Bismuth-doped ZnO nanosheets were synthesized using co-precipitation. We performed the standard characterization techniques, then discussed the deposition conditions and their effects on the morphology.

Bismuth-Doped ZnO Nanosheet using Co-precipication

Using generative adversarial networks, we're able to generate realistic broadband seismograms in all 3 components conditioned on the magnitude, epicenter distance, and vs30.

Using GANs to Generate Realistic Broadband Earthquake Accelorograms

We quantify pinholes in TiO2 film caused by dust particles during the deposition

The Ultimate Guide to Creating TiO2 Pinholes with Dust Particles

Straightforward XPS measurement for metallic vanadium, niobium, and tantalum.

Vanadium, niobium and tantulum by XPS

We explore the use of large language models (LLMs) for ontology population tasks in finance. The findings reveal that LLMs-based generative approaches, especially when provided with positive and negative examples in the prompts, outperform span-based methods, achieving a 61.05% F1 score.

Financial Product Ontology Population with Large Language Models

We introduce a methodology for event extraction, particularly aimed at low-resource languages like Thai. The proposed framework simplifies the traditional annotation process, enhancing efficiency in extracting events from text.

Streamlining Event Extraction with a Simplified Annotation Framework

This paper presents a cross-document coreference resolution approach tailored for low-resource languages, specifically focusing on Thai. The authors adapt an existing English model that uses agglomerative clustering to identify and group coreferent entities across documents. The study also compares manual and automatic span detection methods, finding that a fine-tuned longformer model provides the best performance, achieving a CoNLL F1 score of 72.87. This research offers a framework that could be extended to other low-resource languages.

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

The paper presents a progressive approach to building Thai spelling correction systems by integrating both neural-based and dictionary-based methods. It introduces an Extendable Neural Contextual Corrector (XNCC), which allows for vocabulary expansion post-training, demonstrating that effective spelling correction can be achieved with minimal annotated data and minor enhancements to traditional methods.

How to Progressively Build Thai Spelling Correction Systems?

We adopted multi-hop KGQA for Thai language data, using a manually-constructed knowledge graph based on banking products. The technique scored well in tests, but potentially proned to over-fitting when the answers are within 1-hop from the starting node.

All Posts

Bismuth-Doped ZnO Nanosheet using Co-precipication

Using GANs to Generate Realistic Broadband Earthquake Accelorograms

The Ultimate Guide to Creating TiO2 Pinholes with Dust Particles

Vanadium, niobium and tantulum by XPS