Unsupervised extractive multi-document summarization method based on transfer learning from BERT multi-task fine-tuning

2021 ◽  
pp. 016555152199061
Author(s):  
Salima Lamsiyah ◽  
Abdelkader El Mahdaouy ◽  
Saïd El Alaoui Ouatik ◽  
Bernard Espinasse
Keyword(s):  
Transfer Learning ◽  
State Of The Art ◽  
Representation Learning ◽  
Fine Tuning ◽  
Text Representation ◽  
Document Summarization ◽  
Semantic Relationships ◽  
Benchmark Datasets ◽  
Tuning Methods ◽  
Fine Tune

Text representation is a fundamental cornerstone that impacts the effectiveness of several text summarization methods. Transfer learning using pre-trained word embedding models has shown promising results. However, most of these representations do not consider the order and the semantic relationships between words in a sentence, and thus they do not carry the meaning of a full sentence. To overcome this issue, the current study proposes an unsupervised method for extractive multi-document summarization based on transfer learning from BERT sentence embedding model. Moreover, to improve sentence representation learning, we fine-tune BERT model on supervised intermediate tasks from GLUE benchmark datasets using single-task and multi-task fine-tuning methods. Experiments are performed on the standard DUC’2002–2004 datasets. The obtained results show that our method has significantly outperformed several baseline methods and achieves a comparable and sometimes better performance than the recent state-of-the-art deep learning–based methods. Furthermore, the results show that fine-tuning BERT using multi-task learning has considerably improved the performance.

scholarly journals Text-Graph Enhanced Knowledge Graph Representation Learning

2021 ◽  
Vol 4 ◽  
Author(s):  
Linmei Hu ◽  
Mengmei Zhang ◽  
Shaohua Li ◽  
Jinghan Shi ◽  
Chuan Shi ◽  
...  
Keyword(s):  
State Of The Art ◽  
Representation Learning ◽  
Graph Representation ◽  
Semantic Relationships ◽  
Convolutional Networks ◽  
Gating Mechanism ◽  
Benchmark Datasets ◽  
Knowledge Graphs ◽  
Low Dimensional ◽  
Embedding Methods

Knowledge Graphs (KGs) such as Freebase and YAGO have been widely adopted in a variety of NLP tasks. Representation learning of Knowledge Graphs (KGs) aims to map entities and relationships into a continuous low-dimensional vector space. Conventional KG embedding methods (such as TransE and ConvE) utilize only KG triplets and thus suffer from structure sparsity. Some recent works address this issue by incorporating auxiliary texts of entities, typically entity descriptions. However, these methods usually focus only on local consecutive word sequences, but seldom explicitly use global word co-occurrence information in a corpus. In this paper, we propose to model the whole auxiliary text corpus with a graph and present an end-to-end text-graph enhanced KG embedding model, named Teger. Specifically, we model the auxiliary texts with a heterogeneous entity-word graph (called text-graph), which entails both local and global semantic relationships among entities and words. We then apply graph convolutional networks to learn informative entity embeddings that aggregate high-order neighborhood information. These embeddings are further integrated with the KG triplet embeddings via a gating mechanism, thus enriching the KG representations and alleviating the inherent structure sparsity. Experiments on benchmark datasets show that our method significantly outperforms several state-of-the-art methods.

scholarly journals Efficient Graph Collaborative Filtering via Contrastive Learning

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4666
Author(s):  
Zhiqiang Pan ◽  
Honghui Chen
Keyword(s):  
Collaborative Filtering ◽  
State Of The Art ◽  
Representation Learning ◽  
First Order ◽  
Satisfactory Performance ◽  
Potential Applications ◽  
Benchmark Datasets ◽  
Bayesian Personalized Ranking ◽  
Graph Neural Networks ◽  
Training Efficiency

Collaborative filtering (CF) aims to make recommendations for users by detecting user’s preference from the historical user–item interactions. Existing graph neural networks (GNN) based methods achieve satisfactory performance by exploiting the high-order connectivity between users and items, however they suffer from the poor training efficiency problem and easily introduce bias for information propagation. Moreover, the widely applied Bayesian personalized ranking (BPR) loss is insufficient to provide supervision signals for training due to the extremely sparse observed interactions. To deal with the above issues, we propose the Efficient Graph Collaborative Filtering (EGCF) method. Specifically, EGCF adopts merely one-layer graph convolution to model the collaborative signal for users and items from the first-order neighbors in the user–item interactions. Moreover, we introduce contrastive learning to enhance the representation learning of users and items by deriving the self-supervisions, which is jointly trained with the supervised learning. Extensive experiments are conducted on two benchmark datasets, i.e., Yelp2018 and Amazon-book, and the experimental results demonstrate that EGCF can achieve the state-of-the-art performance in terms of Recall and normalized discounted cumulative gain (NDCG), especially on ranking the target items at right positions. In addition, EGCF shows obvious advantages in the training efficiency compared with the competitive baselines, making it practicable for potential applications.

scholarly journals New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Young Jae Kim ◽  
Jang Pyo Bae ◽  
Jun-Won Chung ◽  
Dong Kyun Park ◽  
Kwang Gi Kim ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Transfer Learning ◽  
Test Data ◽  
State Of The Art ◽  
Early Stage ◽  
Statistical Significance ◽  
Recall Rate ◽  
Training Data ◽  
Fine Tuning ◽  
Accuracy Evaluation

AbstractWhile colorectal cancer is known to occur in the gastrointestinal tract. It is the third most common form of cancer of 27 major types of cancer in South Korea and worldwide. Colorectal polyps are known to increase the potential of developing colorectal cancer. Detected polyps need to be resected to reduce the risk of developing cancer. This research improved the performance of polyp classification through the fine-tuning of Network-in-Network (NIN) after applying a pre-trained model of the ImageNet database. Random shuffling is performed 20 times on 1000 colonoscopy images. Each set of data are divided into 800 images of training data and 200 images of test data. An accuracy evaluation is performed on 200 images of test data in 20 experiments. Three compared methods were constructed from AlexNet by transferring the weights trained by three different state-of-the-art databases. A normal AlexNet based method without transfer learning was also compared. The accuracy of the proposed method was higher in statistical significance than the accuracy of four other state-of-the-art methods, and showed an 18.9% improvement over the normal AlexNet based method. The area under the curve was approximately 0.930 ± 0.020, and the recall rate was 0.929 ± 0.029. An automatic algorithm can assist endoscopists in identifying polyps that are adenomatous by considering a high recall rate and accuracy. This system can enable the timely resection of polyps at an early stage.

Tomato pest classification using deep convolutional neural network with transfer learning, fine tuning and scratch learning

2021 ◽  
pp. 1-10
Author(s):  
Gayatri Pattnaik ◽  
Vimal K. Shrivastava ◽  
K. Parvathi
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Data Augmentation ◽  
State Of The Art ◽  
Deep Convolutional Neural Network ◽  
Fine Tuning ◽  
Tomato Plants ◽  
Random Weights

Pests are major threat to economic growth of a country. Application of pesticide is the easiest way to control the pest infection. However, excessive utilization of pesticide is hazardous to environment. The recent advances in deep learning have paved the way for early detection and improved classification of pest in tomato plants which will benefit the farmers. This paper presents a comprehensive analysis of 11 state-of-the-art deep convolutional neural network (CNN) models with three configurations: transfers learning, fine-tuning and scratch learning. The training in transfer learning and fine tuning initiates from pre-trained weights whereas random weights are used in case of scratch learning. In addition, the concept of data augmentation has been explored to improve the performance. Our dataset consists of 859 tomato pest images from 10 categories. The results demonstrate that the highest classification accuracy of 94.87% has been achieved in the transfer learning approach by DenseNet201 model with data augmentation.

A Study of the Influence of Data Complexity and Similarity on Soft Biometrics Classification Performance in a Transfer Learning Scenario

2021 ◽  
Vol 18 (2) ◽  
pp. 56-65
Author(s):  
Marcelo Romero ◽  
◽  
Matheus Gutoski ◽  
Leandro Takeshi Hattori ◽  
Manassés Ribeiro ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Classification Performance ◽  
Fine Tuning ◽  
Similarity Metrics ◽  
Soft Biometrics ◽  
Final Layer ◽  
The One ◽  
Fully Connected ◽  
The Relationship ◽  
Fine Tune

Transfer learning is a paradigm that consists in training and testing classifiers with datasets drawn from distinct distributions. This technique allows to solve a particular problem using a model that was trained for another purpose. In the recent years, this practice has become very popular due to the increase of public available pre-trained models that can be fine-tuned to be applied in different scenarios. However, the relationship between the datasets used for training the model and the test data is usually not addressed, specially where the fine-tuning process is done only for the fully connected layers of a Convolutional Neural Network with pre-trained weights. This work presents a study regarding the relationship between the datasets used in a transfer learning process in terms of the performance achieved by models complexities and similarities. For this purpose, we fine-tune the final layer of Convolutional Neural Networks with pre-trained weights using diverse soft biometrics datasets. An evaluation of the performances of the models, when tested with datasets that are different from the one used for training the model, is presented. Complexity and similarity metrics are also used to perform the evaluation.

scholarly journals Star Topology Convolution for Graph Representation Learning

2020 ◽  
Author(s):  
Chong Wu ◽  
Zhenan Feng ◽  
Jiangbin Zheng ◽  
Houwang Zhang ◽  
Jiawang Cao ◽  
...  
Keyword(s):  
Protein Identification ◽  
State Of The Art ◽  
Feature Space ◽  
Representation Learning ◽  
Graph Representation ◽  
Global Features ◽  
Star Topology ◽  
Identification Methods ◽  
Benchmark Datasets ◽  
Deep Layers

<div><div><div><p>We present a novel graph convolutional method called star topology convolution (STC). This method makes graph convolution more similar to conventional convolutional neural networks (CNNs) in Euclidean feature space. Unlike most existing spectral convolutional methods, this method learns subgraphs which have a star topology rather than a fixed graph. It has fewer parameters in its convolutional filter and is inductive so that it is more flexible and can be applied to large and evolving graphs. As for CNNs in Euclidean feature space, the convolutional filter is localized and maintains a good weight sharing property. By introducing deep layers, the method can learn global features like a CNN. To validate the method, STC was compared to state-of-the-art spectral convolutional and spatial convolutional methods in a supervised learning setting on three benchmark datasets: Cora, Citeseer and Pubmed. The experimental results show that STC outperforms the other methods. STC was also applied to protein identification tasks and outperformed traditional and advanced protein identification methods.</p></div></div></div>

scholarly journals Semantics-Aligned Representation Learning for Person Re-Identification

2020 ◽  
Vol 34 (07) ◽  
pp. 11173-11180 ◽  
Author(s):  
Xin Jin ◽  
Cuiling Lan ◽  
Wenjun Zeng ◽  
Guoqiang Wei ◽  
Zhibo Chen
Keyword(s):  
State Of The Art ◽  
Representation Learning ◽  
The State ◽  
Feature Representation ◽  
Texture Image ◽  
Computationally Efficient ◽  
Feature Maps ◽  
Benchmark Datasets ◽  
Texture Generation ◽  
Base Network

Person re-identification (reID) aims to match person images to retrieve the ones with the same identity. This is a challenging task, as the images to be matched are generally semantically misaligned due to the diversity of human poses and capture viewpoints, incompleteness of the visible bodies (due to occlusion), etc. In this paper, we propose a framework that drives the reID network to learn semantics-aligned feature representation through delicate supervision designs. Specifically, we build a Semantics Aligning Network (SAN) which consists of a base network as encoder (SA-Enc) for re-ID, and a decoder (SA-Dec) for reconstructing/regressing the densely semantics aligned full texture image. We jointly train the SAN under the supervisions of person re-identification and aligned texture generation. Moreover, at the decoder, besides the reconstruction loss, we add Triplet ReID constraints over the feature maps as the perceptual losses. The decoder is discarded in the inference and thus our scheme is computationally efficient. Ablation studies demonstrate the effectiveness of our design. We achieve the state-of-the-art performances on the benchmark datasets CUHK03, Market1501, MSMT17, and the partial person reID dataset Partial REID.

Adverse Drug Event Prediction using Noisy Literature-Derived Knowledge Graphs: Algorithm Development and Evaluation (Preprint)

2021 ◽  
Author(s):  
Soham Dasgupta ◽  
Aishwarya Jayagopal ◽  
Abel Lim Jun Hong ◽  
Ragunathan Mariappan ◽  
Vaibhav Rajan
Keyword(s):  
Predictive Models ◽  
State Of The Art ◽  
Representation Learning ◽  
Biomedical Literature ◽  
Drug Event ◽  
Classification Models ◽  
Learning Methods ◽  
Post Marketing Surveillance ◽  
Benchmark Datasets ◽  
Knowledge Graphs

BACKGROUND Adverse Drug Events (ADEs) are unintended side-effects of drugs that cause substantial clinical and economic burden globally. Not all ADEs are discovered during clinical trials and so, post-marketing surveillance, called pharmacovigilance, is routinely conducted to find unknown ADEs. A wealth of information, that facilitates ADE discovery, lies in the enormous and continuously growing body of biomedical literature. Knowledge graphs (KG) encode information from the literature, where vertices and edges represent clinical concepts and their relations respectively. The scale and unstructured form of the literature necessitates the use of natural language processing (NLP) to automatically create such KGs. Previous studies have demonstrated the utility of such literature-derived KGs in ADE prediction. Through unsupervised learning of representations (features) of clinical concepts from the KG, that are used in machine learning models, state-of-the-art results for ADE prediction were obtained on benchmark datasets. OBJECTIVE In literature-derived KGs there is `noise’ in the form of false positive (erroneous) and false negative (absent) nodes and edges due to limitations of the NLP techniques used to infer the KGs. Previous representation learning methods do not account for such inaccuracies in the graph. NLP algorithms can quantify the confidence in their inference of extracted concepts and relations from the literature. Our hypothesis that motivates this work is that by utilizing such confidence scores during representation learning, the learnt embeddings would yield better features for ADE prediction models. METHODS We develop methods to utilize these confidence scores on two well-known representation learning methods – Deepwalk and TransE – to develop their `weighted’ versions – Weighted Deepwalk and Weighted TransE. These methods are used to learn representations from a large literature-derived KG, SemMedDB, containing more than 93 million clinical relations. They are compared with Embeddings of Sematic Predictions (ESP), that, to our knowledge, is the best reported representation learning method on SemMedDB with state-of-the-art results for ADE prediction. Representations learnt from different methods are used (separately) as features of drugs and diseases to build classification models for ADE prediction using benchmark datasets. The classification performance of all the methods is compared rigorously over multiple cross-validation settings. RESULTS The `weighted’ versions we design are able to learn representations that yield more accurate predictive models compared to both the corresponding unweighted versions of Deepwalk and TransE, as well as ESP, in our experiments. Performance improvements are up to 5.75% in F1 score and 8.4% in AUC, thus advancing the state-of-the-art in ADE prediction from literature-derived KGs. Implementation of our new methods and all experiments are available at https://bitbucket.org/cdal/kb_embeddings. CONCLUSIONS Our classification models can be used to aid pharmacovigilance teams in detecting potentially new ADEs. Our experiments demonstrate the importance of modelling inaccuracies in the inferred KGs for representation learning, which may also be useful in other predictive models that utilize literature-derived KGs.

scholarly journals Probing Natural Language Inference Models through Semantic Fragments

2020 ◽  
Vol 34 (05) ◽  
pp. 8713-8721
Author(s):  
Kyle Richardson ◽  
Hai Hu ◽  
Lawrence Moss ◽  
Ashish Sabharwal
Keyword(s):  
Natural Language ◽  
State Of The Art ◽  
Fine Tuning ◽  
Language Understanding ◽  
Inference Models ◽  
Linguistic Understanding ◽  
Benchmark Datasets ◽  
Linguistic Behavior ◽  
Linguistic Models

Do state-of-the-art models for language understanding already have, or can they easily learn, abilities such as boolean coordination, quantification, conditionals, comparatives, and monotonicity reasoning (i.e., reasoning about word substitutions in sentential contexts)? While such phenomena are involved in natural language inference (NLI) and go beyond basic linguistic understanding, it is unclear the extent to which they are captured in existing NLI benchmarks and effectively learned by models. To investigate this, we propose the use of semantic fragments—systematically generated datasets that each target a different semantic phenomenon—for probing, and efficiently improving, such capabilities of linguistic models. This approach to creating challenge datasets allows direct control over the semantic diversity and complexity of the targeted linguistic phenomena, and results in a more precise characterization of a model's linguistic behavior. Our experiments, using a library of 8 such semantic fragments, reveal two remarkable findings: (a) State-of-the-art models, including BERT, that are pre-trained on existing NLI benchmark datasets perform poorly on these new fragments, even though the phenomena probed here are central to the NLI task; (b) On the other hand, with only a few minutes of additional fine-tuning—with a carefully selected learning rate and a novel variation of “inoculation”—a BERT-based model can master all of these logic and monotonicity fragments while retaining its performance on established NLI benchmarks.

scholarly journals Fake or Genuine? Contextualised Text Representation for Fake Review Detection

2021 ◽  
Author(s):  
Rami Mohawesh ◽  
Shuxiang Xu ◽  
Matthew Springer ◽  
Muna Al-Hawawreh ◽  
Sumbal Maqsood
Keyword(s):  
State Of The Art ◽  
Online Reviews ◽  
Learning Approaches ◽  
Text Representation ◽  
Purchasing Decisions ◽  
Linguistic Features ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Hidden Patterns ◽  
Fake Reviews

Online reviews have a significant influence on customers' purchasing decisions for any products or services. However, fake reviews can mislead both consumers and companies. Several models have been developed to detect fake reviews using machine learning approaches. Many of these models have some limitations resulting in low accuracy in distinguishing between fake and genuine reviews. These models focused only on linguistic features to detect fake reviews and failed to capture the semantic meaning of the reviews. To deal with this, this paper proposes a new ensemble model that employs transformer architecture to discover the hidden patterns in a sequence of fake reviews and detect them precisely. The proposed approach combines three transformer models to improve the robustness of fake and genuine behaviour profiling and modelling to detect fake reviews. The experimental results using semi-real benchmark datasets showed the superiority of the proposed model over state-of-the-art models.

Sign in / Sign up

Export Citation Format

Share Document