A survey of pre-trained language models for processing scientific text

X Ho, AKD Nguyen, AT Dao, J Jiang, Y Chida… - arXiv preprint arXiv …, 2024 - arxiv.org
The number of Language Models (LMs) dedicated to processing scientific text is on the rise.
Keeping pace with the rapid growth of scientific LMs (SciLMs) has become a daunting task …

Research status and application of artificial intelligence large models in the oil and gas industry

LIU He, REN Yili, LI Xin, D Yue, W Yongtao… - Petroleum Exploration …, 2024 - Elsevier
This article elucidates the concept of large model technology, summarizes the research
status of large model technology both domestically and internationally, provides an overview …

BERTabaporu: assessing a genre-specific language model for Portuguese NLP

PB Costa, MC Pavan, WR Santos… - Proceedings of the …, 2023 - aclanthology.org
Transformer-based language models such as Bidirectional Encoder Representations from
Transformers (BERT) are now mainstream in the NLP field, but extensions to languages …

Integrating Economic Theory, Domain Knowledge, and Social Knowledge into Hybrid Sentiment Models for Predicting Crude Oil Markets

H Kaplan, A Weichselbraun, AMP Braşoveanu - Cognitive Computation, 2023 - Springer
For several decades, sentiment analysis has been considered a key indicator for assessing
market mood and predicting future price changes. Accurately predicting commodity markets …

ManuBERT: A pretrained Manufacturing science language representation model

A Kumar, B Starly, C Lynch - Available at SSRN 4375613, 2023 - papers.ssrn.com
Abstract Recent advances in Technical Language Processing (TLP) have created
opportunities to leverage the rich textual data to develop new applications in data-driven …

An Evaluation of Large Language Models for Geological Named Entity Recognition

RO Nunes, AS Spritzer, DG Balreira… - 2024 IEEE 36th …, 2024 - ieeexplore.ieee.org
Recent advancements in Natural Language Processing (NLP) have highlighted the success
of transformer-based models in various tasks, including Named Entity Recognition (NER) …

Tucano: Advancing Neural Text Generation for Portuguese

NK Corrêa, A Sen, S Falk, S Fatimah - arXiv preprint arXiv:2411.07854, 2024 - arxiv.org
Significant advances have been made in natural language processing in recent years.
However, our current deep learning approach to language modeling requires substantial …

[PDF][PDF] Evaluating Pre-training Strategies for Literary Named Entity Recognition in Portuguese

MO Silva, MM Moro - … of the 16th International Conference on …, 2024 - aclanthology.org
In specialized domains, the performance of generic language models can be suboptimal
due to significant domain-specific differences. To address such a problem, different pre …

[PDF][PDF] Evaluating Domain-adapted Language Models for Governmental Text Classification Tasks in Portuguese

MO Silva, GP Oliveira, LGL Costa, GL Pappa - SBBD. SBC, 2024 - researchgate.net
Domain-adaptive pre-training (DAPT) is a technique in natural language processing (NLP)
that tailors pre-trained language models to specific domains, enhancing their performance in …