LIVIVO - Search results -

Search results

Result 1 - 10 of total 69

Search options

Book ; Online: Detecting Bias in Transfer Learning Approaches for Text Classification

Li, Irene

2021

Abstract: Classification is an essential and fundamental task in machine learning, playing a cardinal role in the field of natural language processing (NLP) and computer vision (CV). In a supervised learning setting, labels are always needed for the classification ...

Abstract	Classification is an essential and fundamental task in machine learning, playing a cardinal role in the field of natural language processing (NLP) and computer vision (CV). In a supervised learning setting, labels are always needed for the classification task. Especially for deep neural models, a large amount of high-quality labeled data are required for training. However, when a new domain comes out, it is usually hard or expensive to acquire the labels. Transfer learning could be an option to transfer the knowledge from a source domain to a target domain. A challenge is that these two domains can be different, either on the feature distribution, or the class distribution for the nature of the samples. In this work, we evaluate some existing transfer learning approaches on detecting the bias of imbalanced classes including traditional and deep models. Besides, we propose an approach to bridge the gap of the domain class imbalance issue. Comment: 3 figures
Keywords	Computer Science - Computation and Language
Subject code	006
Publishing date	2021-02-03
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: NNKGC

Li, Irene / Yang, Boming

Improving Knowledge Graph Completion with Node Neighborhoods

2023

Abstract: Knowledge graph completion (KGC) aims to discover missing relations of query entities. Current text-based models utilize the entity name and description to infer the tail entity given the head entity and a certain relation. Existing approaches also ... ...

Abstract	Knowledge graph completion (KGC) aims to discover missing relations of query entities. Current text-based models utilize the entity name and description to infer the tail entity given the head entity and a certain relation. Existing approaches also consider the neighborhood of the head entity. However, these methods tend to model the neighborhood using a flat structure and are only restricted to 1-hop neighbors. In this work, we propose a node neighborhood-enhanced framework for knowledge graph completion. It models the head entity neighborhood from multiple hops using graph neural networks to enrich the head node information. Moreover, we introduce an additional edge link prediction task to improve KGC. Evaluation on two public datasets shows that this framework is simple yet effective. The case study also shows that the model is able to predict explainable predictions. Comment: DL4KG Workshop, ISWC 2023
Keywords	Computer Science - Computation and Language
Subject code	004
Publishing date	2023-02-13
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article: Medical student attitudes and perceptions of psychedelic-assisted therapies.

Li, Irene / Fong, Rodney / Hagen, Molly / Tabaac, Burton

Frontiers in psychiatry

2023 Volume 14, Page(s) 1190507

Abstract: Introduction: Although certain psychedelic agents may soon gain federal approval for use in treating specific psychiatric conditions, the utilization of such therapies in clinical practice will depend largely on the attitudes of healthcare providers. ... ...

Abstract	Introduction: Although certain psychedelic agents may soon gain federal approval for use in treating specific psychiatric conditions, the utilization of such therapies in clinical practice will depend largely on the attitudes of healthcare providers. Therefore, this study assesses the current attitudes, knowledge, exposure, and acceptance of psychedelics and psychedelic-assisted therapies amongst medical students. Methods: In fall semester of 2022, surveys were emailed to 580 medical students attending medical institutions in the state of Nevada in the United States. Utilizing knowledge and attitude items from previously published studies, the survey collected demographic data and assessed student attitudes with five-point Likert-scale variables. Data was analyzed using summary statistics and Kruskal-Wallis tests for differences in mean survey scores (i.e., attitudes towards psychedelics) based on demographic factors. Results: 132 medical students participated in the survey (22.7% response rate). Medical students demonstrated overall positive attitudes towards psychedelics, lack of knowledge regarding psychedelics, and uncertainty towards neurocognitive risks of psychedelics. Overall, 78.6% of students agreed that psychedelics have therapeutic potential, while 95.2% agreed that psychedelics deserves further research in assessing this potential. Additionally, there was no statistically significant effect of demographic variables, including age, sex, and level of training, on attitudes. Discussion: Although students are overall curious and optimistic about psychedelics, they demonstrate a lack of knowledge regarding recent research efforts. As the field of psychiatry prepares to implement psychedelics and psychedelic-assisted therapies, education and awareness of such agents should be initiated early on in medical clinical training.
Language	English
Publishing date	2023-06-27
Publishing country	Switzerland
Document type	Journal Article
ZDB-ID	2564218-2
ISSN	1664-0640
ISSN	1664-0640
DOI	10.3389/fpsyt.2023.1190507
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

Article ; Online: Evaluation of phenobarbital for prevention of alcohol withdrawal in trauma patients.

Kip, Lindsey Marie / Forni, Allison / Dorfman, Jon David / Li, Irene

The journal of trauma and acute care surgery

2023 Volume 95, Issue 4, Page(s) 573–576

Abstract: Background: Up to 30% of trauma patients experience alcohol withdrawal syndrome (AWS) during their hospital admission, which is associated with worse outcomes. While benzodiazepines and phenobarbital are the mainstay of AWS management, there are limited ...

Abstract	Background: Up to 30% of trauma patients experience alcohol withdrawal syndrome (AWS) during their hospital admission, which is associated with worse outcomes. While benzodiazepines and phenobarbital are the mainstay of AWS management, there are limited data on the prevention of AWS. The objective was to evaluate the safety and efficacy of phenobarbital for the prevention of AWS. Methods: Adult patients admitted to a level 1 trauma center who received at least one dose of phenobarbital for the prevention of AWS between January 2019 and August 2021 were included. Patients were case matched to a control group managed with symptom-triggered therapy based on risk of AWS. Risk factors included sex, age, history of AWS/delirium tremens or withdrawal seizures, selected laboratory values, and screening questionnaires. The primary endpoint was the need for rescue therapy. Secondary endpoints included the time to rescue therapy, intensive care unit (ICU) length of stay (LOS), and hospital LOS. Results: Overall, 110 patients were included with 55 patients in each group. The phenobarbital group had higher baseline Injury Severity Scores ( p = 0.03) and were more likely to be admitted to the ICU (44% vs. 24%; p = 0.03). The phenobarbital group required less rescue therapy (16% vs. 62%; p < 0.001) with a longer time to rescue therapy administration (26 vs. 11 hours; p = 0.01). The phenobarbital group had a longer hospital LOS (216 vs. 87 hours; p = 0.0001) but no difference in ICU LOS ( p = 0.36). There was no incidence of delirium tremens or seizures and no difference in intubation rates ( p = 0.68). There was no incidence of hypotension associated with phenobarbital. Conclusion: Patients managed with phenobarbital had a lower need for rescue therapy for AWS with no increased adverse effects. Further studies should evaluate a protocol to prevent alcohol withdrawal in the trauma population. Level of evidence: Therapeutic/Care Management; Level III.
MeSH term(s)	Adult ; Humans ; Substance Withdrawal Syndrome/drug therapy ; Substance Withdrawal Syndrome/etiology ; Substance Withdrawal Syndrome/prevention & control ; Alcoholism/complications ; Alcoholism/drug therapy ; Alcohol Withdrawal Delirium/drug therapy ; Alcohol Withdrawal Delirium/prevention & control ; Alcohol Withdrawal Delirium/complications ; Retrospective Studies ; Phenobarbital/therapeutic use ; Benzodiazepines ; Seizures/complications ; Seizures/drug therapy
Chemical Substances	Phenobarbital (YQE403BP4D) ; Benzodiazepines (12794-10-4)
Language	English
Publishing date	2023-06-15
Publishing country	United States
Document type	Journal Article
ZDB-ID	2651070-4
ISSN	2163-0763 ; 2163-0755
ISSN (online)	2163-0763
ISSN	2163-0755
DOI	10.1097/TA.0000000000004039
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 127: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (1.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Book ; Online: Better Explain Transformers by Illuminating Important Information

Song, Linxin / Cui, Yan / Luo, Ao / Lecue, Freddy / Li, Irene

2024

Abstract: Transformer-based models excel in various natural language processing (NLP) tasks, attracting countless efforts to explain their inner workings. Prior methods explain Transformers by focusing on the raw gradient and attention as token attribution scores, ...

Abstract	Transformer-based models excel in various natural language processing (NLP) tasks, attracting countless efforts to explain their inner workings. Prior methods explain Transformers by focusing on the raw gradient and attention as token attribution scores, where non-relevant information is often considered during explanation computation, resulting in confusing results. In this work, we propose highlighting the important information and eliminating irrelevant information by a refined information flow on top of the layer-wise relevance propagation (LRP) method. Specifically, we consider identifying syntactic and positional heads as important attention heads and focus on the relevance obtained from these important heads. Experimental results demonstrate that irrelevant information does distort output attribution scores and then should be masked during explanation computation. Compared to eight baselines on both classification and question-answering datasets, our method consistently outperforms with over 3\% to 33\% improvement on explanation metrics, providing superior explanation performance. Our anonymous code repository is available at: https://github.com/LinxinS97/Mask-LRP
Keywords	Computer Science - Computation and Language
Publishing date	2024-01-18
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: HiPool

Li, Irene / Feng, Aosong / Radev, Dragomir / Ying, Rex

Modeling Long Documents Using Graph Neural Networks

2023

Abstract: Encoding long sequences in Natural Language Processing (NLP) is a challenging problem. Though recent pretraining language models achieve satisfying performances in many NLP tasks, they are still restricted by a pre-defined maximum length, making them ... ...

Abstract	Encoding long sequences in Natural Language Processing (NLP) is a challenging problem. Though recent pretraining language models achieve satisfying performances in many NLP tasks, they are still restricted by a pre-defined maximum length, making them challenging to be extended to longer sequences. So some recent works utilize hierarchies to model long sequences. However, most of them apply sequential models for upper hierarchies, suffering from long dependency issues. In this paper, we alleviate these issues through a graph-based method. We first chunk the sequence with a fixed length to model the sentence-level information. We then leverage graphs to model intra- and cross-sentence correlations with a new attention mechanism. Additionally, due to limited standard benchmarks for long document classification (LDC), we propose a new challenging benchmark, totaling six datasets with up to 53k samples and 4034 average tokens' length. Evaluation shows our model surpasses competitive baselines by 2.6% in F1 score, and 4.8% on the longest sequence dataset. Our method is shown to outperform hierarchical sequential models with better performance and scalability, especially for longer sequences.
Keywords	Computer Science - Computation and Language
Subject code	006
Publishing date	2023-05-05
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: How can obstetrical anaesthesiologists help in reducing the rate of caesarean delivery?

Zhao, Peishan / Li, Irene / Hu, Yiling / Hu, Ling-Qun

Anaesthesiology intensive therapy

2022 Volume 54, Issue 4, Page(s) 339–340

MeSH term(s)	Female ; Pregnancy ; Humans ; Cesarean Section ; Anesthesiologists
Language	English
Publishing date	2022-12-15
Publishing country	Poland
Document type	Letter
ISSN	1731-2531
ISSN (online)	1731-2531
DOI	10.5114/ait.2022.121044
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Exosomes in the tumor microenvironment as mediators of cancer therapy resistance.

Li, Irene / Nabet, Barzin Y

Molecular cancer

2019 Volume 18, Issue 1, Page(s) 32

Abstract: Exosomes are small extracellular vesicles that contain genetic material, proteins, and lipids. They function as potent signaling molecules between cancer cells and the surrounding cells that comprise the tumor microenvironment (TME). Exosomes derived ... ...

Abstract	Exosomes are small extracellular vesicles that contain genetic material, proteins, and lipids. They function as potent signaling molecules between cancer cells and the surrounding cells that comprise the tumor microenvironment (TME). Exosomes derived from both tumor and stromal cells have been implicated in all stages of cancer progression and play an important role in therapy resistance. Moreover, due to their nature as mediators of cell-cell communication, they are integral to TME-dependent therapy resistance. In this review, we discuss current exosome isolation and profiling techniques and their role in TME interactions and therapy resistance. We also explore emerging clinical applications of both exosomes as biomarkers, direct therapeutic targets, and engineered nanocarriers. In order to fully understand the TME, careful interrogation of exosomes and their cargo is critical. This understanding is a promising avenue for the development of effective clinical applications.
MeSH term(s)	Antibodies, Neutralizing/pharmacology ; B7-H1 Antigen/antagonists & inhibitors ; B7-H1 Antigen/genetics ; B7-H1 Antigen/immunology ; Biomarkers, Tumor/chemistry ; Biomarkers, Tumor/immunology ; CTLA-4 Antigen/antagonists & inhibitors ; CTLA-4 Antigen/genetics ; CTLA-4 Antigen/immunology ; Cancer-Associated Fibroblasts/drug effects ; Cancer-Associated Fibroblasts/immunology ; Cancer-Associated Fibroblasts/pathology ; Cell Communication/immunology ; Disease Progression ; Drug Carriers ; Drug Resistance, Neoplasm/genetics ; Drug Resistance, Neoplasm/immunology ; Endothelial Cells/drug effects ; Endothelial Cells/immunology ; Endothelial Cells/pathology ; Exosomes/chemistry ; Exosomes/immunology ; Exosomes/transplantation ; Humans ; Immunotherapy/methods ; Killer Cells, Natural/drug effects ; Killer Cells, Natural/immunology ; Killer Cells, Natural/pathology ; Neoplasms/genetics ; Neoplasms/immunology ; Neoplasms/pathology ; Neoplasms/therapy ; Stromal Cells/drug effects ; Stromal Cells/immunology ; Stromal Cells/pathology ; Tumor Microenvironment/drug effects ; Tumor Microenvironment/genetics ; Tumor Microenvironment/immunology
Chemical Substances	Antibodies, Neutralizing ; B7-H1 Antigen ; Biomarkers, Tumor ; CD274 protein, human ; CTLA-4 Antigen ; CTLA4 protein, human ; Drug Carriers
Language	English
Publishing date	2019-03-01
Publishing country	England
Document type	Journal Article ; Research Support, N.I.H., Extramural ; Research Support, U.S. Gov't, Non-P.H.S. ; Review
ZDB-ID	2091373-4
ISSN	1476-4598 ; 1476-4598
ISSN (online)	1476-4598
ISSN	1476-4598
DOI	10.1186/s12943-019-0975-5
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Book ; Online: Topic-Centric Explanations for News Recommendation

Liu, Dairui / Greene, Derek / Li, Irene / Jiang, Xuefei / Dong, Ruihai

2023

Abstract: News recommender systems (NRS) have been widely applied for online news websites to help users find relevant articles based on their interests. Recent methods have demonstrated considerable success in terms of recommendation performance. However, the ... ...

Abstract	News recommender systems (NRS) have been widely applied for online news websites to help users find relevant articles based on their interests. Recent methods have demonstrated considerable success in terms of recommendation performance. However, the lack of explanation for these recommendations can lead to mistrust among users and lack of acceptance of recommendations. To address this issue, we propose a new explainable news model to construct a topic-aware explainable recommendation approach that can both accurately identify relevant articles and explain why they have been recommended, using information from associated topics. Additionally, our model incorporates two coherence metrics applied to assess topic quality, providing measure of the interpretability of these explanations. The results of our experiments on the MIND dataset indicate that the proposed explainable NRS outperforms several other baseline systems, while it is also capable of producing interpretable topics compared to those generated by a classical LDA topic model. Furthermore, we present a case study through a real-world example showcasing the usefulness of our NRS for generating explanations. Comment: 20 pages
Keywords	Computer Science - Information Retrieval
Subject code	006
Publishing date	2023-06-12
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Going Beyond Local

Yang, Boming / Liu, Dairui / Suzumura, Toyotaro / Dong, Ruihai / Li, Irene

Global Graph-Enhanced Personalized News Recommendations

2023

Abstract: Precisely recommending candidate news articles to users has always been a core challenge for personalized news recommendation systems. Most recent works primarily focus on using advanced natural language processing techniques to extract semantic ... ...

Abstract	Precisely recommending candidate news articles to users has always been a core challenge for personalized news recommendation systems. Most recent works primarily focus on using advanced natural language processing techniques to extract semantic information from rich textual data, employing content-based methods derived from local historical news. However, this approach lacks a global perspective, failing to account for users' hidden motivations and behaviors beyond semantic information. To address this challenge, we propose a novel model called GLORY (Global-LOcal news Recommendation sYstem), which combines global representations learned from other users with local representations to enhance personalized recommendation systems. We accomplish this by constructing a Global-aware Historical News Encoder, which includes a global news graph and employs gated graph neural networks to enrich news representations, thereby fusing historical news representations by a historical news aggregator. Similarly, we extend this approach to a Global Candidate News Encoder, utilizing a global entity graph and a candidate news aggregator to enhance candidate news representation. Evaluation results on two public news datasets demonstrate that our method outperforms existing approaches. Furthermore, our model offers more diverse recommendations. Comment: Recsys 2023, Best Student Paper
Keywords	Computer Science - Information Retrieval ; Computer Science - Computation and Language
Publishing date	2023-07-13
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED