP output and the integration of bag-of-words and NLP output improved the performance of text classification. Specifically, in comparison with the best performance achieved in the BioCreAtIvE II IAS, the feature-level and classifier-level integration of multiple features improved the performance of classification 2.71% and 3.95%, respectively.

Exploiting and integrating rich features for biological literature classification

BackgroundEfficient features play an important role in automated text classification, which definitely facilitates the access of large-scale data. In the bioscience field, biological structures and terminologies are described by a large number of features; domain dependent features would significantly improve the classification performance. How to effectively select and integrate different types of features to improve the biological literature classification performance is the major issue studied in this paper.ResultsTo efficiently classify the biological literatures, we propose a novel feature value schema TF*ML, features covering from lower level domain independent “string feature” to higher level domain dependent “semantic template feature”, and proper integrations among the features. Compared to our previous approaches, the performance is improved in terms of AUC and F-Score by 11.5% and 8.8% respectively, and outperforms the best performance achieved in BioCreAtIvE 2006.ConclusionsDifferent types of features possess different discriminative capabilities in literature classification; proper integration of domain independent and dependent features would significantly improve the performance and overcome the over-fitting on data distribution.