Dual-cell differentiable architecture search for language modeling

2021 ◽  
pp. 1-8
Author(s):  
Quan Wan ◽  
Lin Wu ◽  
Zhengtao Yu
Keyword(s):  
Language Processing ◽  
Network Architecture ◽  
Language Model ◽  
Model Performance ◽  
Input Sequence ◽  
Search Space ◽  
Language Modeling ◽  
Information Storage ◽  
Data Set ◽  
Initial Results

Initial results of neural architecture search (NAS) in natural language processing (NLP) have been achieved, but the search space of most NAS methods is based on the simplest recurrent cell and thus does not consider the modeling of long sequences. The remote information tends to disappear gradually when the input sequence is long, resulting in poor model performance. In this paper, we present an approach based on dual cells to search for a better-performing network architecture. We construct a search space that is more compatible with language modeling tasks by adding an information storage cell inside the search cell, so that we can make better use of the remote information of the sequence and improve the performance of the model. The language model searched by our method achieves better results than those of the baseline method on the Penn Treebank data set and WikiText-2 data set.

scholarly journals Language modeling and bidirectional coders representations: an overview of key technologies

Informatics ◽  
2021 ◽  
Vol 17 (4) ◽  
pp. 61-72
Author(s):  
D. I. Kachkou
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Text Processing ◽  
Language Model ◽  
Language Modeling ◽  
Attention Mechanism ◽  
Data Set ◽  
Effective Learning ◽  
Key Technologies ◽  
Model Improvement

The article is an essay on the development of technologies for natural language processing, which formed the basis of BERT (Bidirectional Encoder Representations from Transformers), a language model from Google, showing high results on the whole class of problems associated with the understanding of natural language. Two key ideas implemented in BERT are knowledge transfer and attention mechanism. The model is designed to solve two problems on a large unlabeled data set and can reuse the identified language patterns for effective learning for a specific text processing problem. Architecture Transformer is based on the attention mechanism, i.e. it involves evaluation of relationships between input data tokens. In addition, the article notes strengths and weaknesses of BERT and the directions for further model improvement.

scholarly journals Interactive NLP in Clinical Care: Identifying Incidental Findings in Radiology Reports

2019 ◽  
Vol 10 (04) ◽  
pp. 655-669
Author(s):  
Gaurav Trivedi ◽  
Esmaeel R. Dadashzadeh ◽  
Robert M. Handzel ◽  
Wendy W. Chapman ◽  
Shyam Visweswaran ◽  
...  
Keyword(s):  
Language Processing ◽  
Gold Standard ◽  
Incidental Findings ◽  
User Study ◽  
Clinical Care ◽  
Model Performance ◽  
Data Set ◽  
Radiology Reports ◽  
System Usability Scale ◽  
And Control

Abstract Background Despite advances in natural language processing (NLP), extracting information from clinical text is expensive. Interactive tools that are capable of easing the construction, review, and revision of NLP models can reduce this cost and improve the utility of clinical reports for clinical and secondary use. Objectives We present the design and implementation of an interactive NLP tool for identifying incidental findings in radiology reports, along with a user study evaluating the performance and usability of the tool. Methods Expert reviewers provided gold standard annotations for 130 patient encounters (694 reports) at sentence, section, and report levels. We performed a user study with 15 physicians to evaluate the accuracy and usability of our tool. Participants reviewed encounters split into intervention (with predictions) and control conditions (no predictions). We measured changes in model performance, the time spent, and the number of user actions needed. The System Usability Scale (SUS) and an open-ended questionnaire were used to assess usability. Results Starting from bootstrapped models trained on 6 patient encounters, we observed an average increase in F1 score from 0.31 to 0.75 for reports, from 0.32 to 0.68 for sections, and from 0.22 to 0.60 for sentences on a held-out test data set, over an hour-long study session. We found that tool helped significantly reduce the time spent in reviewing encounters (134.30 vs. 148.44 seconds in intervention and control, respectively), while maintaining overall quality of labels as measured against the gold standard. The tool was well received by the study participants with a very good overall SUS score of 78.67. Conclusion The user study demonstrated successful use of the tool by physicians for identifying incidental findings. These results support the viability of adopting interactive NLP tools in clinical care settings for a wider range of clinical applications.

scholarly journals Alternating Language Modeling for Cross-Lingual Pre-Training

2020 ◽  
Vol 34 (05) ◽  
pp. 9386-9393
Author(s):  
Jian Yang ◽  
Shuming Ma ◽  
Dongdong Zhang ◽  
ShuangZhi Wu ◽  
Zhoujun Li ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Machine Translation ◽  
Language Processing ◽  
Language Model ◽  
Language Modeling ◽  
Training Methods ◽  
Training Method ◽  
Source Sentence ◽  
The Rich ◽  
Cross Lingual

Language model pre-training has achieved success in many natural language processing tasks. Existing methods for cross-lingual pre-training adopt Translation Language Model to predict masked words with the concatenation of the source sentence and its target equivalent. In this work, we introduce a novel cross-lingual pre-training method, called Alternating Language Modeling (ALM). It code-switches sentences of different languages rather than simple concatenation, hoping to capture the rich cross-lingual context of words and phrases. More specifically, we randomly substitute source phrases with target translations to create code-switched sentences. Then, we use these code-switched data to train ALM model to learn to predict words of different languages. We evaluate our pre-training ALM on the downstream tasks of machine translation and cross-lingual classification. Experiments show that ALM can outperform the previous pre-training methods on three benchmarks.1

scholarly journals Designing convolutional neural networks with constrained evolutionary piecemeal training

2021 ◽  
Author(s):  
Dolly Sapra ◽  
Andy D. Pimentel
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Language Processing ◽  
Network Architecture ◽  
High Performance ◽  
Search Algorithm ◽  
Search Space ◽  
Pareto Optimal Set

AbstractThe automated architecture search methodology for neural networks is known as Neural Architecture Search (NAS). In recent times, Convolutional Neural Networks (CNNs) designed through NAS methodologies have achieved very high performance in several fields, for instance image classification and natural language processing. Our work is in the same domain of NAS, where we traverse the search space of neural network architectures with the help of an evolutionary algorithm which has been augmented with a novel approach of piecemeal-training. In contrast to the previously published NAS techniques, wherein the training with given data is considered an isolated task to estimate the performance of neural networks, our work demonstrates that a neural network architecture and the related weights can be jointly learned by combining concepts of the traditional training process and evolutionary architecture search in a single algorithm. The consolidation has been realised by breaking down the conventional training technique into smaller slices and collating them together with an integrated evolutionary architecture search algorithm. The constraints on architecture search space are placed by limiting its various parameters within a specified range of values, consequently regulating the neural network’s size and memory requirements. We validate this concept on two vastly different datasets, namely, the CIFAR-10 dataset in the domain of image classification, and PAMAP2 dataset in the Human Activity Recognition (HAR) domain. Starting from randomly initialized and untrained CNNs, the algorithm discovers models with competent architectures, which after complete training, reach an accuracy of of 92.5% for CIFAR-10 and 94.36% PAMAP2. We further extend the algorithm to include an additional conflicting search objective: the number of parameters of the neural network. Our multi-objective algorithm produces a Pareto optimal set of neural networks, by optimizing the search for both the accuracy and the parameter count, thus emphasizing the versatility of our approach.

scholarly journals Exploring the Data Efficiency of Cross-Lingual Post-Training in Pretrained Language Models

2021 ◽  
Vol 11 (5) ◽  
pp. 1974 ◽  
Author(s):  
Chanhee Lee ◽  
Kisu Yang ◽  
Taesun Whang ◽  
Chanjun Park ◽  
Andrew Matteson ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Language Model ◽  
Language Modeling ◽  
Language Models ◽  
Low Resource ◽  
High Resource ◽  
Cross Lingual ◽  
Data Efficiency

Language model pretraining is an effective method for improving the performance of downstream natural language processing tasks. Even though language modeling is unsupervised and thus collecting data for it is relatively less expensive, it is still a challenging process for languages with limited resources. This results in great technological disparity between high- and low-resource languages for numerous downstream natural language processing tasks. In this paper, we aim to make this technology more accessible by enabling data efficient training of pretrained language models. It is achieved by formulating language modeling of low-resource languages as a domain adaptation task using transformer-based language models pretrained on corpora of high-resource languages. Our novel cross-lingual post-training approach selectively reuses parameters of the language model trained on a high-resource language and post-trains them while learning language-specific parameters in the low-resource language. We also propose implicit translation layers that can learn linguistic differences between languages at a sequence level. To evaluate our method, we post-train a RoBERTa model pretrained in English and conduct a case study for the Korean language. Quantitative results from intrinsic and extrinsic evaluations show that our method outperforms several massively multilingual and monolingual pretrained language models in most settings and improves the data efficiency by a factor of up to 32 compared to monolingual training.

scholarly journals Surrogate-guided sampling designs for classification of rare outcomes from electronic medical records data

Biostatistics ◽  
2020 ◽  
Author(s):  
W Katherine Tan ◽  
Patrick J Heagerty
Keyword(s):  
Machine Learning ◽  
Clinical Outcomes ◽  
Language Processing ◽  
Large Scale ◽  
Model Performance ◽  
Learning Performance ◽  
Accurate Identification ◽  
Text Data ◽  
Data Set ◽  
The Impact

Summary Scalable and accurate identification of specific clinical outcomes has been enabled by machine-learning applied to electronic medical record systems. The development of classification models requires the collection of a complete labeled data set, where true clinical outcomes are obtained by human expert manual review. For example, the development of natural language processing algorithms requires the abstraction of clinical text data to obtain outcome information necessary for training models. However, if the outcome is rare then simple random sampling results in very few cases and insufficient information to develop accurate classifiers. Since large scale detailed abstraction is often expensive, time-consuming, and not feasible, more efficient strategies are needed. Under such resource constrained settings, we propose a class of enrichment sampling designs, where selection for abstraction is stratified by auxiliary variables related to the true outcome of interest. Stratified sampling on highly specific variables results in targeted samples that are more enriched with cases, which we show translates to increased model discrimination and better statistical learning performance. We provide mathematical details and simulation evidence that links sampling designs to their resulting prediction model performance. We discuss the impact of our proposed sampling on both model training and validation. Finally, we illustrate the proposed designs for outcome label collection and subsequent machine-learning, using radiology report text data from the Lumbar Imaging with Reporting of Epidemiology study.

scholarly journals Using Character-Level and Entity-Level Representations to Enhance Bidirectional Encoder Representation From Transformers-Based Clinical Semantic Textual Similarity Model: ClinicalSTS Modeling Study (Preprint)

2020 ◽  
Author(s):  
Ying Xiong ◽  
Shuai Chen ◽  
Qingcai Chen ◽  
Jun Yan ◽  
Buzhou Tang
Keyword(s):  
Language Processing ◽  
Pearson Correlation ◽  
Language Model ◽  
Model Performance ◽  
Clinical Text ◽  
Sentence Level ◽  
Level Information ◽  
Semantically Enhanced ◽  
Copy And Paste ◽  
Semantic Textual Similarity

BACKGROUND With the popularity of electronic health records (EHRs), the quality of health care has been improved. However, there are also some problems caused by EHRs, such as the growing use of copy-and-paste and templates, resulting in EHRs of low quality in content. In order to minimize data redundancy in different documents, Harvard Medical School and Mayo Clinic organized a national natural language processing (NLP) clinical challenge (n2c2) on clinical semantic textual similarity (ClinicalSTS) in 2019. The task of this challenge is to compute the semantic similarity among clinical text snippets. OBJECTIVE In this study, we aim to investigate novel methods to model ClinicalSTS and analyze the results. METHODS We propose a semantically enhanced text matching model for the 2019 n2c2/Open Health NLP (OHNLP) challenge on ClinicalSTS. The model includes 3 representation modules to encode clinical text snippet pairs at different levels: (1) character-level representation module based on convolutional neural network (CNN) to tackle the out-of-vocabulary problem in NLP; (2) sentence-level representation module that adopts a pretrained language model bidirectional encoder representation from transformers (BERT) to encode clinical text snippet pairs; and (3) entity-level representation module to model clinical entity information in clinical text snippets. In the case of entity-level representation, we compare 2 methods. One encodes entities by the entity-type label sequence corresponding to text snippet (called entity I), whereas the other encodes entities by their representation in MeSH, a knowledge graph in the medical domain (called entity II). RESULTS We conduct experiments on the ClinicalSTS corpus of the 2019 n2c2/OHNLP challenge for model performance evaluation. The model only using BERT for text snippet pair encoding achieved a Pearson correlation coefficient (PCC) of 0.848. When character-level representation and entity-level representation are individually added into our model, the PCC increased to 0.857 and 0.854 (entity I)/0.859 (entity II), respectively. When both character-level representation and entity-level representation are added into our model, the PCC further increased to 0.861 (entity I) and 0.868 (entity II). CONCLUSIONS Experimental results show that both character-level information and entity-level information can effectively enhance the BERT-based STS model.

scholarly journals Rare Words: A Major Problem for Contextualized Embeddings and How to Fix it by Attentive Mimicking

2020 ◽  
Vol 34 (05) ◽  
pp. 8766-8774 ◽  
Author(s):  
Timo Schick ◽  
Hinrich Schütze
Keyword(s):  
Neural Network ◽  
Natural Language Processing ◽  
Language Processing ◽  
Deep Neural Network ◽  
Language Model ◽  
Language Modeling ◽  
Fine Tuning ◽  
Language Models ◽  
Network Architectures ◽  
Semantic Properties

Pretraining deep neural network architectures with a language modeling objective has brought large improvements for many natural language processing tasks. Exemplified by BERT, a recently proposed such architecture, we demonstrate that despite being trained on huge amounts of data, deep language models still struggle to understand rare words. To fix this problem, we adapt Attentive Mimicking, a method that was designed to explicitly learn embeddings for rare words, to deep language models. In order to make this possible, we introduce one-token approximation, a procedure that enables us to use Attentive Mimicking even when the underlying language model uses subword-based tokenization, i.e., it does not assign embeddings to all words. To evaluate our method, we create a novel dataset that tests the ability of language models to capture semantic properties of words without any task-specific fine-tuning. Using this dataset, we show that adding our adapted version of Attentive Mimicking to BERT does substantially improve its understanding of rare words.

scholarly journals Efficient Search Mechanism from Large Scale Corpora for Domain-Specific Language Modeling in Speech Recognition

2019 ◽  
Vol 8 (6) ◽  
pp. 1682-1689
Keyword(s):  
Big Data ◽  
Speech Recognition ◽  
Language Model ◽  
Search Space ◽  
Document Retrieval ◽  
Language Modeling ◽  
Domain Specific Language ◽  
Specific Language ◽  
Recognition Process ◽  
Domain Specific

With the Internet and the World Wide Web revolution, large corpora in variety of forms are germinating ceaselessly that can be manifested as big data. One obligatory area for the usage of such large corpora is language modeling for large vocabulary continuous speech recognition. Language modeling is an indispensable module in speech recognition architecture, which plays a vital role in reducing the search space during the recognition process. Additionally, the language model that is contiguous to the domain of the speech can dwindle the search space and escalate the recognition accuracy. In this paper, an efficient searching mechanism for domain-specific document retrieval from the large corpora has been elucidated using Elasticsearch which is a distributed and an efficient search engine for big data. This assisted us in tuning the language model in accordance with the domain and also by reducing the search time by more than 90% in comparison to conventional search and retrieval mechanism used in our earlier work. A word level and a phrase level retrieval process for creating domain-specific language model has been implemented. The evaluation of the system is performed on the basis of word error rate (WER) and perplexity (PPL) of the speech recognition system. The results shows nearly 10% decrease on WER and a major reduction in the PPL that helped in boosting the performance of the speech recognition process. From the results, it can be consummated that Elasticsearch is an efficient mechanism for domain specific document retrieval from large corpora rather than using topic modeling toolkits

scholarly journals Graph Neural Architecture Search

2020 ◽  
Author(s):  
Yang Gao ◽  
Hong Yang ◽  
Peng Zhang ◽  
Chuan Zhou ◽  
Yue Hu
Keyword(s):  
Neural Networks ◽  
Network Architecture ◽  
Domain Knowledge ◽  
Search Space ◽  
Recurrent Network ◽  
Validation Data ◽  
Data Set ◽  
Neural Architecture ◽  
Real World Datasets ◽  
Graph Neural Networks

Graph neural networks (GNNs) emerged recently as a powerful tool for analyzing non-Euclidean data such as social network data. Despite their success, the design of graph neural networks requires heavy manual work and domain knowledge. In this paper, we present a graph neural architecture search method (GraphNAS) that enables automatic design of the best graph neural architecture based on reinforcement learning. Specifically, GraphNAS uses a recurrent network to generate variable-length strings that describe the architectures of graph neural networks, and trains the recurrent network with policy gradient to maximize the expected accuracy of the generated architectures on a validation data set. Furthermore, to improve the search efficiency of GraphNAS on big networks, GraphNAS restricts the search space from an entire architecture space to a sequential concatenation of the best search results built on each single architecture layer. Experiments on real-world datasets demonstrate that GraphNAS can design a novel network architecture that rivals the best human-invented architecture in terms of validation set accuracy. Moreover, in a transfer learning task we observe that graph neural architectures designed by GraphNAS, when transferred to new datasets, still gain improvement in terms of prediction accuracy.

Sign in / Sign up

Export Citation Format

Share Document