scholarly journals An Empirical Study of Korean Sentence Representation with Various Tokenizations

Electronics ◽  
2021 ◽  
Vol 10 (7) ◽  
pp. 845
Author(s):  
Danbi Cho ◽  
Hyunyoung Lee ◽  
Seungshik Kang
Keyword(s):  
Empirical Study ◽  
Natural Language ◽  
Sentiment Analysis ◽  
Machine Translation ◽  
Text Classification ◽  
State Of The Art ◽  
Language Models ◽  
Vocabulary Size ◽  
Analysis Task ◽  
Natural Language Process

It is important how the token unit is defined in a sentence in natural language process tasks, such as text classification, machine translation, and generation. Many studies recently utilized the subword tokenization in language models such as BERT, KoBERT, and ALBERT. Although these language models achieved state-of-the-art results in various NLP tasks, it is not clear whether the subword tokenization is the best token unit for Korean sentence embedding. Thus, we carried out sentence embedding based on word, morpheme, subword, and submorpheme, respectively, on Korean sentiment analysis. We explored the two-sentence representation methods for sentence embedding: considering the order of tokens in a sentence and not considering the order. While inputting a sentence, which is decomposed by token unit, to the two-sentence representation methods, we construct the sentence embedding with various tokenizations to find the most effective token unit for Korean sentence embedding. In our work, we confirmed: the robustness of the subword unit for out-of-vocabulary (OOV) problems compared to other token units, the disadvantage of replacing whitespace with a particular symbol in the sentiment analysis task, and that the optimal vocabulary size is 16K in subword and submorpheme tokenization. We empirically noticed that the subword, which was tokenized by a vocabulary size of 16K without replacement of whitespace, was the most effective for sentence embedding on the Korean sentiment analysis task.

scholarly journals Evaluating Multilingual BERT for Estonian

2020 ◽  
Author(s):  
Claudia Kittask ◽  
Kirill Milintsevich ◽  
Kairit Sirts
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Text Classification ◽  
State Of The Art ◽  
Language Models ◽  
Neural Models ◽  
Comparable Level ◽  
Art Performance ◽  
Multiple Languages

Recently, large pre-trained language models, such as BERT, have reached state-of-the-art performance in many natural language processing tasks, but for many languages, including Estonian, BERT models are not yet available. However, there exist several multilingual BERT models that can handle multiple languages simultaneously and that have been trained also on Estonian data. In this paper, we evaluate four multilingual models—multilingual BERT, multilingual distilled BERT, XLM and XLM-RoBERTa—on several NLP tasks including POS and morphological tagging, NER and text classification. Our aim is to establish a comparison between these multilingual BERT models and the existing baseline neural models for these tasks. Our results show that multilingual BERT models can generalise well on different Estonian NLP tasks outperforming all baselines models for POS and morphological tagging and text classification, and reaching the comparable level with the best baseline for NER, with XLM-RoBERTa achieving the highest results compared with other multilingual models.

scholarly journals Towards Improving Open Student Answer Assessment using Pretrained Transformers

2021 ◽  
Vol 34 (1) ◽  
Author(s):  
Nisrine Ait Khayi ◽  
Vasile Rus ◽  
Lasang Tamang
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Transfer Learning ◽  
Language Processing ◽  
Text Classification ◽  
Question Answering ◽  
State Of The Art ◽  
Language Models ◽  
Assessment Task ◽  
Fine Tune

The transfer learning pretraining-finetuning  paradigm has revolutionized the natural language processing field yielding state-of the art results in  several subfields such as text classification and question answering. However, little work has been done investigating pretrained language models for the  open student answer assessment task. In this paper, we fine tune pretrained T5, BERT, RoBERTa, DistilBERT, ALBERT and XLNet models on the DT-Grade dataset which contains freely generated (or open) student answers together with judgment of their correctness. The experimental results demonstrated the effectiveness of these models based on the transfer learning pretraining-finetuning paradigm for open student answer assessment. An improvement of 8%-15% in accuracy was obtained over previous methods. Particularly, a T5 based method led to state-of-the-art results with an accuracy and F1 score of 0.88.

Deep Learning for text in limted data settings

2020 ◽  
Author(s):  
Pathikkumar Patel ◽  
Bhargav Lad ◽  
Jinan Fiaidhi
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Transfer Learning ◽  
Text Classification ◽  
State Of The Art ◽  
Time Series Forecasting ◽  
Text Data ◽  
Performance Levels

During the last few years, RNN models have been extensively used and they have proven to be better for sequence and text data. RNNs have achieved state-of-the-art performance levels in several applications such as text classification, sequence to sequence modelling and time series forecasting. In this article we will review different Machine Learning and Deep Learning based approaches for text data and look at the results obtained from these methods. This work also explores the use of transfer learning in NLP and how it affects the performance of models on a specific application of sentiment analysis.

scholarly journals Pre-Trained Transformer-Based Language Models for Sundanese

2021 ◽  
Author(s):  
Wilson Wongso ◽  
Henry Lucky ◽  
Derwin Suhartono
Keyword(s):  
Natural Language ◽  
Text Classification ◽  
Training Data ◽  
Language Models ◽  
Classification Task ◽  
Language Understanding ◽  
Training Corpus ◽  
Low Resource ◽  
Corpus Size ◽  
Fine Tune

Abstract The Sundanese language has over 32 million speakers worldwide, but the language has reaped little to no benefits from the recent advances in natural language understanding. Like other low-resource languages, the only alternative is to fine-tune existing multilingual models. In this paper, we pre-trained three monolingual Transformer-based language models on Sundanese data. When evaluated on a downstream text classification task, we found that most of our monolingual models outperformed larger multilingual models despite the smaller overall pre-training data. In the subsequent analyses, our models benefited strongly from the Sundanese pre-training corpus size and do not exhibit socially biased behavior. We released our models for other researchers and practitioners to use.

scholarly journals Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation

2019 ◽  
Vol 33 ◽  
pp. 6626-6633
Author(s):  
Xiang Kong ◽  
Qizhe Xie ◽  
Zihang Dai ◽  
Eduard Hovy
Keyword(s):  
Machine Translation ◽  
State Of The Art ◽  
The State ◽  
Computational Time ◽  
Memory Consumption ◽  
Image Captioning ◽  
Vocabulary Size ◽  
Language Generation ◽  
Practical Applications ◽  
Coding Schemes

Mixture of Softmaxes (MoS) has been shown to be effective at addressing the expressiveness limitation of Softmax-based models. Despite the known advantage, MoS is practically sealed by its large consumption of memory and computational time due to the need of computing multiple Softmaxes. In this work, we set out to unleash the power of MoS in practical applications by investigating improved word coding schemes, which could effectively reduce the vocabulary size and hence relieve the memory and computation burden. We show both BPE and our proposed Hybrid-LightRNN lead to improved encoding mechanisms that can halve the time and memory consumption of MoS without performance losses. With MoS, we achieve an improvement of 1.5 BLEU scores on IWSLT 2014 German-to-English corpus and an improvement of 0.76 CIDEr score on image captioning. Moreover, on the larger WMT 2014 machine translation dataset, our MoSboosted Transformer yields 29.6 BLEU score for English-toGerman and 42.1 BLEU score for English-to-French, outperforming the single-Softmax Transformer by 0.9 and 0.4 BLEU scores respectively and achieving the state-of-the-art result on WMT 2014 English-to-German task.

scholarly journals Biomedical Concept Recognition Using Deep Neural Sequence Models

2019 ◽  
Author(s):  
Negacy D. Hailu ◽  
Michael Bada ◽  
Asmelash Teka Hadgu ◽  
Lawrence E. Hunter
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Language Processing ◽  
State Of The Art ◽  
Conditional Random Field ◽  
Concept Recognition ◽  
Performance Improvements ◽  
Art Performance

AbstractBackgroundthe automated identification of mentions of ontological concepts in natural language texts is a central task in biomedical information extraction. Despite more than a decade of effort, performance in this task remains below the level necessary for many applications.Resultsrecently, applications of deep learning in natural language processing have demonstrated striking improvements over previously state-of-the-art performance in many related natural language processing tasks. Here we demonstrate similarly striking performance improvements in recognizing biomedical ontology concepts in full text journal articles using deep learning techniques originally developed for machine translation. For example, our best performing system improves the performance of the previous state-of-the-art in recognizing terms in the Gene Ontology Biological Process hierarchy, from a previous best F1 score of 0.40 to an F1 of 0.70, nearly halving the error rate. Nearly all other ontologies show similar performance improvements.ConclusionsA two-stage concept recognition system, which is a conditional random field model for span detection followed by a deep neural sequence model for normalization, improves the state-of-the-art performance for biomedical concept recognition. Treating the biomedical concept normalization task as a sequence-to-sequence mapping task similar to neural machine translation improves performance.

scholarly journals Text: An R-package for Analyzing and Visualizing Human Language Using Natural Language Processing and Deep Learning

2021 ◽  
Author(s):  
Oscar Nils Erik Kjell ◽  
H. Andrew Schwartz ◽  
Salvatore Giorgi
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Rating Scale ◽  
State Of The Art ◽  
R Package ◽  
Language Models ◽  
Categorical Variables ◽  
Human Language

The language that individuals use for expressing themselves contains rich psychological information. Recent significant advances in Natural Language Processing (NLP) and Deep Learning (DL), namely transformers, have resulted in large performance gains in tasks related to understanding natural language such as machine translation. However, these state-of-the-art methods have not yet been made easily accessible for psychology researchers, nor designed to be optimal for human-level analyses. This tutorial introduces text (www.r-text.org), a new R-package for analyzing and visualizing human language using transformers, the latest techniques from NLP and DL. Text is both a modular solution for accessing state-of-the-art language models and an end-to-end solution catered for human-level analyses. Hence, text provides user-friendly functions tailored to test hypotheses in social sciences for both relatively small and large datasets. This tutorial describes useful methods for analyzing text, providing functions with reliable defaults that can be used off-the-shelf as well as providing a framework for the advanced users to build on for novel techniques and analysis pipelines. The reader learns about six methods: 1) textEmbed: to transform text to traditional or modern transformer-based word embeddings (i.e., numeric representations of words); 2) textTrain: to examine the relationships between text and numeric/categorical variables; 3) textSimilarity and 4) textSimilarityTest: to computing semantic similarity scores between texts and significance test the difference in meaning between two sets of texts; and 5) textProjection and 6) textProjectionPlot: to examine and visualize text within the embedding space according to latent or specified construct dimensions (e.g., low to high rating scale scores).

scholarly journals Neural Machine Translation between Vietnamese and English: an Empirical Study

2019 ◽  
Vol 35 (2) ◽  
pp. 147-166 ◽  
Author(s):  
Hong-Hai Phan-Vu ◽  
Viet Trung Tran ◽  
Van Nam Nguyen ◽  
Hoang Vu Dang ◽  
Phan Thuan Do
Keyword(s):  
Neural Networks ◽  
Empirical Study ◽  
Machine Translation ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Neural Models ◽  
Neural Machine Translation ◽  
Parallel Corpora ◽  
Parameter Search ◽  
Popular Language

Machine translation is shifting to an end-to-end approach based on deep neural networks. The state of the art achieves impressive results for popular language pairs such as English - French or English - Chinese. However for English - Vietnamese the shortage of parallel corpora and expensive hyper-parameter search present practical challenges to neural-based approaches. This paper highlights our efforts on improving English-Vietnamese translations in two directions: (1) Building the largest open Vietnamese - English corpus to date, and (2) Extensive experiments with the latest neural models to achieve the highest BLEU scores. Our experiments provide practical examples of effectively employing different neural machine translation models with low-resource language pairs.

scholarly journals Concept Recognition as a Machine Translation Problem

2020 ◽  
Author(s):  
Mayla R Boguslav ◽  
Negacy D Hailu ◽  
Michael Bada ◽  
William A Baumgartner ◽  
Lawrence E Hunter
Keyword(s):  
Machine Learning ◽  
Machine Translation ◽  
Language Processing ◽  
State Of The Art ◽  
Training Data ◽  
Language Models ◽  
Alternative Methods ◽  
Automated Assignment ◽  
Concept Recognition ◽  
Alternative Approaches

AbstractBackgroundAutomated assignment of specific ontology concepts to mentions in text is a critical task in biomedical natural language processing, and the subject of many open shared tasks. Although the current state of the art involves the use of neural network language models as a post-processing step, the very large number of ontology classes to be recognized and the limited amount of gold-standard training data has impeded the creation of end-to-end systems based entirely on machine learning. Recently, Hailu et al. recast the concept recognition problem as a type of machine translation and demonstrated that sequence-to-sequence machine learning models had the potential to outperform multi-class classification approaches. Here we systematically characterize the factors that contribute to the accuracy and efficiency of several approaches to sequence-to-sequence machine learning.ResultsWe report on our extensive studies of alternative methods and hyperparameter selections. The results not only identify the best-performing systems and parameters across a wide variety of ontologies but also illuminate about the widely varying resource requirements and hyperparameter robustness of alternative approaches. Analysis of the strengths and weaknesses of such systems suggest promising avenues for future improvements as well as design choices that can increase computational efficiency with small costs in performance. Bidirectional Encoder Representations from Transformers for Biomedical Text Mining (BioBERT) for span detection (as previously found) along with the Open-source Toolkit for Neural Machine Translation (OpenNMT) for concept normalization achieve state-of-the-art performance for most ontologies in CRAFT Corpus. This approach uses substantially fewer computational resources, including hardware, memory, and time than several alternative approaches.ConclusionsMachine translation is a promising avenue for fully machine-learning-based concept recognition that achieves state-of-the-art results on the CRAFT Corpus, evaluated via a direct comparison to previous results from the 2019 CRAFT Shared Task. Experiments illuminating the reasons for the surprisingly good performance of sequence-to-sequence methods targeting ontology identifiers suggest that further progress may be possible by mapping to alternative target concept representations. All code and models can be found at: https://github.com/UCDenver-ccp/Concept-Recognition-as-Translation.

scholarly journals Leveraging Pre-trained Checkpoints for Sequence Generation Tasks

2020 ◽  
Vol 8 ◽  
pp. 264-280
Author(s):  
Sascha Rothe ◽  
Shashi Narayan ◽  
Aliaksei Severyn
Keyword(s):  
Natural Language Processing ◽  
Empirical Study ◽  
Natural Language ◽  
Language Processing ◽  
State Of The Art ◽  
Text Summarization ◽  
Neural Models ◽  
Language Understanding ◽  
Sequence Generation ◽  
Compute Time

Unsupervised pre-training of large neural models has recently revolutionized Natural Language Processing. By warm-starting from the publicly released checkpoints, NLP practitioners have pushed the state-of-the-art on multiple benchmarks while saving significant amounts of compute time. So far the focus has been mainly on the Natural Language Understanding tasks. In this paper, we demonstrate the efficacy of pre-trained checkpoints for Sequence Generation. We developed a Transformer-based sequence-to-sequence model that is compatible with publicly available pre-trained BERT, GPT-2, and RoBERTa checkpoints and conducted an extensive empirical study on the utility of initializing our model, both encoder and decoder, with these checkpoints. Our models result in new state-of-the-art results on Machine Translation, Text Summarization, Sentence Splitting, and Sentence Fusion.

Sign in / Sign up

Export Citation Format

Share Document