检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

7,585 篇 会议
71 册 图书
49 篇 期刊文献
2 篇 学位论文

馆藏范围

7,706 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

6,483 篇 工学
- 6,256 篇 计算机科学与技术...
- 3,577 篇 软件工程
- 748 篇 信息与通信工程
- 535 篇 控制科学与工程
- 272 篇 电气工程
- 212 篇 生物工程
- 121 篇 化学工程与技术
- 100 篇 机械工程
- 86 篇 电子科学与技术（可...
- 74 篇 生物医学工程（可授...
- 63 篇 安全科学与工程
- 59 篇 农业工程
- 57 篇 交通运输工程
- 49 篇 网络空间安全
1,522 篇 管理学
- 1,165 篇 图书情报与档案管...
- 467 篇 管理科学与工程(可...
- 134 篇 工商管理
1,471 篇 文学
- 1,464 篇 外国语言文学
- 161 篇 中国语言文学
1,446 篇 理学
- 776 篇 数学
- 352 篇 物理学
- 249 篇 生物学
- 240 篇 统计学（可授理学、...
- 120 篇 化学
- 101 篇 系统科学
164 篇 法学
- 153 篇 社会学
129 篇 医学
- 93 篇 临床医学
- 75 篇 基础医学(可授医学...
111 篇 教育学
- 105 篇 教育学
68 篇 农学
- 68 篇 作物学
42 篇 经济学
6 篇 哲学
3 篇 艺术学
1 篇 军事学

主题

1,181 篇 natural language...
872 篇 computational li...
619 篇 natural language...
283 篇 semantics
165 篇 natural language...
128 篇 machine learning
127 篇 graphic methods
123 篇 iterative method...
111 篇 sentiment analys...
110 篇 speech recogniti...
105 篇 deep learning
94 篇 syntactics
90 篇 text processing
86 篇 speech processin...
81 篇 embeddings
72 篇 information retr...
69 篇 modeling languag...
69 篇 artificial intel...
66 篇 contrastive lear...
63 篇 zero-shot learni...

机构

74 篇 carnegie mellon ...
36 篇 national univers...
34 篇 carnegie mellon ...
34 篇 language technol...
34 篇 institute for na...
33 篇 university of wa...
33 篇 school of comput...
32 篇 tsinghua univers...
31 篇 university of ch...
30 篇 nanyang technolo...
30 篇 stanford univers...
29 篇 zhejiang univers...
27 篇 alibaba grp peop...
26 篇 gaoling school o...
26 篇 carnegie mellon ...
25 篇 harbin institute...
25 篇 peking universit...
25 篇 natl univ singap...
24 篇 allen inst artif...
23 篇 the chinese univ...

作者

42 篇 neubig graham
39 篇 zhou guodong
39 篇 smith noah a.
36 篇 liu yang
36 篇 lapata mirella
34 篇 sun maosong
32 篇 zhang min
30 篇 liu qun
30 篇 hovy eduard
29 篇 zhao jun
27 篇 schütze hinrich
27 篇 liu zhiyuan
26 篇 gurevych iryna
25 篇 vulic ivan
22 篇 huang xuanjing
21 篇 chang kai-wei
21 篇 liu kang
21 篇 zhang yue
21 篇 zhang qi
20 篇 wen ji-rong

语言

6,955 篇 英文
722 篇 其他
23 篇 中文
8 篇 法文
4 篇 土耳其文
2 篇 德文
2 篇 俄文

检索条件"任意字段=Proceedings of the Conference on Empirical Methods in Natural Language Processing"

共 7707 条记录，以下是271-280 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Make Some Noise: Unlocking language Model Parallel Inference Capability through Noisy Training

Make Some Noise: Unlocking Language Model Parallel Inference...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Wang, Yixuan Luo, Xianzhen Wei, Fuxuan Liu, Yijun Zhu, Qingfu Zhang, Xuanyu Yang, Qing Xu, Dongliang Che, Wanxiang Harbin Institute of Technology Harbin China Science Technology Co. Ltd. China

ISBN: (纸本)9798891761643

Existing speculative decoding methods typically require additional model structure and training processes to assist the model for draft token generation. This makes the migration of acceleration methods to the new model more costly and more demanding on device memory. To address this problem, we propose the Make Some Noise (MSN) training framework as a replacement for the supervised fine-tuning stage of the large language model. The training method simply introduces some noise at the input for the model to learn the denoising task. It significantly enhances the parallel decoding capability of the model without affecting the original task capability. In addition, we propose a tree-based retrieval-augmented Jacobi (TR-Jacobi) decoding strategy to further improve the inference speed of MSN models. Experiments in both the general and code domains have shown that MSN can improve inference speed by 2.3-2.7x times without compromising model performance. The MSN model also achieves comparable acceleration ratios to the SOTA model with additional model structure on Spec-Bench. © 2024 Association for Computational Linguistics.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

LUQ: Long-text Uncertainty Quantification for LLMs

LUQ: Long-text Uncertainty Quantification for LLMs

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Zhang, Caiqi Liu, Fangyu Basaldella, Marco Collier, Nigel Language Technology Lab University of Cambridge United Kingdom Amazon Alexa United Kingdom

ISBN: (纸本)9798891761643

Large language Models (LLMs) have demonstrated remarkable capability in a variety of NLP tasks. However, LLMs are also prone to generate nonfactual content. Uncertainty Quantification (UQ) is pivotal in enhancing our understanding of a model's confidence on its generation, thereby aiding in the mitigation of nonfactual outputs. Existing research on UQ predominantly targets short text generation, typically yielding brief, word-limited responses. However, real-world applications frequently necessitate much longer responses. Our study first highlights the limitations of current UQ methods in handling long text generation. We then introduce LUQ with its two variations: LUQ-ATOMIC and LUQ-PAIR, a series of novel sampling-based UQ approaches specifically designed for long text. Our findings reveal that LUQ outperforms existing baseline methods in correlating with the model's factuality scores (negative coefficient of -0.85 observed for Gemini Pro). To further improve the factuality of LLM responses, we propose LUQ-ENSEMBLE, a method that ensembles responses from multiple models and selects the response with the lowest uncertainty. The ensembling method greatly improves the response factuality upon the best standalone LLM. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Structured Object language Modeling (SoLM): Native Structured Objects Generation Conforming to Complex Schemas with Self-Supervised Denoising

Structured Object Language Modeling (SoLM): Native Structure...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Tavanaei, Amir Koo, Kee Kiat Ceker, Hayreddin Jiang, Shaobai Li, Qi Han, Julien Bouyarmane, Karim Amazon Seattle United States

ISBN: (纸本)9798891761667

In this paper, we study the problem of generating structured objects that conform to a complex schema, with intricate dependencies between the different components (facets) of the object. The facets of the object (attributes, fields, columns, properties) can be a mix of short, structured, type-constrained facts, or long natural-language descriptions. The object has to be self-consistent between the different facets in the redundant information it carries (relative consistency), while being grounded with respect to world knowledge (absolute consistency). We frame the problem as a language Modeling problem (Structured Object language Modeling) and train an LLM to perform the task natively, without requiring instructions or prompt-engineering. We propose a self-supervised denoising method to train the model from an existing dataset of such objects. The input query can be the existing object itself, in which case the model acts as a regenerator, completing, correcting, normalizing the input, or any unstructured blurb to be structured. We show that the self-supervised denoising training provides a strong baseline, and that additional supervised fine-tuning with small amount of human demonstrations leads to further improvement. Experimental results show that the proposed method matches or outperforms prompt-engineered general-purpose state-of-the-art LLMs (Claude 3, Mixtral-8x7B), while being order-of-magnitude more cost-efficient. © 2024 Association for Computational Linguistics.

关键词： Structured Query language

来源：评论

学校读者我要写书评

暂无评论

Consistent Bidirectional language Modelling: Expressive Power and Representational Conciseness

Consistent Bidirectional Language Modelling: Expressive Powe...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Shopov, Georgi Gerdjikov, Stefan IICT Bulgarian Academy of Sciences Bulgaria FMI Sofia University Bulgaria

ISBN: (纸本)9798891761643

The inability to utilise future contexts and the pre-determined left-to-right generation order are major limitations of unidirectional language models. Bidirectionality has been introduced to address those deficiencies. However, a crucial shortcoming of bidirectional language models is the potential inconsistency of their conditional distributions. This fundamental flaw greatly diminishes their applicability and hinders their capability of tractable sampling and likelihood computation. In this work, we introduce a class of bidirectional language models, called latent language models, that are consistent by definition and can be efficiently used both for generation and scoring of sequences. We define latent language models based on the well-understood formalism of bisequential decompositions from automata theory. This formal correspondence allows us to precisely charaterise the abilities and limitations of a subclass of latent language models, called rational language models. As a result, we obtain that latent language models are exponentially more concise and significantly more expressive than unidirectional language models. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large language Models Fine-Tuning

AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Mem...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Yang, Yifan Zhen, Kai Banijamali, Ershad Mouchtaris, Athanasios Zhang, Zheng University of California Santa Barbara United States Amazon AGI United States

ISBN: (纸本)9798891761643

Fine-tuning large language models (LLMs) has achieved remarkable performance across various natural language processing tasks, yet it demands more and more memory as model sizes keep growing. To address this issue, the recently proposed Memory-efficient Zeroth-order (MeZO) methods attempt to fine-tune LLMs using only forward passes, thereby avoiding the need for a backpropagation graph. However, significant performance drops and a high risk of divergence have limited their widespread adoption. In this paper, we propose the Adaptive Zeroth-order Tensor-Train Adaption (AdaZeta) framework, specifically designed to improve the performance and convergence of the ZO methods. To enhance dimension-dependent ZO estimation accuracy, we introduce a fast-forward, low-parameter tensorized adapter. To tackle the frequently observed divergence issue in large-scale ZO finetuning tasks, we propose an adaptive query number schedule that guarantees convergence. Detailed theoretical analysis and extensive experimental results on Roberta-Large and Llama-2-7B models substantiate the efficacy of our AdaZeta framework in terms of accuracy, memory efficiency, and convergence speed. © 2024 Association for Computational Linguistics.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

User Inference Attacks on Large language Models

User Inference Attacks on Large Language Models

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Kandpal, Nikhil Pillutla, Krishna Oprea, Alina Kairouz, Peter Choquette-Choo, Christopher A. Xu, Zheng University of Toronto Vector Institute Canada Madras India Northeastern University United States Google United States

ISBN: (纸本)9798891761643

Text written by humans makes up the vast majority of the data used to pre-train and fine-tune large language models (LLMs).Many sources of this data-like code, forum posts, personal websites, and books-are easily attributed to one or a few "users".In this paper, we ask if it is possible to infer if any of a user's data was used to train an *** only would this constitute a breach of privacy, but it would also enable users to detect when their data was used for *** develop the first effective attacks for user inference-at times, with near-perfect success-against *** attacks are easy to employ, requiring only black-box access to an LLM and a few samples from the user, which need not be the ones that were trained *** find, both theoretically and empirically, that certain properties make users more susceptible to user inference: being an outlier, having highly correlated examples, and contributing a larger fraction of *** on these findings, we identify several methods for mitigating user inference including training with example-level differential privacy, removing within-user duplicate examples, and reducing a user's contribution to the training *** these provide partial mitigation, our work highlights the need to develop methods to fully protect LLMs from user inference. © 2024 Association for Computational Linguistics.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Contextualized Sequence Likelihood: Enhanced Confidence Scores for natural language Generation

Contextualized Sequence Likelihood: Enhanced Confidence Scor...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Lin, Zhen Trivedi, Shubhendu Sun, Jimeng University of Illinois Urbana-Champaign United States Carle's Illinois College of Medicine University of Illinois Urbana-Champaign United States

ISBN: (纸本)9798891761643

The advent of large language models (LLMs) has dramatically advanced the state-of-the-art in numerous natural language generation tasks. For LLMs to be applied reliably, it is essential to have an accurate measure of their confidence. Currently, the most commonly used confidence score function is the likelihood of the generated sequence, which, however, conflates semantic and syntactic components. For instance, in question-answering (QA) tasks, an awkward phrasing of the correct answer might result in a lower probability prediction. Additionally, different tokens should be weighted differently depending on the context. In this work, we propose enhancing the predicted sequence probability by assigning different weights to various tokens using attention values elicited from the base LLM. By employing a validation set, we can identify the relevant attention heads, thereby significantly improving the reliability of the vanilla sequence probability confidence measure. We refer to this new score as the Contextualized Sequence Likelihood (CSL). CSL is easy to implement, fast to compute, and offers considerable potential for further improvement with task-specific prompts. Across several QA datasets and a diverse array of LLMs, CSL has demonstrated significantly higher reliability than state-of-the-art baselines in predicting generation quality, as measured by the AUROC or AUARC. © 2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

We are Who We Cite: Bridges of Influence Between natural language processing and Other Academic Fields

We are Who We Cite: Bridges of Influence Between Natural Lan...

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Wahle, Jan Philip Ruas, Terry Abdalla, Mohamed Gipp, Bela Mohammad, Saif M. Natl Res Council Canada Ottawa ON Canada Univ Gottingen Gottingen Germany Inst Better Hlth Toronto ON Canada

ISBN: (纸本)9798891760608

natural language processing (NLP) is poised to substantially influence the world. However, significant progress comes hand-in-hand with substantial risks. Addressing them requires broad engagement with various fields of study. Yet, little empirical work examines the state of such engagement (past or current). In this paper, we quantify the degree of influence between 23 fields of study and NLP (on each other). We analyzed similar to 77k NLP papers, similar to 3.1m citations from NLP papers to other papers, and similar to 1.8m citations from other papers to NLP papers. We show that, unlike most fields, the cross-field engagement of NLP, measured by our proposed Citation Field Diversity Index (CFDI), has declined from 0.58 in 1980 to 0.31 in 2022 (an all-time low). In addition, we find that NLP has grown more insular-citing increasingly more NLP papers and having fewer papers that act as bridges between fields. NLP citations are dominated by computer science;Less than 8% of NLP citations are to linguistics, and less than 3% are to math and psychology. These findings underscore NLP's urgent need to reflect on its engagement with various fields.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Annotator-Centric Active Learning for Subjective NLP Tasks

Annotator-Centric Active Learning for Subjective NLP Tasks

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： van der Meer, Michiel Falk, Neele Murukannaiah, Pradeep K. Liscio, Enrico Idiap Research Institute Switzerland Leiden Institute of Advanced Computer Science Leiden University Netherlands Institute for Natural Language Processing University of Stuttgart Germany Interactive Intelligence TU Delft Netherlands

ISBN: (纸本)9798891761643

Active Learning (AL) addresses the high costs of collecting human annotations by strategically annotating the most informative ***, for subjective NLP tasks, incorporating a wide range of perspectives in the annotation process is crucial to capture the variability in human *** introduce Annotator-Centric Active Learning (ACAL), which incorporates an annotator selection strategy following data *** objective is two-fold: (1) to efficiently approximate the full diversity of human judgments, and (2) to assess model performance using annotator-centric metrics, which value minority and majority perspectives *** experiment with multiple annotator selection strategies across seven subjective NLP tasks, employing both traditional and novel, human-centered evaluation *** findings indicate that ACAL improves data efficiency and excels in annotator-centric performance ***, its success depends on the availability of a sufficiently large and diverse pool of annotators to sample from. © 2024 Association for Computational Linguistics.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

DA3: A Distribution-Aware Adversarial Attack against language Models

DA3: A Distribution-Aware Adversarial Attack against Languag...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Wang, Yibo Dong, Xiangjue Caverlee, James Yu, Philip S. University of Illinois Chicago United States Texas A&M University United States

ISBN: (纸本)9798891761643

language models can be manipulated by adversarial attacks, which introduce subtle perturbations to input data. While recent attack methods can achieve a relatively high attack success rate (ASR), we've observed that the generated adversarial examples have a different data distribution compared with the original examples. Specifically, these adversarial examples exhibit reduced confidence levels and greater divergence from the training data distribution. Consequently, they are easy to detect using straightforward detection methods, diminishing the efficacy of such attacks. To address this issue, we propose a Distribution-Aware Adversarial Attack (DA3) method. DA3 considers the distribution shifts of adversarial examples to improve attacks' effectiveness under detection methods. We further design a novel evaluation metric, the Non-detectable Attack Success Rate (NASR), which integrates both ASR and detectability for the attack task. We conduct experiments on four widely used datasets to validate the attack effectiveness and transferability of adversarial examples generated by DA3 against both the white-box BERT-BASE and ROBERTA-BASE models and the black-box LLAMA2-7B model. © 2024 Association for Computational Linguistics.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 24 25 26 27 28 29 30 31 32 33 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：