检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yan, Shi-Qi Gu, Jia-Chen Zhu, Yun Ling, Zhen-Hua National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei China Department of Computer Science University of California Los Angeles United States Google DeepMind United Kingdom

Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable complement to LLMs, it relies heavily on the relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong. To this end, we propose the Corrective Retrieval Augmented Generation (CRAG) to improve the robustness of generation. Specifically, a lightweight retrieval evaluator is designed to assess the overall quality of retrieved documents for a query, returning a confidence degree based on which different knowledge retrieval actions can be triggered. Since retrieval from static and limited corpora can only return suboptimal documents, large-scale web searches are utilized as an extension for augmenting the retrieval results. Besides, a decompose-then-recompose algorithm is designed for retrieved documents to selectively focus on key information and filter out irrelevant information in them. CRAG is plug-and-play and can be seamlessly coupled with various RAG-based approaches. Experiments on four datasets covering short- and long-form generation tasks show that CRAG can significantly improve the performance of RAG-based approaches. Copyright © 2024, The Authors. All rights reserved.

关键词： Structured Query language

来源：评论

学校读者我要写书评

暂无评论

Sagalee: an Open Source Automatic speech Recognition Dataset for Oromo language

Sagalee: an Open Source Automatic Speech Recognition Dataset...

引用

International Conference on Acoustics, speech, and Signal processing (ICASSP)

作者： Turi Abu Ying Shi Thomas Fang Zheng Dong Wang Center for Speech and Language Technologies BNRist Beijing Department of Computer Science and Technology Tsinghua University Beijing China School of Computer Science and Technology Harbin Institute of Technology Harbin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We present a novel Automatic speech Recognition (ASR) dataset for the Oromo language, a widely spoken language in Ethiopia and neighboring regions. The dataset was collected through a crowdsourcing initiative, encompassing a diverse range of speakers and phonetic variations. It consists of 100 hours of real-world audio recordings paired with transcriptions, covering read speech in both clean and noisy environments. This dataset addresses the critical need for ASR resources for the Oromo language which is underrepresented. To show its applicability for the ASR task, we conducted experiments using the Conformer model, achieving a Word Error Rate (WER) of 15.32% with hybrid CTC and AED loss and WER of 18.74% with pure CTC loss. Additionally, fine-tuning the Whisper model resulted in a significantly improved WER of 10.82%. These results establish baselines for Oromo ASR, highlighting both the challenges and the potential for improving ASR performance in Oromo. The dataset is publicly available at https://***/turinaf/sagalee and we encourage its use for further research and development in Oromo speech processing.

关键词： Crowdsourcing Error analysis Signal processing Phonetics Audio recording Acoustics Noise measurement speech processing Research and development Automatic speech recognition

来源：评论

学校读者我要写书评

暂无评论

VATEX2020: PLSTM framework for video captioning

VATEX2020: PLSTM framework for video captioning

引用

2022 International Conference on Machine Learning and Data Engineering, ICMLDE 2022

作者： Singh, Alok Singh, Salam Michael Meetei, Loitongbam Sanayai Das, Ringki Singh, Thoudam Doren Bandyopadhyay, Sivaji Department of Computer Science and Engineering National Institute of Technology Assam Silchar India Center for Natural Language Processing National Institute of Technology Assam Silchar India

Captioning a video involves condensing the video's information into text, which can be useful in video sentiment analysis, video-guided machine translation (VMT), visual question-answering and humanitarian aid. This paper discusses the details of the architecture of the pLSTM framework that is employed for the VATEX-2020 video captioning challenge. In this work, a sequential method is employed wherein to encode visual features a 3D convolutional neural network (C3D) is used. C3D was pretrained using the Sports-1M dataset. In the decoding phase, the input captions and visual features are fused separately in Long Short Term Memory networks (LSTM). The element-wise dot product is performed on the output of both LSTMs to get the final output. On both publicly available and private test data sets, our model achieves BLEU-4 scores of 0.20 and 0.22, respectively. © 2023 The Authors. Published by Elsevier B.V.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

EEVEE: An Easy Annotation Tool for Natural language processing

arXiv

引用

arXiv 2024年

作者： Sorensen, Axel Peng, Siyao Plank, Barbara van der Goot, Rob Department of Computer Science IT University of Copenhagen Denmark Munich Germany MaiNLP Center for Information and Language Processing LMU Munich Germany

Annotation tools are the starting point for creating Natural language processing (NLP) datasets. There is a wide variety of tools available;setting up these tools is however a hindrance. We propose EEVEE, an annotation tool focused on simplicity, efficiency, and ease of use. It can run directly in the browser (no setup required) and uses tab-separated files (as opposed to character offsets or task-specific formats) for annotation. It allows for annotation of multiple tasks on a single dataset and supports four task-types: sequence labeling, span labeling, text classification and seq2seq.1 © 2024, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Sagalee: an Open Source Automatic speech Recognition Dataset for Oromo language

arXiv

引用

arXiv 2025年

作者： Abu, Turi Shi, Ying Zheng, Thomas Fang Wang, Dong Center for Speech and Language Technologies BNRist Beijing China Department of Computer Science and Technology Tsinghua University Beijing China School of Computer Science and Technology Harbin Institute of Technology Harbin China

We present a novel Automatic speech Recognition (ASR) dataset for the Oromo language, a widely spoken language in Ethiopia and neighboring regions. The dataset was collected through a crowd-sourcing initiative, encompassing a diverse range of speakers and phonetic variations. It consists of 100 hours of real-world audio recordings paired with transcriptions, covering read speech in both clean and noisy environments. This dataset addresses the critical need for ASR resources for the Oromo language which is underrepresented. To show its applicability for the ASR task, we conducted experiments using the Conformer model, achieving a Word Error Rate (WER) of 15.32% with hybrid CTC and AED loss and WER of 18.74% with pure CTC loss. Additionally, fine-tuning the Whisper model resulted in a significantly improved WER of 10.82%. These results establish baselines for Oromo ASR, highlighting both the challenges and the potential for improving ASR performance in Oromo. The dataset is publicly available at https://***/turinaf/sagalee and we encourage its use for further research and development in Oromo speech processing. © 2025, CC BY.

关键词： speech recognition

来源：评论

学校读者我要写书评

暂无评论

Are Clinical T5 Models Better for Clinical Text?

arXiv

引用

arXiv 2024年

作者： Li, Yahan Harrigian, Keith Zirikly, Ayah Dredze, Mark Department of Computer Science University of Southern California United States Department of Computer Science Johns Hopkins University United States Center for Language and Speech Processing Whiting School of Engineering Johns Hopkins University United States Malone Center for Engineering in Healthcare Johns Hopkins University United States

Large language models with a transformerbased encoder/decoder architecture, such as T5 (Raffel et al., 2023), have become standard platforms for supervised tasks. To bring these technologies to the clinical domain, recent work has trained new (Lehman et al., 2023) or adapted existing (Lu et al., 2022) models to clinical data. However, the evaluation of these clinical T5 models and comparison to other models has been limited. Are the clinical T5 models better choices than FLAN-tuned (Chung et al., 2022a) generic T5 models? Do they generalize better to new clinical domains that differ from the training sets? We comprehensively evaluate these models across several clinical tasks and domains. We find that clinical T5 models provide marginal improvements over existing models, and perform worse when evaluated on different domains. Our results inform future choices in developing clinical LLMs. © 2024, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decoding speech Categorization using Microstate Cortical EEG Signals and Machine Learning

Decoding Speech Categorization using Microstate Cortical EEG...

引用

2024 IEEE Signal processing in Medicine and Biology Symposium, SPMB 2024

作者： Mahmud, M. Hasan, M. Yeasin, M. Bidelman, G. Univ. Of Tennessee Health Science Center Div. Of General Internal Medicine MemphisTN United States Middle Tennessee State University Computational And Data Science MurfreesboroTN United States University Of Memphis Department Of Electrical And Computer Engineering TN United States Indiana University Language And Hearing Sciences Department Of Speech BloomingtonIN United States

ISBN: (纸本)9798350388572

Categorical perception (CP) is a perceptual phenomenon that refers to the tendency of humans to group speech sounds into discrete units. In this work, we used cortical event-related potential (ERP) signals, recorded during a speech identification task, as input to a Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM) and machine learning (ML) classifiers to examine how neural signatures of the brain distinguish prototypical vs. ambiguous speech token categories. Particularly, we used extreme gradient boosting (XGBoost), support vector machine, and random forest classifiers. Our analysis shows that using source reconstructed whole-brain data, the XGBoost classifier yielded the best classification accuracy of 94.12% with (area under the curve (AUC) 94.13%, Precision 94.00%, F1-score 94.00%) in the 197-258 ms time window after the stimulus onset. We also identified 15 important brain regions that distinguished vowel classes with accuracy of 90.28% (AUC 90.17%, F1-score 90.00%, Precision 90.00%), 4% less than whole-brain data. Remarkably, out of these 15 critical brain regions, nine were from the left hemisphere, consistent with the left-brain dominance for language processing. The best speech decoding was obtained from early portions of the ERP (~180-320 ms), which corroborates notions that sensory encoding is critical for successful phonetic processing. © 2024 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Development of Rule-Based Chunker for Sindhi 1st

Development of Rule-Based Chunker for Sindhi

引用

1st International Conference on Computation of Artificial Intelligence and Machine Learning, ICCAIML 2024

作者： Arora, Palak Nathani, Bharti Joshi, Nisheeth Katyayan, Pragya Speech and Language Processing Lab Center for Artificial Intelligence Banasthali Vidyapith Rajasthan Radha Kishnpura India Department of Computer Science Banasthali Vidyapith Rajasthan Radha Kishnpura India Department of Mathematics and Statistics Banasthali Vidyapith Rajasthan Radha Kishnpura India

ISBN: (纸本)9783031714832

language is a primary means of communication. It is a medium through which we can interact with society. Recognizing it, each language has its own set of grammatical rules. This study focused on the development of a rule-based chunker for a resource-poor language Sindhi using the Devanagari script. We have chosen a rule-based approach as language itself is a sequence of rules. This approach is fairly useful due to its ability to capture nuances of a language. The language rules were created and validated with the help of language experts. To develop the chunker, 50,000 sentences were used for the construction of rules. These sentences belonged to various domains like travel and tourism, health and administration. For this study, there was a requirement for a POS-tagged dataset. The data was annotated using Part of speech tagger based on the Hidden Markov Model (HMM). 1,000 sentences were used to evaluate the system. The developed chunker showed an accuracy of 97.8%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

SciMRC: Multi-perspective Scientific Machine Reading Comprehension 30

SciMRC: Multi-perspective Scientific Machine Reading Compreh...

引用

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

作者： Zhang, Xiao Zheng, Heqi Nie, Yuxiang Huang, Heyan Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Southeast Academy of Information Technology Beijing Institute of Technology China State Grid Smart Grid Research Institute Co. Ltd. China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9782493814104

Scientific Machine Reading Comprehension (SMRC) aims to facilitate the understanding of scientific texts through human-machine interactions. While existing dataset has significantly contributed to this field, it predominantly focus on single-perspective question-answer pairs, thereby overlooking the inherent variation in comprehension levels among different readers. To address this limitation, we introduce a novel multi-perspective scientific machine reading comprehension dataset, SciMRC, which incorporates perspectives from beginners, students, and experts. Our dataset comprises 741 scientific papers and 6,057 question-answer pairs, with 3,306, 1,800, and 951 pairs corresponding to beginners, students, and experts respectively. Extensive experiments conducted on SciMRC using pre-trained models underscore the importance of considering diverse perspectives in SMRC and highlight the challenging nature of our scientific machine comprehension tasks. © 2024 ELRA language Resource Association: CC BY-NC 4.0.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Diversity and Tiny Models: Comparing Binary Networks and the Fruit Fly Algorithm on Document Representation Tasks 3

Algorithmic Diversity and Tiny Models: Comparing Binary Netw...

引用

3rd Workshop on Simple and Efficient Natural language processing, SustaiNLP 2022

作者： Ceron, Tanise Truong, Nhut Herbelot, Aurelie Institute for Natural Language Processing University of Stuttgart Germany Center for Mind/Brain Sciences University of Trento Italy Department of Information Engineering and Computer Science University of Trento Italy

ISBN: (纸本)9781959429241

Neural language models have seen a dramatic increase in size in the last years. While many still advocate that 'bigger is better', work in model distillation has shown that the number of parameters used by very large networks is actually more than what is required for state-of-the-art performance. This prompts an obvious question: can we build smaller models from scratch, rather than going through the inefficient process of training at scale and subsequently reducing model size? In this paper, we investigate the behaviour of a biologically inspired algorithm, based on the fruit fly's olfactory system. This algorithm has shown good performance in the past on the task of learning word embeddings. We now put it to the test on the task of semantic hashing. Specifically, we compare the fruit fly to a standard binary network on the task of generating locality-sensitive hashes for text documents, measuring both task performance and energy consumption. Our results indicate that the two algorithms have complementary strengths while showing similar electricity usage. © 2022 Association for Computational Linguistics.

关键词： Distillation

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：