A survey of knowledge enhanced pre-trained language models

L Hu, Z Liu, Z Zhao, L Hou, L Nie… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Pre-trained Language Models (PLMs) which are trained on large text corpus via self-
supervised learning method, have yielded promising performance on various tasks in …

End-to-end transformer-based models in textual-based NLP

A Rahali, MA Akhloufi - Ai, 2023 - mdpi.com
Transformer architectures are highly expressive because they use self-attention
mechanisms to encode long-range dependencies in the input sequences. In this paper, we …

EASE: Entity-aware contrastive learning of sentence embedding

S Nishikawa, R Ri, I Yamada, Y Tsuruoka… - arxiv preprint arxiv …, 2022 - arxiv.org
We present EASE, a novel method for learning sentence embeddings via contrastive
learning between sentences and their related entities. The advantage of using entity …

Applications of large language models (LLMs) in business analytics–exemplary use cases in data preparation tasks

M Nasseri, P Brandtner, R Zimmermann… - … Conference on Human …, 2023 - Springer
The application of data analytics in management has become a crucial success factor for the
modern enterprise. To apply analytical models, appropriately prepared data must be …

Harnessing the Power of LLMs for Service Quality Assessment from User-Generated Content

T Falatouri, D Hrušecká, T Fischer - IEEE Access, 2024 - ieeexplore.ieee.org
Adopting Large Language Models (LLMs) creates opportunities for organizations to
increase efficiency, particularly in sentiment analysis and information extraction tasks. This …

Leveraging large language models for literature review tasks-a case study using chatgpt

R Zimmermann, M Staab, M Nasseri… - … Conference on Advanced …, 2024 - Springer
Literature reviews constitute an indispensable component of research endeavors; however,
they often prove laborious and time-intensive. This study explores the potential of ChatGPT …

Leveraging knowledge in multilingual commonsense reasoning

Y Fang, S Wang, Y Xu, R Xu, S Sun, C Zhu… - arxiv preprint arxiv …, 2021 - arxiv.org
Commonsense reasoning (CSR) requires the model to be equipped with general world
knowledge. While CSR is a language-agnostic process, most comprehensive knowledge …

Structure-inducing pre-training

MBA McDermott, B Yap, P Szolovits… - Nature Machine …, 2023 - nature.com
Abstract Language model pre-training and the derived general-purpose methods have
reshaped machine learning research. However, there remains considerable uncertainty …

Machine-created universal language for cross-lingual transfer

Y Liang, Q Zhu, J Zhao, N Duan - … of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
There are two primary approaches to addressing cross-lingual transfer: multilingual pre-
training, which implicitly aligns the hidden representations of various languages, and …

Enhancing multilingual language model with massive multilingual knowledge triples

L Liu, X Li, R He, L Bing, S Joty, L Si - arxiv preprint arxiv:2111.10962, 2021 - arxiv.org
Knowledge-enhanced language representation learning has shown promising results
across various knowledge-intensive NLP tasks. However, prior methods are limited in …