检索结果-内蒙古大学图书馆

Intelligent Systems conference

作者： Striegl, Julian Rottmann, Sebastian Loitsch, Claudia ScaDS AI Dresden Leipzig Ctr Scalable Data Analyt & Artificial Intelligenc D-01187 Dresden Germany

ISBN: (纸本)9783031663284;9783031663291

Conversational agent-based psychotherapy is a novel field of research. Its importance has rapidly increased in recent years due to the heightened demand for psychotherapy treatment options and a related demand for cost-effective, scalable, and low-threshold solutions to provide mental health support to the general population. This methodological literature review investigates the current state of research on the effectiveness and acceptance of chatbot and voice assistant-based psychotherapy approaches by focusing on used measurement methods and achieved study outcomes. Following the updated PRISMA guidelines for reporting systematic reviews 1432 publications are identified and reduced to a result set of 22 publications based on a rigorous screening process. Overall, the current state of research suggests that conversational agents might be an effective treatment option for people with depression and anxiety and show good acceptance by users. As there is a high heterogeneity of study designs, and methodologies, and a lack of randomized controlled trials with conventional treatment control groups, more research in the field is needed.

关键词： natural language processing Conversational agents Human-computer interaction Internet-based psychotherapy Depression Anxiety

来源：评论

学校读者我要写书评

暂无评论

Deep learning-enabled natural language processing to identify directional pharmacokinetic drug-drug interactions

引用

BMC BIOINFORMATICS 2023年第1期24卷 413-413页

作者： Zirkle, Joel Han, Xiaomei Racz, Rebecca Samieegohar, Mohammadreza Chaturbedi, Anik Mann, John Chakravartula, Shilpa Li, Zhihua US FDA Div Appl Regulatory Sci Off Clin Pharmacol Off Translat SciCtr Drug Evaluat & Res WO Bldg 64 Rm 207810903 New Hampshire Ave Silver Spring MD 20993 USA

BackgroundDuring drug development, it is essential to gather information about the change of clinical exposure of a drug (object) due to the pharmacokinetic (PK) drug-drug interactions (DDIs) with another drug (precipitant). While many natural language processing (NLP) methods for DDI have been published, most were designed to evaluate if (and what kind of) DDI relationships exist in the text, without identifying the direction of DDI (object vs. precipitant drug). Here we present a method for the automatic identification of the directionality of a PK DDI from literature or drug *** reannotated the Text Analysis conference (TAC) DDI track 2019 corpus for identifying the direction of a PK DDI and evaluated the performance of a fine-tuned BioBERT model on this task by following the training and validation steps prespecified by *** initial attempt showed the model achieved an F-score of 0.82 in identifying sentences as containing PK DDI and an F-score of 0.97 in identifying object versus precipitant drugs in those *** and conclusionDespite a growing list of NLP methods for DDI extraction, most of them use a common set of corpora to perform general purpose tasks (e.g., classifying a sentence into one of several fixed DDI categories). There is a lack of coordination between the drug development and biomedical informatics method development community to develop corpora and methods to perform specific tasks (e.g., extract clinical exposure changes due to PK DDI). We hope that our effort can encourage such a coordination so that more "fit for purpose" NLP methods could be developed and used to facilitate the drug development process.

关键词： Pharmacokinetic Drug-drug interactions natural language processing Directionality Transformer language model

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Study on German language Models for Clinical and Biomedical Text Understanding 30

Comprehensive Study on German Language Models for Clinical a...

引用

Joint 30th International conference on Computational Linguistics and 14th International conference on language Resources and Evaluation, LREC-COLING 2024

作者： Idrissi-Yaghir, Ahmad Dada, Amin Schäfer, Henning Arzideh, Kamyar Baldini, Giulia Trienes, Jan Hasin, Max Bewersdorff, Jeanette Schmidt, Cynthia S. Bauer, Marie Smith, Kaleb E. Bian, Jiang Wu, Yonghui Schlötterer, Jörg Zesch, Torsten Horn, Peter A. Seifert, Christin Nensa, Felix Kleesiek, Jens Friedrich, Christoph M. Department of Computer Science University of Applied Sciences and Arts Dortmund Dortmund Germany Institute for Medical Informatics Biometry and Epidemiology University Hospital Essen Essen Germany Essen Germany Institute for Transfusion Medicine University Medicine Essen Essen Germany CATALPA FernUniversität in Hagen Germany NVIDIA Santa ClaraCA United States Department of Health Outcomes and Biomedical Informatics College of Medicine University of Florida GainesvilleFL United States Cancer Informatics and eHealth Core University of Florida Health Cancer Center University of Florida GainesvilleFL United States University of Marburg Marburg Germany University of Mannheim Mannheim Germany University Hospital Essen Institute of Interventional and Diagnostic Radiology and Neuroradiology Essen Germany Essen Germany Heidelberg Germany Department of Physics TU Dortmund Dortmund Germany

ISBN: (纸本)9782493814104

Recent advances in natural language processing (NLP) can be largely attributed to the advent of pre-trained language models such as BERT and RoBERTa. While these models demonstrate remarkable performance on general datasets, they can struggle in specialized domains such as medicine, where unique domain-specific terminologies, domain-specific abbreviations, and varying document structures are common. This paper explores strategies for adapting these models to domain-specific requirements, primarily through continuous pre-training on domain-specific data. We pre-trained several German medical language models on 2.4B tokens derived from translated public English medical data and 3B tokens of German clinical data. The resulting models were evaluated on various German downstream tasks, including named entity recognition (NER), multi-label classification, and extractive question answering. Our results suggest that models augmented by clinical and translation-based pre-training typically outperform general domain models in medical contexts. We conclude that continuous pre-training has demonstrated the ability to match or even exceed the performance of clinical models trained from scratch. Furthermore, pre-training on clinical data or leveraging translated texts have proven to be reliable methods for domain adaptation in medical NLP tasks. © 2024 ELRA language Resource Association: CC BY-NC 4.0.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Do Noisy Customer Reviews Discourage Platform Sellers? empirical Analysis of an Online Solar Marketplace

引用

M&SOM-MANUFACTURING & SERVICE OPERATIONS MANAGEMENT 2023年第6期25卷 2195-2215页

作者： Huang, Herbie Sunar, Nur Swaminathan, Jayashankar M. Roy, Rahul Lazada Lazada One Singapore 189554 Singapore Univ North Carolina Chapel Hill Kenan Flagler Business Sch Chapel Hill NC 27599 USA

Problem definition: Customer reviews are essential to online marketplaces. However, reviews typically vary;ratings of a product or service are rarely the same. In many service marketplaces, including the ones for solar panel installations, supply-side participants are active. That is, a seller must make a proposal to serve each customer. In such marketplaces, it is not clear how (or if) the dispersion in customer reviews affects the seller activity level and number of matches in the marketplace. Our paper examines this by considering both ratings and text reviews. To our knowledge, this is the first paper that empirically studies how the review dispersion affects a seller's activity level and the number of matches in an online marketplace with active sellers. Distinct from literature, we examine the relationship between the review dispersion and supply-side activities in an online service marketplace. Methodology/results: We collaborated with one of the largest online solar marketplaces in the United States that connects potential solar panel adopters with installers. We obtained a unique data set from the marketplace for 2013- 2018. We complement this with public data sets. Our analysis uses traditional econometrics methods, a clustering method, and the deep-learning-based natural-language-processing model BERT developed by Google AI. We find that the dispersion in customer reviews has a significant and inverted U-shaped relationship with an installer's marketplace activity level. Intuitively, a marketplace operator would favor having more sellers with perfect ratings. In contrast, we identify a significant and inverted U-shaped relationship between the market-level review dispersion and transactions. Managerial implications: Our paper provides key insights to marketplace operators and sellers. We find that in contrast to general belief, an operator can improve its market transactions by keeping/promoting sellers with low ratings or avoiding (negative) review filte

关键词： online marketplace solar PV installation green technology customer reviews supply-side dynamics

来源：评论

学校读者我要写书评

暂无评论

Application of natural language processing in the Automatic Detection of English Writing Errors

Application of Natural Language Processing in the Automatic ...

引用

Sensors, Electronics and Computer Engineering (ICSECE), IEEE International conference on

作者： Cailan Nie Global Language Center Xi'an Eurasia University Xi’an China

ISBN: (数字)9798350373646

ISBN: (纸本)9798350373653

This paper aims to explore a set of automatic detection methods for English writing errors based on natural language processing (NLP) to solve the problem of low error recognition rate in the traditional artificial speech modes. In this paper, an integrated speech acquisition, processing and recognition system is proposed. The system uses language model (LM) to identify errors in English sentences, and realizes accurate translation recognition through neural machine translation (NMT). In addition, BP neural networks are used to fit the English translation process in order to accurately identify English translations. Experimental data show that compared with the traditional artificial speech models, the recognition rate of this model is 0.952, the recall rate is 0.9732, and the F-value is 0.968, which significantly improves the recognition accuracy. The correct recognition rate was 95.96%, and the false positive rate was only 2.22 % . Experimental results show that the proposed method can effectively identify grammatical errors in English sentences, and the system has excellent performance.

关键词： Accuracy Computational modeling Neural networks Speech recognition Writing natural language processing Data models Sensors Speech processing Sensor arrays

来源：评论

学校读者我要写书评

暂无评论

Automating Lexicon Generation: A Comprehensive Review of Alternative Approaches 27

Automating Lexicon Generation: A Comprehensive Review of Alt...

引用

27th International conference on Knowledge Based and Intelligent Information and Engineering Sytems, KES 2023

作者： Ghali, Julien Pierre Edmond Inuzuka, Nobuhiro Shima, Kosuke Moriyama, Koichi Mutoh, Atsuko Nagoya Institute of Technology Gokisocho Showa Ward Aichi Nagoya466-006 Japan

Lexicon-based approaches to Document Classification are widely used, but the manual construction of lexicons can be time-consuming and resource-intensive. In this paper, we propose methods for automating the generation of lexicons later used for Document Classification. We explored diverse methods for generating lexicons, including semantic matches, frequency-based approaches, machine learning algorithms, and large language model techniques. We, later, used these lexicons to classify documents based on their content. By comparing our different lexicons results on a same task, based on criteria such as scalability and the F1 score, we determine optimized use-case for those methods. We show that our automated approaches are effective and efficient, producing accurate classifications with minimal human intervention. Some approaches have the potential to streamline the document classification process, reducing the time and resources required for manual lexicon generation, it also gives optimized use-case for the different methods. Thereafter, we discussed the obtained results. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： document classification lexicon generation machine learning natural language processing (NLP) semantic topic modeling transformers

来源：评论

学校读者我要写书评

暂无评论

Relative Importance in Sentence processing 59

Relative Importance in Sentence Processing

引用

Joint conference of 59th Annual Meeting of the Association-for-Computational-Linguistics (ACL) / 11th International Joint conference on natural language processing (IJCNLP) / 6th Workshop on Representation Learning for NLP (RepL4NLP)

作者： Hollenstein, Nora Beinborn, Lisa Univ Copenhagen Ctr Language Technol Copenhagen Denmark Vrije Univ Amsterdam Computat Linguist & Text Min Lab Amsterdam Netherlands

ISBN: (纸本)9781954085534

Determining the relative importance of the elements in a sentence is a key factor for effortless natural language understanding. For human language processing, we can approximate patterns of relative importance by measuring reading fixations using eye-tracking technology. In neural language models, gradientbased saliency methods indicate the relative importance of a token for the target objective. In this work, we compare patterns of relative importance in English language processing by humans and models and analyze the underlying linguistic patterns. We find that human processing patterns in English correlate strongly with saliency-based importance in language models and not with attention-based importance. Our results indicate that saliency could be a cognitively more plausible metric for interpreting neural language models. The code is available on github: https://***/beinborn/relative_importance.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

TCM-SD: A Benchmark for Probing Syndrome Differentiation via natural language processing 21

TCM-SD: A Benchmark for Probing Syndrome Differentiation via...

引用

21st China National conference on Computational Linguistics, CCL 2022

作者： Ren, Mucheng Huang, Heyan Zhou, Yuxiang Cao, Qianwen Bu, Yuan Gao, Yang School of Computer Science and Technology Beijing Institute of Technology Beijing China Xuzhou City Hospital of Traditional Chinese Medicine Xuzhou China

ISBN: (纸本)9783031183140

Traditional Chinese Medicine (TCM) is a natural, safe, and effective therapy that has spread and been applied worldwide. The unique TCM diagnosis and treatment system requires a comprehensive analysis of a patient’s symptoms hidden in the clinical record written in free text. Prior studies have shown that this system can be informationized and intelligentized with the aid of artificial intelligence (AI) technology, such as natural language processing (NLP). However, existing datasets are not of sufficient quality nor quantity to support the further development of data-driven AI technology in TCM. Therefore, in this paper, we focus on the core task of the TCM diagnosis and treatment system—syndrome differentiation (SD)—and we introduce the first public large-scale benchmark for SD, called TCM-SD. Our benchmark contains 54,152 real-world clinical records covering 148 syndromes. Furthermore, we collect a large-scale unlabelled textual corpus in the field of TCM and propose a domain-specific pre-trained language model, called ZY-BERT. We conducted experiments using deep neural networks to establish a strong performance baseline, reveal various challenges in SD, and prove the potential of domain-specific pre-trained language model. Our study and analysis reveal opportunities for incorporating computer science and linguistics knowledge to explore the empirical validity of TCM theories. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Fine-Grained Image Classification: A Survey 4

Few-Shot Fine-Grained Image Classification: A Survey

引用

4th International conference on natural language processing, ICNLP 2022

作者： Liu, Ying Bai, Yilun Che, Xin He, Jinglu Xi'an University of Posts and Telecommunications Center for Image and Information Processing Xi'an China

ISBN: (数字)9781665495448

ISBN: (纸本)9781665495448

With the development of deep learning, fine-grained image classification task has made remarkable achievements, but it largely depends on a large number of annotated data samples. However, in practical applications, such as public safety, medicine, endangered species and other professional fields, such fine-grained samples with annotations are difficult to obtain. When the samples are insufficient, the traditional deep learning training method is easy to yield the over fitting phenomenon, which greatly limits the applicability of such algorithms. The general few-shot algorithm is not designed for the fine-grained characteristics of the image, so it can not effectively extract the subtle differences in the image, which results in poor performance. Therefore, fine-grained image classification task based on few-shot learning has attracted more and more attentions in recent years. This paper introduces the task of few-shot fine-grained image classification, and summarizes the literatures in this field over the recent years. According to the few-shot learning methods, the existing algorithms are divided into the following three categories: meta learning based methods, multimodal based methods, and data augmentation based methods. In addition, the common datasets and performance evaluation indexes in the field of few-shot fine-grained image classification are summarized. Finally, the technical difficulties and research trends in this field are discussed. © 2022 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

It’s MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk 1

It’s MBR All the Way Down: Modern Generation Techniques Thr...

引用

1st Big Picture Workshop: Crafting a Research Narrative, BigPicture 2023

作者： Bertsch, Amanda Xie, Alex Neubig, Graham Gormley, Matthew R. Carnegie Mellon University United States

ISBN: (纸本)9798891760516

Minimum Bayes Risk (MBR) decoding is a method for choosing the outputs of a machine learning system based not on the output with the highest probability, but the output with the lowest risk (expected error) among multiple candidates. It is a simple but powerful method: for an additional cost at inference time, MBR provides reliable several-point improvements across metrics for a wide variety of tasks without any additional data or training. Despite this, MBR is not frequently applied in NLP works, and knowledge of the method itself is limited. We first provide an introduction to the method and the recent literature. We show that several recent methods that do not reference MBR can be written as special cases of MBR;this reformulation provides additional theoretical justification for the performance of these methods, explaining some results that were previously only empirical. We provide theoretical and empirical results about the effectiveness of various MBR variants and make concrete recommendations for the application of MBR in NLP models, including future directions in this area. © 2023 - Big Picture *** rights reserved

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：