A Comparison of Thai Sentence Boundary Detection Approaches Using Online Product Review Data

Thiengburanathum, Pree

doi:10.1007/978-3-030-57811-4_40

Cited by 3 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To handle excessively long comments, we performed sentence tokenization using a Conditional Random Field (CRF) model constructed from four distinct datasets established in our previous research work [48].…”

Section: A Benchmark Datasetsmentioning

confidence: 99%

SETAR: Stacking Ensemble Learning for Thai Sentiment Analysis Using RoBERTa and Hybrid Feature Representation

Thiengburanathum,

Charoenkwan

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Sentiment classification of social media posts is among the most challenging and timeconsuming tasks for analysts. This is particularly true when applied to languages that employ scriptio continua, such as the Thai language, in which there are no spaces between written words and where there is no end of sentence punctuation. Thai is considered a scarce-resource language as few datasets are available to researchers. Although machine-learning (ML) and deep-learning (DL) algorithms can identify sentiment classification polarity, the performance of the existing classification models are still inadequate. This study proposes a novel stacking ensemble learning technique for identifying sentiment classification polarity in the Thai language, SETAR. Our stacking ensemble strategy utilized the pre-trained Thai language model (WangChanBERTa), based on a Robustly Optimized BERT Pretraining Approach (RoBERTa) architecture to form a feature vector. This feature was combined with three distinct feature vectors obtained from three well-known categories, namely Word2Vec, TF-IDF, and bag-of-words, as a new hybrid sentence representation. The base learners were trained using seven chosen complex heterogeneous ML algorithms, including support vector machine (SVM), random forest (RF), extremely randomized trees (ET), light gradient boosting machine (LGBM), multi-layer perceptron (MLP), partial least squares (PLS), and logistic regression (LR) to enable the development of the final meta-learners. The results revealed that our proposed stacking ensemble model outperformed the baseline models of all classification metrics among the training and test sets, as was determined by extensive benchmarking, carried out on the four datasets, which included our developed sentiment corpus that domain experts annotated.

show abstract

Section: A Benchmark Datasetsmentioning

confidence: 99%

SETAR: Stacking Ensemble Learning for Thai Sentiment Analysis Using RoBERTa and Hybrid Feature Representation

Thiengburanathum,

Charoenkwan

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Pree Thiengburanathum [35] compared two machine learning-based methods, namely CRF and BiLSTM-CRF, for sentence boundary detection in Thai sentences. In this study, a plain text corpus from Thai web forums consisting of online product review data was used.…”

Section: Background Studymentioning

confidence: 99%

Sentence Boundary Extraction from Scientific Literature of Electric Double Layer Capacitor Domain: Tools and Techniques

et al. 2022

View full text Add to dashboard Cite

Given the growth of scientific literature on the web, particularly material science, acquiring data precisely from the literature has become more significant. Material information systems, or chemical information systems, play an essential role in discovering data, materials, or synthesis processes using the existing scientific literature. Processing and understanding the natural language of scientific literature is the backbone of these systems, which depend heavily on appropriate textual content. Appropriate textual content means a complete, meaningful sentence from a large chunk of textual content. The process of detecting the beginning and end of a sentence and extracting them as correct sentences is called sentence boundary extraction. The accurate extraction of sentence boundaries from PDF documents is essential for readability and natural language processing. Therefore, this study provides a comparative analysis of different tools for extracting PDF documents into text, which are available as Python libraries or packages and are widely used by the research community. The main objective is to find the most suitable technique among the available techniques that can correctly extract sentences from PDF files as text. The performance of the used techniques Pypdf2, Pdfminer.six, Pymupdf, Pdftotext, Tika, and Grobid is presented in terms of precision, recall, f-1 score, run time, and memory consumption. NLTK, Spacy, and Gensim Natural Language Processing (NLP) tools are used to identify sentence boundaries. Of all the techniques studied, the Grobid PDF extraction package using the NLP tool Spacy achieved the highest f-1 score of 93% and consumed the least amount of memory at 46.13 MegaBytes.

show abstract

“…The results indicated that the BiLSTM-CNN model with word, character, and POS features achieved the best performance with an F1-score of 81.34%. In contrast, the lowest F1-score of 2.16% was obtained using BiLSTM-CNN with only word and character features.However, in the study ofThiengburanathum (2021), the CRF model performed better than the BiLSTM-CRF model. In the study, CRF and BiLSTM-CRF were compared for Thai sentence segmentation on textual data related to beauty products.…”

mentioning

confidence: 90%

Thai sentence segmentation using large language models

Panitsrisit

View full text Add to dashboard Cite

Thai sentence segmentation has been on the topic of interest among Thai NLP communities. However, not much literature has explored the use of transformer-based large language models to tackle the issue. We conduct three experiments on the LST20 corpus, including (1) fine-tuning WangchanBERTa, a large language model pre-trained on Thai, across different classification tasks, (2) joint learning for clause and sentence segmentation, and (3) cross-lingual transfer using the multilingual model XLM-RoBERTa. Our findings show that WangchanBERTa outperforms other models in Thai sentence segmentation, and fine-tuning it with token and contextual information further improves its performance. However, cross-lingual transfer from English and Chinese to Thai is not effective for this task.

show abstract

A Comparison of Thai Sentence Boundary Detection Approaches Using Online Product Review Data

Cited by 3 publications

References 1 publication

SETAR: Stacking Ensemble Learning for Thai Sentiment Analysis Using RoBERTa and Hybrid Feature Representation

SETAR: Stacking Ensemble Learning for Thai Sentiment Analysis Using RoBERTa and Hybrid Feature Representation

Sentence Boundary Extraction from Scientific Literature of Electric Double Layer Capacitor Domain: Tools and Techniques

Thai sentence segmentation using large language models

Contact Info

Product

Resources

About