scholarly journals Transfer Language Space with Similar Domain Adaptation: A Case Study with Hepatocellular Carcinoma

2020 ◽  
Author(s):  
Patricia Balthazar ◽  
Scott Jeffery Lee ◽  
Daniel Rubin ◽  
Terry Dessar ◽  
Judy Gichoya ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Domain Adaptation ◽  
Language Model ◽  
Complex Model ◽  
Language Models ◽  
Pixel Intensity ◽  
Cross Domain ◽  
Radiology Reports ◽  
Generic Language ◽  
Similar Domain

Transfer learning is a common practice in image classification with deep learning where the available data is often limited for training a complex model with millions of parameters. However, transferring language models requires special attention since cross-domain vocabularies (e.g. between news articles and radiology reports) do not always overlap as the pixel intensity range overlaps mostly for images. We present a concept of similar domain adaptation where we transfer an interinstitutional language model between two different modalities (ultrasound to MRI) to capture liver abnormalities. Our experiments show that such transfer is more effective for performing shared targeted task than generic language space transfer. We use MRI screening exam reports for hepatocellular carcinoma as the use-case and apply the transfer language space strategy to automatically label thousands of imaging exams.

Tri-training for Dependency Parsing Domain Adaptation

2022 ◽  
Vol 21 (3) ◽  
pp. 1-17
Author(s):  
Shu Jiang ◽  
Zuchao Li ◽  
Hai Zhao ◽  
Bao-Liang Lu ◽  
Rui Wang
Keyword(s):  
Transfer Learning ◽  
High Performance ◽  
Domain Adaptation ◽  
Language Model ◽  
Training Methods ◽  
Dependency Parsing ◽  
Cross Domain ◽  
Cross Lingual ◽  
Domain Transfer ◽  
Domain Transfer Learning

In recent years, the research on dependency parsing focuses on improving the accuracy of the domain-specific (in-domain) test datasets and has made remarkable progress. However, there are innumerable scenarios in the real world that are not covered by the dataset, namely, the out-of-domain dataset. As a result, parsers that perform well on the in-domain data usually suffer from significant performance degradation on the out-of-domain data. Therefore, to adapt the existing in-domain parsers with high performance to a new domain scenario, cross-domain transfer learning methods are essential to solve the domain problem in parsing. This paper examines two scenarios for cross-domain transfer learning: semi-supervised and unsupervised cross-domain transfer learning. Specifically, we adopt a pre-trained language model BERT for training on the source domain (in-domain) data at the subword level and introduce self-training methods varied from tri-training for these two scenarios. The evaluation results on the NLPCC-2019 shared task and universal dependency parsing task indicate the effectiveness of the adopted approaches on cross-domain transfer learning and show the potential of self-learning to cross-lingual transfer learning.

scholarly journals MenuNER: Domain-Adapted BERT Based NER Approach for a Domain with Limited Dataset and Its Application to Food Menu Domain

2021 ◽  
Vol 11 (13) ◽  
pp. 6007
Author(s):  
Muzamil Hussain Syed ◽  
Sun-Tae Chung
Keyword(s):  
Domain Adaptation ◽  
Language Model ◽  
Named Entity Recognition ◽  
Word Embedding ◽  
Fine Tuning ◽  
Entity Recognition ◽  
Language Models ◽  
Feature Vectors ◽  
Named Entity ◽  
Domain Specific

Entity-based information extraction is one of the main applications of Natural Language Processing (NLP). Recently, deep transfer-learning utilizing contextualized word embedding from pre-trained language models has shown remarkable results for many NLP tasks, including Named-entity recognition (NER). BERT (Bidirectional Encoder Representations from Transformers) is gaining prominent attention among various contextualized word embedding models as a state-of-the-art pre-trained language model. It is quite expensive to train a BERT model from scratch for a new application domain since it needs a huge dataset and enormous computing time. In this paper, we focus on menu entity extraction from online user reviews for the restaurant and propose a simple but effective approach for NER task on a new domain where a large dataset is rarely available or difficult to prepare, such as food menu domain, based on domain adaptation technique for word embedding and fine-tuning the popular NER task network model ‘Bi-LSTM+CRF’ with extended feature vectors. The proposed NER approach (named as ‘MenuNER’) consists of two step-processes: (1) Domain adaptation for target domain; further pre-training of the off-the-shelf BERT language model (BERT-base) in semi-supervised fashion on a domain-specific dataset, and (2) Supervised fine-tuning the popular Bi-LSTM+CRF network for downstream task with extended feature vectors obtained by concatenating word embedding from the domain-adapted pre-trained BERT model from the first step, character embedding and POS tag feature information. Experimental results on handcrafted food menu corpus from customers’ review dataset show that our proposed approach for domain-specific NER task, that is: food menu named-entity recognition, performs significantly better than the one based on the baseline off-the-shelf BERT-base model. The proposed approach achieves 92.5% F1 score on the YELP dataset for the MenuNER task.

scholarly journals A Survey on Sentiment Analysis and Opinion Mining in Greek Social Media

Information ◽  
2021 ◽  
Vol 12 (8) ◽  
pp. 331
Author(s):  
Georgios Alexandridis ◽  
Iraklis Varlamis ◽  
Konstantinos Korovesis ◽  
George Caridakis ◽  
Panagiotis Tsantilas
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Opinion Mining ◽  
Language Model ◽  
Language Models ◽  
Current Work ◽  
Support Vector ◽  
Greek Language ◽  
Linguistic Resources ◽  
Generic Language

As the amount of content that is created on social media is constantly increasing, more and more opinions and sentiments are expressed by people in various subjects. In this respect, sentiment analysis and opinion mining techniques can be valuable for the automatic analysis of huge textual corpora (comments, reviews, tweets etc.). Despite the advances in text mining algorithms, deep learning techniques, and text representation models, the results in such tasks are very good for only a few high-density languages (e.g., English) that possess large training corpora and rich linguistic resources; nevertheless, there is still room for improvement for the other lower-density languages as well. In this direction, the current work employs various language models for representing social media texts and text classifiers in the Greek language, for detecting the polarity of opinions expressed on social media. The experimental results on a related dataset collected by the authors of the current work are promising, since various classifiers based on the language models (naive bayesian, random forests, support vector machines, logistic regression, deep feed-forward neural networks) outperform those of word or sentence-based embeddings (word2vec, GloVe), achieving a classification accuracy of more than 80%. Additionally, a new language model for Greek social media has also been trained on the aforementioned dataset, proving that language models based on domain specific corpora can improve the performance of generic language models by a margin of 2%. Finally, the resulting models are made freely available to the research community.

A novel scheme of domain transfer in document-level cross-domain sentiment classification

2021 ◽  
pp. 016555152110123
Author(s):  
Yueting Lei ◽  
Yanting Li
Keyword(s):  
Language Model ◽  
Sentiment Classification ◽  
Language Models ◽  
Product Reviews ◽  
Data Set ◽  
Emotional Words ◽  
Cross Domain ◽  
Text Ranking ◽  
Domain Transfer

The sentiment classification aims to learn sentiment features from the annotated corpus and automatically predict the sentiment polarity of new sentiment text. However, people have different ways of expressing feelings in different domains. Thus, there are important differences in the characteristics of sentimental distribution across different domains. At the same time, in certain specific domains, due to the high cost of corpus collection, there is no annotated corpus available for the classification of sentiment. Therefore, it is necessary to leverage or reuse existing annotated corpus for training. In this article, we proposed a new algorithm for extracting central sentiment sentences in product reviews, and improved the pre-trained language model Bidirectional Encoder Representations from Transformers (BERT) to achieve the domain transfer for cross-domain sentiment classification. We used various pre-training language models to prove the effectiveness of the newly proposed joint algorithm for text-ranking and emotional words extraction, and utilised Amazon product reviews data set to demonstrate the effectiveness of our proposed domain-transfer framework. The experimental results of 12 different cross-domain pairs showed that the new cross-domain classification method was significantly better than several popular cross-domain sentiment classification methods.

scholarly journals Text Classification Model Enhanced by Unlabeled Data for LaTeX Formula

2021 ◽  
Vol 11 (22) ◽  
pp. 10536
Author(s):  
Hua Cheng ◽  
Renjie Yu ◽  
Yixin Tang ◽  
Yiquan Fang ◽  
Tao Cheng
Keyword(s):  
Text Classification ◽  
Language Model ◽  
Unlabeled Data ◽  
Language Models ◽  
Classification Model ◽  
Specific Domain ◽  
Proper Nouns ◽  
Teacher Student ◽  
Generic Language ◽  
Model Training

Generic language models pretrained on large unspecific domains are currently the foundation of NLP. Labeled data are limited in most model training due to the cost of manual annotation, especially in domains including massive Proper Nouns such as mathematics and biology, where it affects the accuracy and robustness of model prediction. However, directly applying a generic language model on a specific domain does not work well. This paper introduces a BERT-based text classification model enhanced by unlabeled data (UL-BERT) in the LaTeX formula domain. A two-stage Pretraining model based on BERT(TP-BERT) is pretrained by unlabeled data in the LaTeX formula domain. A double-prediction pseudo-labeling (DPP) method is introduced to obtain high confidence pseudo-labels for unlabeled data by self-training. Moreover, a multi-rounds teacher–student model training approach is proposed for UL-BERT model training with few labeled data and more unlabeled data with pseudo-labels. Experiments on the classification of the LaTex formula domain show that the classification accuracies have been significantly improved by UL-BERT where the F1 score has been mostly enhanced by 2.76%, and lower resources are needed in model training. It is concluded that our method may be applicable to other specific domains with enormous unlabeled data and limited labelled data.

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.

INTEGRATION OF n-GRAM LANGUAGE MODELS IN MULTIPLE CLASSIFIER SYSTEMS FOR OFFLINE HANDWRITTEN TEXT LINE RECOGNITION

2008 ◽  
Vol 22 (07) ◽  
pp. 1301-1321 ◽  
Author(s):  
ROMAN BERTOLAMI ◽  
HORST BUNKE
Keyword(s):  
Language Model ◽  
Language Models ◽  
Combination Method ◽  
Text Line ◽  
Multiple Classifier Systems ◽  
Classifier Systems ◽  
Handwritten Text ◽  
Handwritten Text Recognition ◽  
Multiple Classifier ◽  
N Gram

Current multiple classifier systems for unconstrained handwritten text recognition do not provide a straightforward way to utilize language model information. In this paper, we describe a generic method to integrate a statistical n-gram language model into the combination of multiple offline handwritten text line recognizers. The proposed method first builds a word transition network and then rescores this network with an n-gram language model. Experimental evaluation conducted on a large dataset of offline handwritten text lines shows that the proposed approach improves the recognition accuracy over a reference system as well as over the original combination method that does not include a language model.

Sign in / Sign up

Export Citation Format

Share Document