Knowledge graph embedding: A survey from the perspective of representation spaces
Knowledge graph embedding (KGE) is an increasingly popular technique that aims to
represent entities and relations of knowledge graphs into low-dimensional semantic spaces …
represent entities and relations of knowledge graphs into low-dimensional semantic spaces …
Artificial intelligence for science in quantum, atomistic, and continuum systems
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural
sciences. Today, AI has started to advance natural sciences by improving, accelerating, and …
sciences. Today, AI has started to advance natural sciences by improving, accelerating, and …
[HTML][HTML] Pre-trained language models with domain knowledge for biomedical extractive summarization
Biomedical text summarization is a critical task for comprehension of an ever-growing
amount of biomedical literature. Pre-trained language models (PLMs) with transformer …
amount of biomedical literature. Pre-trained language models (PLMs) with transformer …
Revisiting parameter-efficient tuning: Are we really there yet?
Parameter-Efficient Tuning (PETuning) methods have been deemed by many as the new
paradigm for using pretrained language models (PLMs). By tuning just a fraction amount of …
paradigm for using pretrained language models (PLMs). By tuning just a fraction amount of …
Review of natural language processing in pharmacology
D Trajanov, V Trajkovski, M Dimitrieva, J Dobreva… - Pharmacological …, 2023 - ASPET
Natural language processing (NLP) is an area of artificial intelligence that applies
information technologies to process the human language, understand it to a certain degree …
information technologies to process the human language, understand it to a certain degree …
Keblm: Knowledge-enhanced biomedical language models
Pretrained language models (PLMs) have demonstrated strong performance on many
natural language processing (NLP) tasks. Despite their great success, these PLMs are …
natural language processing (NLP) tasks. Despite their great success, these PLMs are …
KCD: Knowledge walks and textual cues enhanced political perspective detection in news media
Political perspective detection has become an increasingly important task that can help
combat echo chambers and political polarization. Previous approaches generally focus on …
combat echo chambers and political polarization. Previous approaches generally focus on …
Recognizing medical search query intent by few-shot learning
Online healthcare services can provide unlimited and in-time medical information to users,
which promotes social goods and breaks the barriers of locations. However, understanding …
which promotes social goods and breaks the barriers of locations. However, understanding …
Kalm: Knowledge-aware integration of local, document, and global contexts for long document understanding
With the advent of pretrained language models (LMs), increasing research efforts have been
focusing on infusing commonsense and domain-specific knowledge to prepare LMs for …
focusing on infusing commonsense and domain-specific knowledge to prepare LMs for …
Revisiting the knowledge injection frameworks
In recent years, large language models (LLMs), such as GPTs, have attained great impact
worldwide. However, how to adapt these LLMs to better suit the vertical domain-specific …
worldwide. However, how to adapt these LLMs to better suit the vertical domain-specific …