PBPakpoom Buabthong

Pakpoom Buabthong

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Pakpoom Buabthong has a total of 61 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Identification of Important Sugar Binary Mixtures Found in Biorefineries Using Terahertz Time-Domain Spectroscopy

    by Rungroj Jintamethasawat, Pacharamon Somboonsaksri, Nichakarn Termsaithong, Jia-Yi Chia, Sutarat Thongratkaew, Kamonwat Nakason, Thitaphat Ngernsutivorakul, Kantapong Sucharitpongpan, Pongtanawat Khemthong, Nantarat Srisuai, et al.

    Terahertz (THz) spectroscopy has shown great promise in identifying and quantifying biomolecules whose vibrational modes fall within the terahertz frequency range. This work aims to develop a framework for determining sugar compositions in common chemical reactions that convert C5 and C6 sugars to higher-value products. To simulate these reaction environments, we prepared three types of solid binary mixtures as pellets: glucose-sorbitol, xylose-xylitol, and glucose-fructose, all with varying concentration ratios. Using a terahertz time-domain spectroscopy (THz-TDS) system, we acquired THz spectra of those binary mixture pellets and implemented four types of linear and nonlinear machine learning models to predict sugar compositions from the acquired spectra. Prediction results from test data sets suggest that support vector regression (SVR) shows superior performance over the rest of machine learning models in all binary mixture experiments, with the average and best root-mean-square errors (RMSE) of 5.42 and 2.83% w/w, respectively. Additionally, we investigated the capability of THz spectroscopy to differentiate molecular isomer structures by preparing sample pellets of pure d-xylose and l-xylose. Our results reveal that THz spectroscopy poses challenges in classifying enantiomerism (d-xylose and l-xylose pairs) but still shows potential for identifying functional isomerism (glucose and fructose pairs). These findings demonstrate that THz spectroscopy, combined with optimized machine learning models, offers a promising alternative to gold-standard techniques by enabling simple, rapid, and nondestructive monitoring of chemical compositions during the sugar synthesis.


  • Open Access

    Streamlining event extraction with a simplified annotation framework

    by Chanatip Saetia, Areeya Thonglong, Thanpitcha Amornchaiteera, Tawunrat Chalothorn, Supawat Taerungruang, Pakpoom Buabthong

    Event extraction, grounded in semantic relationships, can serve as a simplified relation extraction. In this study, we propose an efficient open-domain event annotation framework tailored for subsequent information extraction, with a specific focus on its applicability to low-resource languages. The proposed event annotation method, which is based on event semantic elements, demonstrates substantial time-efficiency gains over traditional Universal Dependencies (UD) tagging. We show how language-specific pretraining outperforms multilingual counterparts in entity and relation extraction tasks and emphasize the importance of task- and language-specific fine-tuning for optimal model performance. Furthermore, we demonstrate the improvement of model performance upon integrating UD information during pre-training, achieving the F1 score of 71.16 and 60.43% for entity and relation extraction respectively. In addition, we showcase the usage of our extracted event graph for improving node classification in a retail banking domain. This work provides valuable guidance on improving information extraction and outlines a methodology for developing training datasets, particularly for low-resource languages.


  • Open Access

    Financial Product Ontology Population with Large Language Models

    by Chanatip Saetia, Jiratha Phruetthiset, Tawunrat Chalothorn, Monchai Lertsutthiwong, Supawat Taerungruang, Pakpoom Buabthong

    Chanatip Saetia, Jiratha Phruetthiset, Tawunrat Chalothorn, Monchai Lertsutthiwong, Supawat Taerungruang, Pakpoom Buabthong. Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing. 2024.


  • A Cross-Document Coreference Resolution Approach to Low-Resource Languages

    by Nathanon Theptakob, Thititorn Seneewong Na Ayutthaya, Chanatip Saetia, Tawunrat Chalothorn, Pakpoom Buabthong


  • Open Access

    How to Progressively Build Thai Spelling Correction Systems?

    by Anuruth Lertpiya, Tawunrat Chalothorn, Pakpoom Buabthong

    Neural-based sequence-to-sequence methods (Seq2Seq) have proven to be highly effective for Context-sensitive Thai spelling correction. However, they also inherit the drawbacks of Seq2Seq, such as a fixed vocabulary and large data requirements. However, dictionary-based methods and their typical applications are insufficiently robust to produce corrections with reduced error rates. These drawbacks inhibit the application of these methods in a broader range of use cases. In this paper, we provide a practical guide on how to build correction systems progressively and efficiently with three main contributions. First, we present a process for efficiently and progressively producing training data for both neural-based and dictionary-based methods. Our annotation process enables existing methods to be trained with only two percent of the data hand annotated. Second, we propose the Extendable Neural Contextual Corrector (XNCC), a novel text correction approach that decouples the dictionary from the neural model. This enables the dictionary to be extended post-training. Finally, we compare text correction systems with various configurations to demonstrate how these systems can be effectively used to produce corrections. Our experiments show that (1) minor changes to dictionary-based methods can significantly improve correction performance, (2) neural-based correction systems can be trained using a fraction of the data, and (3) XNCC can have the dictionary extended to generalize to new data without re-training. Lastly, we provide recommendations for progressively building text correction systems at multiple levels of implementation effort based on our findings.


  • Failure Modes of Platinized pn+-GaInP Photocathodes for Solar-Driven H2 Evolution

    by Weilai Yu, Pakpoom Buabthong, James L. Young, Zachary P. Ifkovits, Sean T. Byrne, Myles A. Steiner, Todd G. Deutsch, Nathan S. Lewis

    The long-term stability for the hydrogen-evolution reaction (HER) of homojunction pn(+)-Ga0.52In0.48P photocathodes (band gap = 1.8 eV) with an electrodeposited Pt catalyst (pn(+)-GaInP/Pt) has been systematically evaluated in both acidic and alkaline electrolytes. Electrode dissolution during chronoamperometry was correlated with changes over time in the current density-potential (J-E) behavior to reveal the underlying failure mechanism. Pristine pn(+)-GaInP/Pt photocathodes yielded an open-circuit photopotential (E-oc) as positive as >1.0 V vs the potential of the reversible hydrogen electrode (RHE) and a light limited current density (J(ph)) of >12 mA cm(-2)(1-sun illumination). However, E-oc and J(ph) gradually degraded at either pH 0 or pH 14. The performance degradation was attributed to three different failure modes: (1) gradual thinning of the n(+)-emitter layer due to GaInP dissolution in acid; (2) active corrosion of the underlying GaAs substrate at positive potentials causing delamination of the upper GaInP epilayers; and (3) direct GaAs/electrolyte contact compromising the operational stability of the device. This work reveals the importance of both substrate stability and structural integrity of integrated photoelectrodes toward stable solar fuel generation.


  • Data-Driven Synthesis of Broadband Earthquake Ground Motions Using Artificial Intelligence

    by Manuel A. Florez, Michaelangelo Caporale, Pakpoom Buabthong, Zachary E. Ross, Domniki Asimaki, Men-Andrin Meier

    Robust estimation of ground motions generated by scenario earthquakes is critical for many engineering applications. We leverage recent advances in generative adversarial networks (GANs) to develop a new framework for synthesizing earthquake acceleration time histories. Our approach extends the Wasserstein GAN formulation to allow for the generation of ground motions conditioned on a set of continuous physical variables. Our model is trained to approximate the intrinsic probability distribution of a massive set of strong‐motion recordings from Japan. We show that the trained generator model can synthesize realistic three‐component accelerograms conditioned on magnitude, distance, and VS30⁠. Our model captures most of the relevant statistical features of the acceleration spectra and waveform envelopes. The output seismograms display clear P‐ and S‐wave arrivals with the appropriate energy content and relative onset timing. The synthesized peak ground acceleration estimates are also consistent with observations. We develop a set of metrics that allow us to assess the training process’s stability and to tune model hyperparameters. We further show that the trained generator network can interpolate to conditions in which no earthquake ground‐motion recordings exist. Our approach allows for the on‐demand synthesis of accelerograms for engineering purposes.


  • Structural and Optical Properties of Bismuth-doped ZnO Nanoparticles Synthesized by Co-precipitation

    by C. Sermsrithong, P. Jaidaew, C. Promjantuk, P. Buabthong

    Bismuth-doped zinc oxide (ZnO) nanoparticles can serve as efficient photocatalysts for various reactions. Herein, we synthesized and discussed the growth mechanisms of Bi-doped ZnO nanoflakes using co-precipitation with Bi concentrations ranging from 0 to 3 %. The resulting ZnO were hexagonal nanosheets with diameters ranging from 80 nm (ZnO) to 200 nm (ZnO: Bi 3%). The dominant crystal structure matches hexagonal wurtzite with a small presence of Bi2O3 diffraction peaks. The estimated crystallite sizes range from ~ 33 nm to ~ 45 nm, indicating multiple crystalline regions in each nanoflake. Nevertheless, as sheet resistance monotonically decreases with the Bi concentration, the higher number of grain boundaries likely has a lower effect on the conductivity compared to an increase in free carriers and larger grain size in the samples with higher Bi concentration. The bandgap decreases from ~ 3.13 eV to ~ 2.96 eV, likely due to the shrinkage effect from electron-electron or electron-impurity interaction that lowers the conduction band of ZnO.


  • Catalytic open-circuit passivation by thin metal oxide films of p-Si anodes in aqueous alkaline electrolytes

    by Harold J. Fu, Pakpoom Buabthong, Zachary Philip Ifkovits, Weilai Yu, Bruce S. Brunschwig, Nathan S. Lewis

    Ni and NiOx-based protective thin films catalyze the oxidation of Si in the presence of O2 in strongly alkaline KOH(aq) even in the absence of illumination.


  • Investigations of the stability of etched or platinized p-InP(100) photocathodes for solar-driven hydrogen evolution in acidic or alkaline aqueous electrolytes

    by Weilai Yu, Matthias H. Richter, Pakpoom Buabthong, Ivan A. Moreno-Hernandez, Carlos G. Read, Ethan Simonoff, Bruce S. Brunschwig, Nathan S. Lewis

    Illuminated etched p-InP photocathode undergoes cathodic corrosion forming metallic In0, while electrodeposited Pt catalyst kinetically stabilizes the electrode surface against such a corrosion pathway.