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

14,549 篇 会议
662 篇 期刊文献
101 册 图书
40 篇 学位论文
1 篇 科技报告

馆藏范围

15,352 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

11,015 篇 工学
- 10,349 篇 计算机科学与技术...
- 5,460 篇 软件工程
- 1,467 篇 信息与通信工程
- 956 篇 电气工程
- 892 篇 控制科学与工程
- 447 篇 生物工程
- 221 篇 网络空间安全
- 220 篇 化学工程与技术
- 186 篇 机械工程
- 177 篇 生物医学工程（可授...
- 141 篇 电子科学与技术（可...
- 101 篇 仪器科学与技术
- 100 篇 安全科学与工程
2,486 篇 理学
- 1,156 篇 数学
- 654 篇 物理学
- 520 篇 生物学
- 394 篇 统计学（可授理学、...
- 241 篇 系统科学
- 232 篇 化学
2,427 篇 管理学
- 1,756 篇 图书情报与档案管...
- 759 篇 管理科学与工程(可...
- 241 篇 工商管理
- 106 篇 公共管理
1,762 篇 文学
- 1,710 篇 外国语言文学
- 184 篇 中国语言文学
515 篇 医学
- 303 篇 临床医学
- 286 篇 基础医学(可授医学...
- 113 篇 公共卫生与预防医...
279 篇 法学
- 249 篇 社会学
239 篇 教育学
- 226 篇 教育学
100 篇 农学
96 篇 经济学
10 篇 艺术学
7 篇 哲学
4 篇 军事学

主题

3,552 篇 natural language...
1,789 篇 natural language...
953 篇 computational li...
741 篇 semantics
683 篇 machine learning
612 篇 deep learning
520 篇 natural language...
352 篇 computational mo...
343 篇 accuracy
339 篇 training
334 篇 large language m...
334 篇 sentiment analys...
325 篇 feature extracti...
312 篇 data mining
290 篇 speech processin...
260 篇 speech recogniti...
255 篇 transformers
236 篇 neural networks
218 篇 iterative method...
212 篇 support vector m...

机构

85 篇 carnegie mellon ...
51 篇 university of ch...
46 篇 tsinghua univers...
45 篇 carnegie mellon ...
43 篇 zhejiang univers...
43 篇 national univers...
38 篇 nanyang technolo...
36 篇 university of sc...
36 篇 university of wa...
35 篇 univ chinese aca...
34 篇 carnegie mellon ...
33 篇 stanford univers...
32 篇 gaoling school o...
32 篇 alibaba grp peop...
31 篇 school of artifi...
29 篇 tsinghua univ de...
28 篇 harbin institute...
27 篇 peking universit...
26 篇 microsoft resear...
26 篇 language technol...

作者

55 篇 zhou guodong
50 篇 neubig graham
46 篇 liu yang
39 篇 sun maosong
36 篇 zhang min
34 篇 liu qun
33 篇 smith noah a.
28 篇 schütze hinrich
26 篇 wen ji-rong
26 篇 liu zhiyuan
26 篇 lapata mirella
24 篇 chang kai-wei
23 篇 zhou jie
23 篇 yang diyi
23 篇 zhao hai
23 篇 zhao wayne xin
21 篇 chua tat-seng
20 篇 dredze mark
18 篇 biemann chris
18 篇 fung pascale

语言

14,307 篇 英文
930 篇 其他
114 篇 中文
18 篇 法文
14 篇 土耳其文
2 篇 德文
2 篇 西班牙文
2 篇 俄文

检索条件"任意字段=Conference on empirical methods in natural language processing"

共 15353 条记录，以下是1131-1140 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：

TREE OF UNCERTAIN THOUGHTS REASONING FOR LARGE language MODELS 49

TREE OF UNCERTAIN THOUGHTS REASONING FOR LARGE LANGUAGE MODE...

引用

49th IEEE International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Mo, Shentong Xin, Miao Carnegie Mellon Univ Pittsburgh PA USA MBZUAI Abu Dhabi U Arab Emirates Chinese Acad Sci Inst Automat Beijing Peoples R China

ISBN: (纸本)9798350344868;9798350344851

While the recently introduced Tree of Thoughts (ToT) has heralded advancements in allowing Large language Models (LLMs) to reason through foresight and backtracking for global decision-making, it has overlooked the inherent local uncertainties in intermediate decision points or "thoughts". These local uncertainties, intrinsic to LLMs given their potential for diverse responses, remain a significant concern in the reasoning process. Addressing this pivotal gap, we introduce the Tree of Uncertain Thoughts (TouT) - a reasoning framework tailored for LLMs. Our TouT effectively leverages Monte Carlo Dropout to quantify uncertainty scores associated with LLMs' diverse local responses at these intermediate steps. By marrying this local uncertainty quantification with global search algorithms, TouT enhances the model's precision in response generation. We substantiate our approach with rigorous experiments on two demanding planning tasks: Game of 24 and Mini Crosswords. The empirical evidence underscores TouT's superiority over both ToT and chain-of-thought prompting methods.

关键词： large language models tree of thoughts uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

Can we teach language models to gloss endangered languages?

Can we teach language models to gloss endangered languages?

引用

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

作者： Ginn, Michael Hulden, Mans Palmer, Alexis University of Colorado United States New College of Florida United States

ISBN: (纸本)9798891761681

Interlinear glossed text (IGT) is a popular format in language documentation projects, where each morpheme is labeled with a descriptive annotation. Automating the creation of interlinear glossed text would be desirable to reduce annotator effort and maintain consistency across annotated corpora. Prior research (Ginn et al., 2023;Zhao et al., 2020;Moeller and Hulden, 2018) has explored a number of statistical and neural methods for automatically producing IGT. As large language models (LLMs) have showed promising results across multilingual tasks, even for rare, endangered languages (Zhang et al., 2024), it is natural to wonder whether they can be utilized for the task of generating IGT. We explore whether LLMs can be effective at the task of interlinear glossing with in-context learning, without any traditional training. We propose new approaches for selecting examples to provide in-context, observing that targeted selection can significantly improve performance. We find that LLM-based methods beat standard transformer baselines, despite requiring no training at all. These approaches still underperform state-of-the-art supervised systems for the task, but are highly practical for researchers outside of the NLP community, requiring minimal effort to use. © 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

Exploring Design Choices for Building language-Specific LLMs

Exploring Design Choices for Building Language-Specific LLMs

引用

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

作者： Tejaswi, Atula Gupta, Nilesh Choi, Eunsol Department of Computer Science The University of Texas Austin United States

ISBN: (纸本)9798891761681

Despite rapid progress in large language models (LLMs), their performance on a vast majority of languages remains unsatisfactory. In this paper, we study building language-specific LLMs by adapting monolingual and multilingual LLMs. We conduct systematic experiments on how design choices (base model selection, vocabulary extension, and continued pretraining) impact the adapted LLM, both in terms of efficiency (how many tokens are needed to encode the same amount of information) and end task performance. We find that (1) the initial performance of LLM does not always correlate with the final performance after the adaptation. Adapting an English-centric models can yield better results than adapting multilingual models despite their worse initial performance on low-resource languages. (2) Efficiency can easily improved with simple vocabulary extension and continued pretraining in most LLMs we study, and (3) The optimal adaptation method (choice of the base model, new vocabulary size, training data, initialization strategy) is highly language-dependent, and the simplest embedding initialization works well across various experimental settings. Together, our work lays foundations on efficiently building language-specific LLMs by adapting existing LLMs. © 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

The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 languages

The Skipped Beat: A Study of Sociopragmatic Understanding in...

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Zhang, Chiyu Doan, Khai Duy Liao, Qisheng Abdul-Mageed, Muhammad Univ British Columbia Deep Learning & Nat Language Proc Grp Vancouver BC Canada MBZUAI Dept Nat Language Proc Abu Dhabi U Arab Emirates MBZUAI Dept Machine Learning Abu Dhabi U Arab Emirates

ISBN: (纸本)9798891760608

Instruction tuned large language models (LLMs), such as ChatGPT, demonstrate remarkable performance in a wide range of tasks. Despite numerous recent studies that examine the performance of instruction-tuned LLMs on various NLP benchmarks, there remains a lack of comprehensive investigation into their ability to understand cross-lingual sociopragmatic meaning (SM), i.e., meaning embedded within social and interactive contexts. This deficiency arises partly from SM not being adequately represented in any of the existing benchmarks. To address this gap, we present SPARROW, an extensive multilingual benchmark specifically designed for SM understanding. SPARROW comprises 169 datasets covering 13 task types across six primary categories (e.g., anti-social language detection, emotion recognition). SPARROW datasets encompass 64 different languages originating from 12 language families representing 16 writing scripts. We evaluate the performance of various multilingual pretrained language models (e.g., mT5) and instruction-tuned LLMs (e.g., BLOOMZ, ChatGPT) on SPARROW through fine-tuning, zero-shot, and/or few-shot learning. Our comprehensive analysis reveals that existing opensource instruction tuned LLMs still struggle to understand SM across various languages, performing close to a random baseline in some cases. We also find that although ChatGPT outperforms many LLMs, it still falls behind task-specific finetuned models with a gap of 12.19 SPARROW score. Our benchmark is available at: https://***/UBC-NLP/SPARROW

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

PIEClass: Weakly-Supervised Text Classification with Prompting and Noise-Robust Iterative Ensemble Training

PIEClass: Weakly-Supervised Text Classification with Prompti...

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Zhang, Yunyi Jiang, Minhao Meng, Yu Zhang, Yu Han, Jiawei Univ Illinois Urbana IL 61801 USA

ISBN: (纸本)9798891760608

Weakly-supervised text classification trains a classifier using the label name of each target class as the only supervision, which largely reduces human annotation efforts. Most existing methods first use the label names as static keyword-based features to generate pseudo labels, which are then used for final classifier training. While reasonable, such a commonly adopted framework suffers from two limitations: (1) keywords can have different meanings in different contexts and some texts may not explicitly contain any keyword, so keyword matching can induce noisy and inadequate pseudo labels;(2) the errors made in the pseudo label generation stage will directly propagate to the classifier training stage without a chance of being corrected. In this paper, we propose a new method, PIEClass, consisting of two modules: (1) a pseudo label acquisition module that uses zero-shot prompting of pre-trained language models (PLM) to get pseudo labels based on contextualized text understanding beyond static keyword matching, and (2) a noise-robust iterative ensemble training module that iteratively trains classifiers and updates pseudo labels by utilizing two PLM fine-tuning methods that regularize each other. Extensive experiments show that PIEClass achieves overall better performance than existing strong baselines on seven benchmark datasets and even achieves similar performance to fully-supervised classifiers on sentiment classification tasks.(1)

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

UNO Arena for Evaluating Sequential Decision-Making Capability of Large language Models

UNO Arena for Evaluating Sequential Decision-Making Capabili...

引用

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

作者： Qin, Zhanyue Wang, Haochuan Liu, Deyuan Song, Ziyang Fan, Cunhang Lv, Zhao Wu, Jinlin Lei, Zhen Tu, Zhiying Chu, Dianhui Yu, Xiaoyan Sui, Dianbo Harbin Institute of Technology China Anhui University China CAIR HKISI-CAS China CASIA China UCAS China Beijing Institute of Technology China

ISBN: (纸本)9798891761643

Sequential decision-making refers to algorithms that take into account the dynamics of the environment, where early decisions affect subsequent decisions. With large language models (LLMs) demonstrating powerful capabilities among various tasks, we cannot help but ask: Can Current LLMs Make Sequential Decisions Effectively? In order to answer this question, we propose the UNO Arena based on the card game UNO for evaluating the sequential decision-making capability of LLMs and explain in detail why we choose the UNO game. In the UNO Arena, we also involve some novel metrics based on Monte Carlo methods for evaluating the sequential decision-making capability of LLMs dynamically. Besides, we set up random players, DQN-based reinforcement learning players, and LLM players (e.g. GPT-4, Gemini-pro) for comparison testing. Furthermore, in order to improve the sequential decision-making capability of LLMs, we propose the TUTRI player, which can involve enabling LLMs to reflect on their actions with the summary of game history and the game strategy. Various experimental results demonstrate that the TUTRI player can achieve a notable breakthrough in the performance of sequential decision-making compared to the vanilla LLM player. © 2024 Association for Computational Linguistics.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Adapter Pruning using Tropical Characterization

Adapter Pruning using Tropical Characterization

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Bhardwaj, Rishabh Vaidya, Tushar Poria, Soujanya Singapore Univ Technol & Design Singapore Singapore Nanyang Technol Univ Singapore Singapore

ISBN: (纸本)9798891760615

Adapters are widely popular parameter-efficient transfer learning approaches in natural language processing that insert trainable modules in between layers of a pre-trained language model. Apart from several heuristics, however, there has been a lack of studies analyzing the optimal number of adapter parameters needed for downstream applications. In this paper, we propose an adapter pruning approach by studying the tropical characteristics of trainable modules. We cast it as an optimization problem that aims to prune parameters from the adapter layers without changing the orientation of underlying tropical hypersurfaces. Our experiments on five NLP datasets show that tropical geometry tends to identify more relevant parameters to prune when compared with the magnitude-based baseline, while a combined approach works best across the tasks.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in language Models

Prompt as Triggers for Backdoor Attack: Examining the Vulner...

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Zhao, Shuai Wen, Jinming Tuan, Luu Anh Zhao, Junbo Fu, Jie Jinan Univ Guangzhou Peoples R China Hong Kong Univ Sci & Technol Hong Kong Peoples R China Nanyang Technol Univ Singapore Singapore Zhejiang Univ Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9798891760608

The prompt-based learning paradigm, which bridges the gap between pre-training and fine-tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot settings. Despite being widely applied, prompt-based learning is vulnerable to backdoor attacks. Textual backdoor attacks are designed to introduce targeted vulnerabilities into models by poisoning a subset of training samples through trigger injection and label modification. However, they suffer from flaws such as abnormal natural language expressions resulting from the trigger and incorrect labeling of poisoned samples. In this study, we propose ProAttack, a novel and efficient method for performing clean-label backdoor attacks based on the prompt, which uses the prompt itself as a trigger. Our method does not require external triggers and ensures correct labeling of poisoned samples, improving the stealthy nature of the backdoor attack. With extensive experiments on rich-resource and few-shot text classification tasks, we empirically validate ProAttack's competitive performance in textual backdoor attacks. Notably, in the rich-resource setting, ProAttack achieves state-of-the-art attack success rates in the clean-label backdoor attack benchmark without external triggers(1).

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Based on the Semantics Analysis of the URL Identification and Malicious Code Detection 24

Based on the Semantics Analysis of the URL Identification an...

引用

1st International conference on Image processing Machine Learning and Pattern Recognition

作者： Wang Mingxin Wuhan Res Inst Posts & Telecommun Wuhan Peoples R China

ISBN: (纸本)9798400707032

The traditional malicious URL identification methods usually adopt blacklist technology, heuristic algorithm and machine learning algorithm. This paper considers that natural language processing technology can be introduced when dealing with text with context. This technique is used to help computers understand, interpret, and manipulate human language. It is often used to deal with contextual problems, and when combined with malicious URL directions, it can produce more accurate models than existing methods. In addition to the traditional TF-IDF detection method, this paper introduces N-Gram and Word2vec methods for the first time, a total of three different natural language processing technologies to process and extract URL data. Through a series of experiments, this paper proves that semantic analysis can improve the accuracy of malicious code detection successfully by adjusting parameters of the optimization model. The final experimental results show that the detection rate of malicious URLs by TF-IDF method and N-Gram method combined with various machine learning models is about 85%, while the detection rate of Word2vec method combined with deep learning model reaches 99%, and the detection accuracy is significantly improved.

关键词： Malicious URL detection natural language processing (NLP) Machine Learning Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Shall We Pretrain Autoregressive language Models with Retrieval? A Comprehensive Study

Shall We Pretrain Autoregressive Language Models with Retrie...

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Wang, Boxin Ping, Wei Xu, Peng McAfee, Lawrence Liu, Zihan Shoeybi, Mohammad Dong, Yi Kuchaiev, Oleksii Li, Bo Xiao, Chaowei Anandkumar, Anima Catanzaro, Bryan UIUC Urbana IL 61801 USA NVIDIA Santa Clara CA 95051 USA Univ Wisconsin Madison WI 53706 USA

ISBN: (纸本)9798891760608

Large decoder-only language models (LMs) can be largely improved in terms of perplexity by retrieval (e.g., RETRO), but its impact on text generation quality and downstream task accuracy is unclear. Thus, it is still an open question: shall we pretrain large autoregressive LMs with retrieval? To answer it, we perform a comprehensive study on a scalable pretrained retrieval-augmented LM (i.e., RETRO) compared with standard GPT and retrievalaugmented GPT incorporated at fine-tuning or inference stages. We first provide the recipe to reproduce RETRO up to 9.5B parameters while retrieving a text corpus with 330B tokens. Based on that, we have the following novel findings: i) RETRO outperforms GPT on text generation with much less degeneration (i.e., repetition), moderately higher factual accuracy, and slightly lower toxicity with a nontoxic retrieval database. ii) On the LM Evaluation Harness benchmark, RETRO largely outperforms GPT on knowledge-intensive tasks, but is on par with GPT on other tasks. Furthermore, we introduce a simple variant of the model, RETRO++, which largely improves open-domain QA results of original RETRO (e.g., EM score +8.6 on natural Question) and significantly outperforms retrieval-augmented GPT in both finetuning and zero-shot evaluation settings. Our findings highlight the promising direction of pretraining autoregressive LMs with retrieval as future foundation models. We release our implementation at: https://***/N VIDIA/Megatron- LM#retro.

关键词： Computational linguistics

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 << < 110 111 112 113 114 115 116 117 118 119 > >>

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：