A survey of large language models for healthcare: from data, technology, and applications to accountability and ethics
The utilization of large language models (LLMs) in the Healthcare domain has generated
both excitement and concern due to their ability to effectively respond to freetext queries with …
both excitement and concern due to their ability to effectively respond to freetext queries with …
A survey on semantic processing techniques
Semantic processing is a fundamental research domain in computational linguistics. In the
era of powerful pre-trained language models and large language models, the advancement …
era of powerful pre-trained language models and large language models, the advancement …
A cross-guidance cross-lingual model on generated parallel corpus for classical Chinese machine reading comprehension
Chinese diachronic gap is a key issue in classical Chinese machine reading
comprehension (CCMRC). Preceding work on bridging this gap has been mostly restricted …
comprehension (CCMRC). Preceding work on bridging this gap has been mostly restricted …
[HTML][HTML] Global information-aware argument mining based on a top-down multi-turn QA model
B Liu, V Schlegel, P Thompson… - Information Processing …, 2023 - Elsevier
Argument mining (AM) aims to automatically generate a graph that represents the argument
structure of a document. Most previous AM models only pay attention to a single argument …
structure of a document. Most previous AM models only pay attention to a single argument …
A T5-based interpretable reading comprehension model with more accurate evidence training
B Guan, X Zhu, S Yuan - Information Processing & Management, 2024 - Elsevier
Pre-trained language models (PLMs) have achieved outstanding performance on Machine
Reading Comprehension (MRC) tasks, but these models' interpretability remains uncertain …
Reading Comprehension (MRC) tasks, but these models' interpretability remains uncertain …
Disentangled retrieval and reasoning for implicit question answering
To date, most of the existing open-domain question answering (QA) methods focus on
explicit questions where the reasoning steps are mentioned explicitly in the question. In this …
explicit questions where the reasoning steps are mentioned explicitly in the question. In this …
[HTML][HTML] Ask and Ye shall be Answered: Bayesian tag-based collaborative recommendation of trustworthy experts over time in community question answering
Several challenging issues have yet to be jointly addressed in the recommendation of
experts for community question answering, including dynamicity, comprehensive profiling …
experts for community question answering, including dynamicity, comprehensive profiling …
ReCoMIF: Reading comprehension based multi-source information fusion network for Chinese spoken language understanding
B Xie, X Jia, X Song, H Zhang, B Chen, B Jiang… - Information …, 2023 - Elsevier
Spoken language understanding (SLU) plays a crucial role in the performance of dialogue
systems. It usually includes slot filling and intent detection (SFID) tasks aiming at semantic …
systems. It usually includes slot filling and intent detection (SFID) tasks aiming at semantic …
PROMISE: A pre-trained knowledge-infused multimodal representation learning framework for medication recommendation
Abstract Electronic Health Records (EHRs) significantly enhance clinical decision-making,
particularly in safe and effective medication recommendation based on complex patient …
particularly in safe and effective medication recommendation based on complex patient …
CBKI: A confidence-based knowledge integration framework for multi-choice machine reading comprehension
X Meng, Y Song, Q Bai, T Wang - Knowledge-Based Systems, 2023 - Elsevier
External knowledge has been introduced into pretrained models to enhance answer
reasoning in machine reading comprehension tasks. However, most methods directly take …
reasoning in machine reading comprehension tasks. However, most methods directly take …