Synergizing machine learning & symbolic methods: A survey on hybrid approaches to natural language processing

R Panchendrarajan, A Zubiaga - Expert Systems with Applications, 2024 - Elsevier
The advancement of machine learning and symbolic approaches have underscored their
strengths and weaknesses in Natural Language Processing (NLP). While machine learning …

A survey on medical document summarization

R Jain, A Jangra, S Saha, A Jatowt - arXiv preprint arXiv:2212.01669, 2022 - arxiv.org
The internet has had a dramatic effect on the healthcare industry, allowing documents to be
saved, shared, and managed digitally. This has made it easier to locate and share important …

Knowledge base index compression via dimensionality and precision reduction

V Zouhar, M Mosbach, M Zhang, D Klakow - arXiv preprint arXiv …, 2022 - arxiv.org
Recently neural network based approaches to knowledge-intensive NLP tasks, such as
question answering, started to rely heavily on the combination of neural retrievers and …

Fusing sentence embeddings into LSTM-based autoregressive language models

V Zouhar, M Mosbach, D Klakow - arXiv preprint arXiv:2208.02402, 2022 - arxiv.org
Although masked language models are highly performant and widely adopted by NLP
practitioners, they can not be easily used for autoregressive language modelling (next word …

[PDF][PDF] Shrinking Knowledge Base Size: Dimension Reduction, Splitting & Filtering

V Zouhar - 2022 - raw.githubusercontent.com
Recently neural network based approaches to knowledge-intensive NLP tasks, such as
question answering, started to rely heavily on the combination of neural retrievers and …

Enhancing documents review through Knowledge Graphs and Large Language Models

P Angelici - skemman.is
In the era of data proliferation, efficiently navigating and extracting insights from complex
document collections is paramount across various sectors. Traditional methods for …