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

14,600 篇 会议
625 篇 期刊文献
101 册 图书
37 篇 学位论文

馆藏范围

15,362 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

10,994 篇 工学
- 10,330 篇 计算机科学与技术...
- 5,391 篇 软件工程
- 1,449 篇 信息与通信工程
- 956 篇 电气工程
- 878 篇 控制科学与工程
- 433 篇 生物工程
- 222 篇 网络空间安全
- 218 篇 化学工程与技术
- 185 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
2,447 篇 理学
- 1,138 篇 数学
- 652 篇 物理学
- 503 篇 生物学
- 379 篇 统计学（可授理学、...
- 240 篇 系统科学
- 231 篇 化学
2,381 篇 管理学
- 1,726 篇 图书情报与档案管...
- 742 篇 管理科学与工程(可...
- 235 篇 工商管理
- 104 篇 公共管理
1,823 篇 文学
- 1,771 篇 外国语言文学
- 169 篇 中国语言文学
504 篇 医学
- 300 篇 临床医学
- 282 篇 基础医学(可授医学...
- 111 篇 公共卫生与预防医...
275 篇 法学
- 245 篇 社会学
237 篇 教育学
- 225 篇 教育学
100 篇 农学
93 篇 经济学
10 篇 艺术学
7 篇 哲学
4 篇 军事学

主题

3,563 篇 natural language...
1,791 篇 natural language...
950 篇 computational li...
753 篇 semantics
686 篇 machine learning
620 篇 deep learning
518 篇 natural language...
373 篇 computational mo...
369 篇 accuracy
356 篇 training
349 篇 large language m...
338 篇 sentiment analys...
328 篇 feature extracti...
311 篇 data mining
289 篇 speech processin...
262 篇 transformers
260 篇 speech recogniti...
236 篇 neural networks
218 篇 iterative method...
216 篇 support vector m...

机构

85 篇 carnegie mellon ...
52 篇 university of ch...
45 篇 tsinghua univers...
44 篇 carnegie mellon ...
42 篇 zhejiang univers...
41 篇 national univers...
35 篇 univ chinese aca...
35 篇 nanyang technolo...
35 篇 carnegie mellon ...
34 篇 university of sc...
34 篇 university of wa...
33 篇 alibaba grp peop...
32 篇 gaoling school o...
32 篇 stanford univers...
30 篇 tsinghua univ de...
30 篇 school of artifi...
28 篇 peking universit...
27 篇 harbin institute...
27 篇 language technol...
26 篇 univ sci & techn...

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

13,826 篇 英文
1,418 篇 其他
123 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 15363 条记录，以下是1331-1340 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：

Code-Switched language Identification is Harder Than You Think 18

Code-Switched Language Identification is Harder Than You Thi...

引用

18th conference of the European-Chapter of the Association-for-Computational-Linguistics (EACL)

作者： Burchell, Laurie Birch, Alexandra Thompson, Robert P. Heafield, Kenneth Univ Edinburgh Sch Informat Inst Language Cognit & Computat 10 Crichton St Edinburgh EH8 9AB Midlothian Scotland Univ Cambridge Dept Mat Sci & Met 27 Charles Babbage Rd Cambridge CB3 0FS England

ISBN: (纸本)9798891760882

Code switching (CS) is a very common phenomenon in written and spoken communication but one that is handled poorly by many natural language processing (NLP) applications. Looking to the application of building CS corpora, we explore CS language identification (LID) for corpus building. We make the task more realistic by scaling it to more languages and considering models with simpler architectures for faster inference. We also reformulate the task as a sentence-level multi-label tagging problem to make it more tractable. Having defined the task, we investigate three reasonable models for this task and define metrics which better reflect desired performance. We present empirical evidence that no current approach is adequate and finally provide recommendations for future work in this area.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Narrowing the Gap between Supervised and Unsupervised Sentence Representation Learning with Large language Model 38

Narrowing the Gap between Supervised and Unsupervised Senten...

引用

38th AAAI conference on Artificial Intelligence (AAAI) / 36th conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence

作者： Li, Mingxin Zhang, Richong Nie, Zhijie Mao, Yongyi Beihang Univ Sch Comp Sci & Engn SKLSDE Beijing Peoples R China Zhongguancun Lab Beijing Peoples R China Beihang Univ Shen Yuan Honors Coll Beijing Peoples R China Univ Ottawa Sch Elect Engn & Comp Sci Ottawa ON Canada

ISBN: (纸本)1577358872

Sentence Representation Learning (SRL) is a fundamental task in natural language processing (NLP), with the Contrastive Learning of Sentence Embeddings (CSE) being the mainstream technique due to its superior performance. An intriguing phenomenon in CSE is the significant performance gap between supervised and unsupervised methods, with their only difference lying in the training data. Previous works attribute this performance gap to differences in two representation properties (alignment and uniformity). However, since alignment and uniformity only measure the results, they fail to answer "What aspects of the training data contribute to the performance gap?" and "How can the performance gap be narrowed?". In this paper, we conduct empirical experiments to answer these "What" and "How" questions. We first answer the "What" question by thoroughly comparing the behavior of supervised and unsupervised CSE during their respective training processes. From the comparison, we identify the similarity pattern as a key factor to the performance gap, and introduce a metric, called Relative Fitting Difficulty (RFD), to measure the complexity of the similarity pattern. Then, based on the insights gained from the "What" question, we tackle the "How" question by increasing the pattern complexity of the training data. We achieve this by leveraging the In-Context Learning (ICL) capability of the Large language Model (LLM) to generate data that simulates complex patterns. By utilizing the hierarchical patterns in the LLM-generated data, we effectively narrow the gap between supervised and unsupervised CSE. We release our codes and appendix at https://***/BDBC-KG-NLP/NGCSE.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Improving Adversarial Robustness in Vision-language Models with Architecture and Prompt Design

Improving Adversarial Robustness in Vision-Language Models w...

引用

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

作者： Bhagwatkar, Rishika Nayak, Shravan Bashivan, Pouya Rish, Irina Mila - Quebec AI Institute Canada Université de Montréal Canada McGill University Canada

ISBN: (纸本)9798891761681

Vision-language Models (VLMs) have seen a significant increase in both research interest and real-world applications across various domains, including healthcare, autonomous systems, and security. However, their growing prevalence demands higher reliability and safety including robustness to adversarial attacks. We systematically examine the possibility of incorporating adversarial robustness through various model design choices. We explore the effects of different vision encoders, the resolutions of vision encoders, and the size and type of language models. Additionally, we introduce novel, cost-effective approaches to enhance robustness through prompt engineering. By simply suggesting the possibility of adversarial perturbations or rephrasing questions, we demonstrate substantial improvements in model robustness against strong image-based attacks such as Auto-PGD. Our findings provide important guidelines for developing more robust VLMs, particularly for deployment in safety-critical environments where reliability and security are paramount. These insights are crucial for advancing the field of VLMs, ensuring they can be safely and effectively utilized in a wide range of applications. © 2024 Association for Computational Linguistics.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Mitigating Catastrophic Forgetting in language Transfer via Model Merging

Mitigating Catastrophic Forgetting in Language Transfer via ...

引用

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

作者： Alexandrov, Anton Raychev, Veselin Müller, Mark Niklas Zhang, Ce Vechev, Martin Toutanova, Kristina INSAIT Sofia University "St. Kliment Ohridski" Bulgaria LogicStar.ai ETH Zurich Switzerland University of Chicago United States Together AI Google DeepMind United Kingdom

ISBN: (纸本)9798891761681

As open-weight large language models (LLMs) achieve ever more impressive performances across a wide range of tasks in English, practitioners aim to adapt these models to different languages. However, such language adaptation is often accompanied by catastrophic forgetting of the base model's capabilities, severely limiting the usefulness of the resulting model. We address this issue by proposing Branch- and-Merge (BAM), a new adaptation method based on iteratively merging multiple models, fine-tuned on a subset of the available training data. BAM is based on the insight that this yields lower magnitude but higher quality weight changes, reducing forgetting of the source domain while maintaining learning on the target domain. We demonstrate in an extensive empirical study on Bulgarian and German that BAM can significantly reduce forgetting while matching or even improving target domain performance compared to both standard continued pretraining and instruction finetuning across different model architectures. © 2024 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BLT: Can Large language Models Handle Basic Legal Text? 6

BLT: Can Large Language Models Handle Basic Legal Text?

引用

6th natural Legal language processing Workshop 2024, NLLP 2024, co-located with the 2024 conference on empirical methods in natural language processing

作者： Blair-Stanek, Andrew Holzenberger, Nils Van Durme, Benjamin Johns Hopkins University United States University of Maryland School of Law United States Télécom Paris - Institut Polytechnique de Paris France

ISBN: (纸本)9798891761834

We find that the best publicly available LLMs like GPT-4 and Claude currently perform poorly on basic legal text handling. This motivates the creation of a benchmark consisting of examples that lawyers and paralegals would expect LLMs to handle zero-shot, such as looking up the text at a line of a witness deposition or at a subsection of a contract. LLMs' poor performance on this benchmark casts into doubt their reliability as-is for legal practice. However, fine-tuning on our training set brings even a small model to near-perfect performance. This benchmark will be useful for fine-tuning LLMs for downstream legal tasks, as well as for tracking LLMs' reliability as-is for basic legal tasks. ©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

Self-training Large language Models through Knowledge Detection

Self-training Large Language Models through Knowledge Detect...

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Yeo, Wei Jie Ferdinan, Teddy Kazienko, Przemyslaw Satapathy, Ranjan Cambria, Erik Singapore Singapore Singapore

ISBN: (纸本)9798891761681

Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autonomously curates its own labels and selectively trains on unknown data samples identified through a reference-free consistency method. empirical evaluations demonstrate significant improvements in reducing hallucination in generation across multiple subjects. Furthermore, the selective training framework mitigates catastrophic forgetting in out-of-distribution benchmarks, addressing a critical limitation in training LLMs. Our findings suggest that such an approach can substantially reduce the dependency on large labeled datasets, paving the way for more scalable and cost-effective language model training. © 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

AUTOHALLUSION: Automatic Generation of Hallucination Benchmarks for Vision-language Models

AUTOHALLUSION: Automatic Generation of Hallucination Benchma...

引用

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

作者： Wu, Xiyang Guan, Tianrui Li, Dianqi Huang, Shuaiyi Liu, Xiaoyu Wang, Xijun Xian, Ruiqi Shrivastava, Abhinav Huang, Furong Boyd-Graber, Jordan Lee Zhou, Tianyi Manocha, Dinesh University of Maryland College Park United States

ISBN: (纸本)9798891761681

Large vision-language models (LVLMs) are prone to hallucinations, where certain contextual cues in an image can trigger the language module to produce overconfident and incorrect reasoning about abnormal or hypothetical *** some benchmarks have been developed to investigate LVLM hallucinations, they often rely on hand-crafted corner cases whose failure patterns may not generalize ***, fine-tuning on these examples could undermine their *** address this, we aim to scale up the number of cases through an automated approach, reducing human bias in crafting such corner *** motivates the development of AUTOHALLUSION, the first automated benchmark generation approach that employs several key strategies to create a diverse range of hallucination *** generated visual-question pairs pose significant challenges to LVLMs, requiring them to overcome contextual biases and distractions to arrive at correct *** enables us to create new benchmarks at the minimum cost and thus overcomes the fragility of hand-crafted *** also reveals common failure patterns and reasons, providing key insights to detect, avoid, or control *** evaluations of top-tier LVLMs, e.g., GPT-4V(ision), Gemini Pro Vision, Claude 3, and LLaVA-1.5, show a 97.7% and 98.7% success rate of hallucination induction on synthetic and real-world datasets of AUTOHALLUSION, paving the way for a long battle against *** codebase and data can be accessed at https://***/wuxiyang1996/AutoHallusion. © 2024 Association for Computational Linguistics.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Scalable and Domain-General Abstractive Proposition Segmentation

Scalable and Domain-General Abstractive Proposition Segmenta...

引用

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

作者： Hosseini, Mohammad Javad Gao, Yang Baumgärtner, Tim Fabrikant, Alex Amplayo, Reinald Kim Google DeepMind United Kingdom Ubiquitous Knowledge Processing Lab Technical University of Darmstadt Germany

ISBN: (纸本)9798891761681

Segmenting text into fine-grained units of meaning is important to a wide range of NLP *** default approach of segmenting text into sentences is often insufficient, especially since sentences are usually complex enough to include multiple units of meaning that merit separate treatment in the downstream *** focus on the task of abstractive proposition segmentation (APS): transforming text into simple, self-contained, well-formed *** recent works have demonstrated the utility of proposition segmentation with few-shot prompted LLMs for downstream tasks such as retrieval-augmented grounding and fact ***, this approach does not scale to large amounts of text and may not always extract all the facts from the input *** this paper, we first introduce evaluation metrics for the task to measure several dimensions of *** then propose a scalable, yet accurate, proposition segmentation *** model proposition segmentation as a supervised task by training LLMs on existing annotated datasets and show that training yields significantly improved *** further show that by using the fine-tuned LLMs (Gemini Pro and Gemini Ultra) as teachers for annotating large amounts of multi-domain synthetic distillation data, we can train smaller student models (Gemma 1 2B and 7B) with results similar to the teacher *** then demonstrate that our technique leads to effective domain generalization, by annotating data in two domains outside the original training data and evaluating on ***, as a key contribution of the paper, we share an easy-to-use API1 for NLP practitioners to use. © 2024 Association for Computational Linguistics.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Breaking language Barriers in Multilingual Mathematical Reasoning: Insights and Observations

Breaking Language Barriers in Multilingual Mathematical Reas...

引用

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

作者： Chen, Nuo Zheng, Zinan Wu, Ning Gong, Ming Zhang, Dongmei Li, Jia Hong Kong University of Science and Technology Hong Kong Microsoft United States

ISBN: (纸本)9798891761681

Existing research predominantly focuses on developing powerful large language models (LLMs) for mathematical reasoning within monolingual languages, with few explorations in preserving efficacy in a multilingual context. To bridge this gap, this paper pioneers exploring and training powerful Multilingual Math Reasoning (xMR) LLMs. Firstly, by utilizing translation, we construct the first multilingual math reasoning instruction dataset, MGSM8KInstruct, encompassing ten distinct languages, thus addressing the issue of training data scarcity in xMR tasks. Based on the collected dataset, we propose different training strategies to build powerful xMR LLMs, named MathOctopus, which notably outperform conventional open-source LLMs and exhibit superiority over ChatGPT in few-shot scenarios. Notably, MathOctopus-13B reaches 47.6% accuracy which exceeds ChatGPT 46.3% on MGSM testset. Beyond remarkable results, we unearth several pivotal observations and insights: (1) When extending the rejection sampling strategy to the multilingual context, it proves effective for model performances, albeit limited. (2) Employing parallel corpora for math Supervised Fine-Tuning (SFT) across multiple languages not only significantly enhances model performance multilingually and elevates their monolingual performance. This indicates that crafting multilingual corpora can be regarded as a vital strategy for enhancing model performance in a specific language, especially in mathematical reasoning tasks. For instance, MathOctopus-7B improves its counterparts that trained on English from 42.4% to 50.8% on the GSM8K test set. © 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

Improving Few-Shot Cross-Domain Named Entity Recognition by Instruction Tuning a Word-Embedding based Retrieval Augmented Large language Model

Improving Few-Shot Cross-Domain Named Entity Recognition by ...

引用

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

作者： Nandi, Subhadip Agrawal, Neeraj IIT Kanpur India IISc Bangalore India

ISBN: (纸本)9798891761667

Few-Shot Cross-Domain NER is the process of leveraging knowledge from data-rich source domains to perform entity recognition on data-scarce target domains. Most previous state-of-the-art (SOTA) approaches use pre-trained language models (PLMs) for cross-domain NER. However, these models are often domain specific. To successfully use these models for new target domains, we need to modify either the model architecture or perform model finetuning using data from the new domains. Both of these result in the creation of entirely new NER models for each target domain which is infeasible for practical scenarios. Recently, several works have attempted to use LLMs to solve Few-Shot Cross-Domain NER. However, most of these are either too expensive for practical purposes or struggle to follow LLM prompt instructions. In this paper, we propose IF-WRANER (Instruction Finetuned Word-embedding based Retrieval Augmented large language model for Named Entity Recognition), a retrieval augmented LLM, finetuned for the NER task. By virtue of the regularization techniques used during LLM finetuning and the adoption of word-level embedding over sentence-level embedding during the retrieval of in-prompt examples, IF-WRANER is able to outperform previous SOTA Few-Shot Cross-Domain NER approaches. We have demonstrated the effectiveness of our model by benchmarking its performance on the open source CrossNER dataset, on which it shows more than 2% F1 score improvement over the previous SOTA model. We have deployed the model for multiple customer care domains of an enterprise. Accurate entity prediction through IF-WRANER helps direct customers to automated workflows for the domains, thereby reducing escalations to human agents by almost 15% and leading to millions of dollars in yearly savings for the company. © 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

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 << < 130 131 132 133 134 135 136 137 138 139 > >>

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：