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

14,416 篇 会议
650 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

15,207 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

10,942 篇 工学
- 10,282 篇 计算机科学与技术...
- 5,394 篇 软件工程
- 1,487 篇 信息与通信工程
- 960 篇 电气工程
- 898 篇 控制科学与工程
- 446 篇 生物工程
- 239 篇 网络空间安全
- 222 篇 化学工程与技术
- 192 篇 机械工程
- 173 篇 生物医学工程（可授...
- 144 篇 电子科学与技术（可...
- 109 篇 安全科学与工程
- 104 篇 交通运输工程
2,490 篇 理学
- 1,167 篇 数学
- 652 篇 物理学
- 518 篇 生物学
- 396 篇 统计学（可授理学、...
- 241 篇 系统科学
- 232 篇 化学
2,426 篇 管理学
- 1,757 篇 图书情报与档案管...
- 763 篇 管理科学与工程(可...
- 239 篇 工商管理
- 109 篇 公共管理
1,761 篇 文学
- 1,709 篇 外国语言文学
- 184 篇 中国语言文学
515 篇 医学
- 300 篇 临床医学
- 281 篇 基础医学(可授医学...
- 117 篇 公共卫生与预防医...
274 篇 法学
- 247 篇 社会学
236 篇 教育学
- 223 篇 教育学
100 篇 农学
97 篇 经济学
9 篇 艺术学
7 篇 哲学
4 篇 军事学

主题

3,531 篇 natural language...
1,755 篇 natural language...
952 篇 computational li...
736 篇 semantics
686 篇 machine learning
610 篇 deep learning
520 篇 natural language...
345 篇 computational mo...
334 篇 training
333 篇 sentiment analys...
329 篇 accuracy
323 篇 large language m...
319 篇 feature extracti...
311 篇 data mining
290 篇 speech processin...
265 篇 speech recogniti...
251 篇 transformers
237 篇 neural networks
217 篇 iterative method...
211 篇 support vector m...

机构

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

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
27 篇 liu zhiyuan
27 篇 lapata mirella
26 篇 wen ji-rong
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

14,595 篇 英文
500 篇 其他
102 篇 中文
18 篇 法文
15 篇 土耳其文
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 15208 条记录，以下是181-190 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：

Forecasting Credit Ratings: A Case Study where Traditional methods Outperform Generative LLMs 9

Forecasting Credit Ratings: A Case Study where Traditional M...

引用

Joint Workshop of the 9th Financial Technology and natural language processing, FinNLP 2025, the 6th Financial Narrative processing, FNP 2025, and the 1st Workshop on Large language Models for Finance and Legal, LLMFinLegal 2025, co-located with the 31st International conference on Computational Linguistics, COLING 2025

作者： Drinkall, Felix Pierrehumbert, Janet B. Zohren, Stefan Department of Engineering Science University of Oxford United Kingdom The Alan Turing Institute United Kingdom Faculty of Linguistics University of Oxford United Kingdom

ISBN: (纸本)9798891762091

Large language Models (LLMs) have been shown to perform well for many downstream tasks. Transfer learning can enable LLMs to acquire skills that were not targeted during pretraining. In financial contexts, LLMs can sometimes beat well-established benchmarks. This paper investigates how well LLMs perform at forecasting corporate credit ratings. We show that while LLMs are very good at encoding textual information, traditional methods are still very competitive when it comes to encoding numeric and multimodal data. For our task, current LLMs perform worse than a more traditional XGBoost architecture that combines fundamental and macroeconomic data with high-density text-based embedding features. We investigate the degree to which the text encoding methodology affects performance and interpretability. The dataset reconstruction and model code from this paper is provided1. © 2025 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

Boosting Large language Model for Speech Synthesis: An empirical Study

Boosting Large Language Model for Speech Synthesis: An Empir...

引用

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

作者： Hongkun Hao Long Zhou Shujie Liu Jinyu Li Shujie Hu Rui Wang Furu Wei Shanghai Jiao Tong University Microsoft Corporation

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Large language models (LLMs) have made significant advancements in natural language processing and are concurrently extending the language ability to other modalities, such as speech and vision. Nevertheless, most of the previous work focuses on prompting LLMs with perception abilities like auditory comprehension, and the effective approach for augmenting LLMs with speech synthesis capabilities remains ambiguous. In this paper, we conduct a comprehensive empirical exploration of boosting LLMs with the ability to generate speech, by combining pre-trained LLM LLaMA/OPT and text-to-speech synthesis model VALL-E. We compare three integration methods between LLMs and speech synthesis models, including directly fine-tuned LLMs, superposed layers of LLMs and VALL-E, and coupled LLMs and VALL-E using LLMs as a powerful text encoder. Experimental results show that, using LoRA method to fine-tune LLMs directly to boost the speech synthesis capability does not work well, and superposed LLMs and VALL-E can improve the quality of generated speech both in speaker similarity and word error rate (WER). Among these three methods, coupled methods leveraging LLMs as the text encoder can achieve the best performance, making it outperform original speech synthesis models with a consistently better speaker similarity and a significant (10.9%) WER reduction.

关键词： Error analysis Large language models Signal processing Boosting natural language processing Acoustics Text to speech

来源：评论

学校读者我要写书评

暂无评论

Cross-language Code Matching with IR2Vec and Cross-Entropy Loss 24

Cross-Language Code Matching with IR2Vec and Cross-Entropy L...

引用

8th International conference on natural language processing and Information Retrieval, NLPIR 2024

作者： Ghosh, Sagarika Das, Soma Chatterji, Sanjay Pratihar, Sanjoy CSE Indian Institute of Information Technology Kalyani West Bengal Kalyani India CSE University of Engineering and Management Jaipur Rajasthan Jaipur India CSE Institute of Engineering and Management Kolkata West Bengal Kolkata India

ISBN: (纸本)9798400717383

In contemporary software development and maintenance, the practice of reusing or copy-pasting code is prevalent to expedite processes. Consequently, numerous techniques have been developed to detect, compare, or match similar code within the same programming language. However, there remains a need for methods capable of detecting, comparing, or matching similar code across different programming languages. This paper presents a neural model utilizing IR2Vec embeddings and cross-entropy loss to facilitate the matching of similar code between disparate languages, such as C and C++. The proposed model achieves a matching accuracy of . To evaluate the model's efficacy, we compute Precision, Recall, and F1 score across various threshold values. © 2024 Copyright held by the owner/author(s).

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Text Complexity of Chinese University Writing Textbooks: Quantitative Analysis Based on Text Features 14

Text Complexity of Chinese University Writing Textbooks: Qua...

引用

14th International conference on Educational and Information Technology, ICEIT 2025

作者： Yang, Zhanji Li, Xiaohong School of Science and Technology Pu'er University Pu'er China School of Humanities Zhaotong University Zhaotong China

ISBN: (纸本)9798331540883

As higher education continues to place greater emphasis on students' writing skills, high-quality writing textbooks have become pivotal to the teaching process. This study employs a text complexity framework to examine the linguistic features of Chinese university writing textbooks, with the aim of evaluating their suitability for fostering students' writing abilities. Specifically, it investigates lexical diversity, syntactic complexity, and readability, providing a theoretical foundation for future textbook improvements and pedagogical optimization. By employing natural language processing (NLP) tools, the study extracts and quantitatively analyzes text features from widely used textbooks, focusing on vocabulary diversity, sentence length, and readability metrics. Statistical methods are then utilized to visualize and compare the data, thereby assessing the alignment between textbook language characteristics and instructional requirements. The findings reveal notable issues in the linguistic features of Chinese writing textbooks, particularly regarding syntactic complexity and readability. Some textbooks exhibit overly nested sentence structures that pose substantial challenges for novice learners. Moreover, the readability indices vary significantly among different textbooks, suggesting that certain language designs do not fully consider the diverse writing foundations and receptive abilities of various student populations. © 2025 IEEE.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Mitigating Shortcut Learning via Smart Data Augmentation based on Large language Model 31

Mitigating Shortcut Learning via Smart Data Augmentation bas...

引用

31st International conference on Computational Linguistics, COLING 2025

作者： Sun, Xinyi Tan, Hongye Guo, Yaxin Qiang, Pengpeng Li, Ru Zhang, Hu School of Computer and Information Technology Shanxi University Taiyuan China Institute of Intelligent Information Processing Shanxi University Taiyuan China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan China

ISBN: (纸本)9798891761964

Data-driven pre-trained language models typically perform shortcut learning wherein they rely on the spurious correlations between the data and the ground truth. This reliance can undermine the robustness and generalization of the model. To address this issue, data augmentation emerges as a promising solution. By integrating anti-shortcut data to the training set, the models' shortcut-induced biases can be mitigated. However, existing methods encounter three challenges: (1) Manual definition of shortcuts is tailored to particular datasets, restricting generalization. (2) The inherent confirmation bias during model training hampers the effectiveness of data augmentation. (3) Insufficient exploration of the relationship between the model performance and the augmented data quantity may result in excessive data consumption. To tackle these challenges, we propose a method of Smart Data Augmentation based on Large language Models (SAug-LLM). It leverages the LLMs to autonomously identify shortcuts and generate their anti-shortcut counterparts. In addition, the dual validation is employed to mitigate the confirmation bias during the model retraining. Furthermore, the data augmentation process is optimized to effectively rectify model biases while minimizing data consumption. We validate the effectiveness and generalization of our method through extensive experiments across various natural language processing tasks, demonstrating an average performance improvement of 5.61%. © 2025 Association for Computational Linguistics.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Systematic Review of Fine-tuning Approaches for Large language Models in the Context of Sinhala 5

Systematic Review of Fine-tuning Approaches for Large Langua...

引用

5th International conference on Advanced Research in Computing, ICARC 2025

作者： Hansaka, Sachin Sumanathilaka, Deshan Informatics Institute of Technology School of Computing Colombo006 Sri Lanka

ISBN: (纸本)9798331530983

The rapid development of large language models (LLMs) such as GPT-3, GPT-4, LlaMA, and mBERT has significantly advanced the natural language processing (NLP) field across many widely spoken languages. However, the effectiveness of these LLMs on low-resource languages such as Sinhala remained unexplored. With the scarcity of high-quality data and linguistic resources, fine-tuning LLMs in Sinhala has gained significant challenges. With a focus on Sinhala specifically, this systematic review addresses the methodologies and outcomes of adapting large language models for underrepresented languages. The purpose of this review is to synthesize existing research, identify effective strategies, contributions, and improvements, and highlight the challenges and opportunities in this domain. By analyzing various approaches, including data augmentation, transfer learning, cross-lingual transfer, parameter-efficient fine-tuning, adapter tuning, and model adaptation likewise, this review provides a comprehensive and precise idea of the current state of LLM fine-tuning on low-resource languages like Sinhala. The results highlight the importance of using creative methods and collaboration to improve LLM performance and usefulness in linguistic environments with limited resources. © 2025 IEEE.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Emotional Knowledge Self-Distillation in Dialogue

Emotional Knowledge Self-Distillation in Dialogue

引用

2025 IEEE International conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Jian, Zhongquan Wang, Yancheng Wu, Weichao Yao, Junfeng Wang, Meihong Wu, Qingqiang School of Informatics Xiamen University Xiamen China School of Film Xiamen University Xiamen China School of Computing and Data Science Xiamen University Malaysia Selangor Malaysia School of Mechanics and Civil Engineering China University of Mining & Technology Beijing China Xiamen Key Laboratory of Intelligent Storage and Computing School of Informatics Xiamen University Xiamen China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen China

ISBN: (纸本)9798350368741

Recognizing emotions in dialogues is vital for effective human-computer interaction, yet remains a challenging task in natural language processing (NLP). Previous studies in Emotion Recognition in Conversation (ERC) have primarily focused on contextual features, while overlooking the importance of emotional features in emotion recognition. To address this gap, we focus on the role of emotional features in ERC and propose a novel method, Emotional Knowledge Self-Distillation (EmoKSD1), to enhance the model's emotional sensitivity. In EmoKSD, utterances are enriched with implicit 〈mask〉 tokens to represent conveyed emotions, allowing the distillation of emotional knowledge from explicit emotional tokens to implicit 〈mask〉 tokens, thereby enhancing the model's ability to perceive subtle emotions within the dialogue. Through thorough evaluations on two public ERC datasets (i.e., IEMOCAP and MELD) using proposed coarse-grained utterance distillation and fine-grained token distillation techniques, EmoKSD demonstrates superior performance compared to existing methods, highlighting the significance of emotional features in ERC. © 2025 IEEE.

关键词： Dialogue System Emotion Recognition in Conversation Knowledge Distillation natural language processing

来源：评论

学校读者我要写书评

暂无评论

A Framework for Effective Invocation methods of Various LLM Services 31

A Framework for Effective Invocation Methods of Various LLM ...

引用

31st International conference on Computational Linguistics, COLING 2025

作者： Wang, Can Sui, Dianbo Zhang, Bolin Liu, Xiaoyu Kang, Jiabao Qiao, Zhidong Tu, Zhiying Shandong Weihai China

ISBN: (纸本)9798891761964

Large language Models (LLMs) have shown impressive abilities in solving various natural language processing tasks and are now widely offered as services. LLM services enable users to accomplish tasks without requiring specialized knowledge, simply by paying service providers. However, numerous providers offer various LLM services with variations in pricing, latency, and performance. These factors are also affected by different invocation methods, such as the choice of context and the use of cache, which lead to unpredictable and uncontrollable service cost and quality. Consequently, utilizing various LLM services invocation methods to construct an effective (cost-saving, low-latency and high-performance) invocation strategy that best meets task demands becomes a pressing challenge. This paper provides a comprehensive overview of methods help LLM services to be invoked efficiently. Technically, we define the problem of constructing an effective LLM services invocation strategy, and based on this, propose a unified LLM service invocation framework. The framework classifies existing methods into four categories: input abstraction, semantic cache, solution design, and output enhancement, which can be used separately or jointly during the invocation life cycle. We discuss the methods in each category and compare them to provide valuable guidance for researchers. Finally, we emphasize the open challenges in this domain and shed light on future research. © 2025 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

SSCM: Self-Supervised Critical Model for Reducing Hallucinations in Chinese Financial Text Generation

SSCM: Self-Supervised Critical Model for Reducing Hallucinat...

引用

2025 IEEE International conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Jin, Keyan Wang, Yapeng Santos, Leonel Fang, Tao Yang, Xu Im, Sio Kei Faculty of Applied Sciences Macao Polytechnic University China Computer Science and Communication Research Centre Polytechnic of Leiria Leiria Portugal Hithink RoyalFlush Information Network Co. Ltd. Hangzhou China Macao Polytechnic University China

ISBN: (纸本)9798350368741

Large language Models (LLMs) show strong performance in natural language processing tasks, but their application in the financial domain is limited. Current methods rely on large datasets and manual prompt engineering, resulting in high data demands, long inference times, and frequent hallucinations. To address these limitations, we propose a novel self-supervised prompt optimization framework tailored for the financial domain. Our approach involves training a critical model that evaluates and ranks generated outputs using both good and bad answers generated from various revised prompts. Experiments on a large Chinese financial corpus show that our framework significantly improves performance on tasks such as summarization and event-based question answering, as evidenced by higher scores on both automated metrics like ROUGE, BLEU, and BERTScore, and also through human evaluations. These results validate the effectiveness of our method in reducing hallucinations and improving the quality of financial text generation. © 2025 IEEE.

关键词： Critical Model Financial Applications Hallucination Large language Models (LLMs)

来源：评论

学校读者我要写书评

暂无评论

Interpreting Face Recognition Templates Using natural language Descriptions

Interpreting Face Recognition Templates Using Natural Langua...

引用

2025 IEEE/CVF Winter conference on Applications of Computer Vision Workshops, WACVW 2025

作者： Manojlovska, Anastasija Ramachandra, Raghavendra Spathoulas, Georgios Struc, Vitomir Grm, Klemen University of Ljubljana Ljubljana1000 Slovenia Ntnu Gjøvik Norway

ISBN: (纸本)9798331536626

Explainable artificial intelligence (XAI) aims to ensure an AI system's decisions are transparent and understandable by humans, which is particularly important in potentially sensitive application scenarios in surveillance, security and law enforcement. In these and related areas, understanding the internal mechanisms governing the decision-making process of AI-based systems can increase trust and consequently user acceptance. While various methods have been developed to provide insights into the behavior of AI-based models, solutions capable of explaining different aspects of the models using natural language are still limited in the literature. In this paper, we therefore propose a novel approach for interpreting the information content encoded in face templates, produced by state-of-the-art (SOTA) face recognition models. Specifically, we utilize the Text Encoder from the Contrastive language-Image Pretraining (CLIP) model and generate natural language descriptions of various face attributes present in the face templates. We implement two versions of our approach, with the off-the-shelf CLIP text-encoder and a fine-tuned version using the VGGFace2 and MAADFace datasets. Our experimental results indicate that the fine-tuned text encoder under the contrastive training paradigm increases the attribute-based explainability of face recognition templates, while both models provide valuable human-understandable insights into modern face recognition models. © 2025 IEEE.

关键词： natural language processing systems

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 << < 15 16 17 18 19 20 21 22 23 24 > >>

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：