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

30 篇 会议
1 册 图书

馆藏范围

31 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

29 篇 工学
- 29 篇 计算机科学与技术...
- 6 篇 软件工程
- 3 篇 信息与通信工程
- 2 篇 化学工程与技术
- 1 篇 农业工程
- 1 篇 生物医学工程（可授...
- 1 篇 生物工程
6 篇 文学
- 6 篇 外国语言文学
3 篇 理学
- 2 篇 化学
- 1 篇 数学
- 1 篇 生物学
1 篇 农学
- 1 篇 作物学
1 篇 管理学
- 1 篇 图书情报与档案管...

主题

3 篇 statistical mach...
2 篇 convolution
2 篇 entity linking
2 篇 ontology
1 篇 spoken dialogue ...
1 篇 distributional s...
1 篇 semantic resourc...
1 篇 long distance de...
1 篇 machine translat...
1 篇 chinese named en...
1 篇 pretrained langu...
1 篇 natural language...
1 篇 natural annotati...
1 篇 distillation
1 篇 role-based rule ...
1 篇 density peak
1 篇 contextual varia...
1 篇 markov logic net...
1 篇 domain-adaptive ...
1 篇 multi-task

机构

3 篇 chinese acad sci...
2 篇 peking univ inst...
2 篇 chinese acad sci...
1 篇 no.24 south sect...
1 篇 school of comput...
1 篇 nanjing universi...
1 篇 key laboratory o...
1 篇 chinese acad sci...
1 篇 ai speech co ltd...
1 篇 soochow univ nlp...
1 篇 tencent peoples ...
1 篇 hunan univ coll ...
1 篇 univ chinese aca...
1 篇 blcu int r&d ctr...
1 篇 beijing jiaotong...
1 篇 harbin inst tech...
1 篇 univ texas dalla...
1 篇 chinese acad sci...
1 篇 bosondata inc pe...
1 篇 southeast univ s...

作者

3 篇 xu bo
3 篇 lu shixiang
2 篇 qun liu
2 篇 liu qun
2 篇 zhang jiajun
2 篇 fan lichun
2 篇 yu dong
2 篇 wei wei
2 篇 fu xiaoyin
1 篇 zhao tianmei
1 篇 duan yitao
1 篇 li shutao
1 篇 zhou guodong
1 篇 lin shouxun
1 篇 ma chenggang
1 篇 ming zhou
1 篇 longhua qian
1 篇 zhou mingqi
1 篇 yang yifan
1 篇 peng xingyuan

语言

31 篇 英文

检索条件"任意字段=1st CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2012"

共 31 条记录，以下是1-10 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：

Overview of the nlpcc 2022 Shared Task: Dialogue Text Analysis (DTA) 11th

Overview of the NLPCC 2022 Shared Task: Dialogue Text Analys...

引用

11th ccf International conference on natural language processing and chinese computing (nlpcc)

作者： Miao, Qingliang Guan, Tao Yang, Yifan Zhang, Yifan Xu, Hua Ge, Fujiang AI Speech Co Ltd Bldg 14Tengfei Sci & Technol Pk388 Xinping St Suzhou Jiangsu Peoples R China

ISBN: (纸本)9783031171895;9783031171888

In this paper, we present an overview of the nlpcc 2022 shared task on Dialogue Texts Analysis (DTA). The evaluation consists of two sub-tasks: (1) Dialogue Topic Extraction (DTE) and (2) Dialogue Summary Generation (DSG). We manually annotated a large-scale corpus for DTA, in which each dialogue contains customer and service conversation. A total of 50 + teams participated in the DTA evaluation task. We believe that DTA will push forward the research in the field of dialogue text analysis.

关键词： Dialogue topic extraction Dialogue summary generation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Entity Linking with Contextualized Entity Embeddings 11th

Enhancing Entity Linking with Contextualized Entity Embeddin...

引用

11th ccf International conference on natural language processing and chinese computing (nlpcc)

作者： Xu, Zhenran Chen, Yulin Shi, Senbao Hu, Baotian Harbin Inst Technol Sch Comp Sci & Technol Shenzhen Peoples R China

ISBN: (纸本)9783031171895;9783031171888

Entity linking (EL) in written language domains has been extensively studied, but EL of spoken language is still unexplored. We propose a conceptually simple and highly effective two-stage approach to tackle this issue. The first stage retrieves candidates with a dual encoder, which independently encodes mention context and entity descriptions. Each candidate is then reranked by a LUKE-based cross-encoder, which concatenates the mention and entity description. Different from previous cross-encoder which takes only words as input, our model adds entities into input. Experiments demonstrate that our model does not need large-scale training on Wikipedia corpus, and outperforms all previous models with or without Wikipedia training. Our approach ranks the 1st in nlpcc 2022 Shared Task on Speech EL Track 2 (Entity Disambiguation-Only).

关键词： Entity linking Entity retrieval Pretrained language model

来源：评论

学校读者我要写书评

暂无评论

DAMO-NLP at nlpcc-2022 Task 2: Knowledge Enhanced Robust NER for Speech Entity Linking 11th

DAMO-NLP at NLPCC-2022 Task 2: Knowledge Enhanced Robust NER...

引用

11th ccf International conference on natural language processing and chinese computing (nlpcc)

作者： Huang, Shen Zhai, Yuchen Long, Xinwei Jiang, Yong Wang, Xiaobin Zhang, Yin Xie, Pengjun Alibaba Grp DAMO Acad Hangzhou Peoples R China Zhejiang Univ DCD Lab DMAC Grp Hangzhou Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9783031171895;9783031171888

Speech Entity Linking aims to recognize and disambiguate named entities in spoken languages. Conventional methods suffer gravely from the unfettered speech styles and the noisy transcripts generated by ASR systems. In this paper, we propose a novel approach called Knowledge Enhanced Named Entity Recognition (KENER), which focuses on improving robustness through painlessly incorporating proper knowledge in the entity recognition stage and thus improving the overall performance of entity linking. KENER first retrieves candidate entities for a sentence without mentions, and then utilizes the entity descriptions as extra information to help recognize mentions. The candidate entities retrieved by a dense retrieval module are especially useful when the input is short or noisy. Moreover, we investigate various data sampling strategies and design effective loss functions, in order to improve the quality of retrieved entities in both recognition and disambiguation stages. Lastly, a linking with filtering module is applied as the final safeguard, making it possible to filter out wrongly-recognized mentions. Our system achieves 1st place in Track 1 and 2nd place in Track 2 of nlpcc-2022 Shared Task 2.

关键词： Entity linking Robust NER

来源：评论

学校读者我要写书评

暂无评论

Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation 11th

Scene-Aware Prompt for Multi-modal Dialogue Understanding an...

引用

11th ccf International conference on natural language processing and chinese computing (nlpcc)

作者： Li, Bin Weng, Yixuan Ma, Ziyu Sun, Bin Li, Shutao Hunan Univ Coll Elect & Informat Engn Changsha Peoples R China Chinese Acad Sci Natl Lab Pattern Recognit Inst Automat Beijing Peoples R China

ISBN: (纸本)9783031171895;9783031171888

This paper introduces the schemes of Team LingJing's experiments in nlpcc-2022-Shared-Task-4 Multi-modal Dialogue Understanding and Generation (MDUG). The MDUG task can be divided into two phases: multi-modal context understanding and response generation. To fully leverage the visual information for both scene understanding and dialogue generation, we propose the scene-aware prompt for the MDUG task. Specifically, we utilize the multi-tasking strategy for jointly modelling the scene- and session- multi-modal understanding. The visual captions are adopted to aware the scene information, while the fixed-type templated prompt based on the scene- and session-aware labels are used to further improve the dialogue generation performance. Extensive experimental results show that the proposed method has achieved state-of-the-art (SOTA) performance compared with other competitive methods, where we rank the 1-st in all three subtasks in this MDUG competition.

关键词： Multi-modal dialogue understanding and generation Multi-task Scene-aware prompt

来源：评论

学校读者我要写书评

暂无评论

ACE: A Context-Enhanced Model for Interactive Argument Pair Identification 10th

ACE: A Context-Enhanced Model for Interactive Argument Pair ...

引用

10th ccf conference on natural language processing and chinese computing, nlpcc 2021

作者： Wu, Yi Liu, Pengyuan School of Information Science Beijing Language and Culture University Beijing China Beijing China

ISBN: (纸本)9783030884826

In recent years, Interactive Argument Pair Identification has attracted widespread attention as an important task in argument mining. Existing methods for the task usually explicitly model the matching score between the argument pairs. However, identifying whether two arguments have an interactive relationship not only depends on the argument itself, but also usually requires its context to better grasp the views expressed by the two arguments. In the nlpcc-2021 shared task Argumentative Text Understanding for AI Debater, we participated in track 2 Interactive Argument Pair Identification in Online Forum and proposed ACE, A Context-Enhanced model which makes good use of the context information of the argument. In the end, we ranked 1st in this task, indicating the effectiveness of our model. © 2021, Springer Nature Switzerland AG.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Fantastic Gradients and Where to Find Them: Improving Multi-attribute Text style Transfer by Quadratic Program 12th

Fantastic Gradients and Where to Find Them: Improving Mult...

引用

12th National ccf conference on natural language processing and chinese computing, nlpcc 2023

作者： Qu, Qian Wang, Jian Yang, Kexin Zhang, Hang Lv, Jiancheng No.24 South Section of 1st Ring Road Chengdu China

ISBN: (纸本)9783031446986

Unsupervised text style transfer (Tst) is an important task with extensive implications in natural language generation (NLG). A prevalent approach involves editing the latent representations of text, guided by gradients from an attribute classifier. However, in multi-attribute Tst, the simultaneous satisfaction of all required attributes remains challenging. In this paper, we unveil that the gradient direction during editing might conflict with certain attribute representations through empirical analysis. To tackle this problem, we introduce a mathematical programming method to impose constraints on the editing direction of multiple attributes, effectively mitigating potential attribute conflicts during the inference stage. Our proposed method considers the potential conflict between different attributes for the first time. Experimental results from the YELP benchmark showcase that our method can effectively improve the multi-attribute-transfer accuracy and quality without compromising single attribute performance. Moreover, our method can be readily integrated with pre-trained auto-encoders, providing an effective and scalable solution for multi-attribute scenarios. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

The Solution of Huawei Cloud & Noahs Ark Lab to the nlpcc-2020 Challenge: Light Pre-Training chinese language Model for NLP Task 9th

The Solution of Huawei Cloud & Noahs Ark Lab to the NLPCC-20...

引用

9th ccf International conference on natural language processing and chinese computing, nlpcc 2020

作者： Zhang, Yuyang Yu, Jintao Wang, Kai Yin, Yichun Chen, Cheng Liu, Qun Huawei Noahs Ark Lab Beijing China Huawei Cloud and AI Shenzhen China

ISBN: (纸本)9783030604561

Pre-trained language models have achieved great success in natural language processing. However, they are difficult to be deployed on resource-restricted devices because of the expensive computation. This paper introduces our solution to the natural language processing and chinese computing (nlpcc) challenge of Light Pre-Training chinese language Model for the natural language processing (http://***/conference/2020/) (https://***/***). The proposed solution uses a state-of-the-art method of BERT knowledge distillation (TinyBERT) with an advanced chinese pre-trained language model (NEZHA) as the teacher model, which is dubbed as TinyNEZHA. In addition, we introduce some effective techniques in the fine-tuning stage to boost the performances of TinyNEZHA. In the official evaluation of nlpcc-2020 challenge, TinyNEZHA achieves a score of 77.71, ranking 1st place among all the participating teams. Compared with the BERT-base, TinyNEZHA obtains almost the same results while being 9 smaller and 8 faster on inference. © 2020, Springer Nature Switzerland AG.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Sign language Recognition with Attention-Enhanced Graph Convolutional Networks 10th

Skeleton-Based Sign Language Recognition with Attention-Enha...

引用

10th ccf conference on natural language processing and chinese computing, nlpcc 2021

作者： Liang, Wuyan Xu, Xiaolong Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China School of Computer and Science Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China

ISBN: (纸本)9783030884796

The natural language processing of sign language is an important task in the field of artificial intelligence and information processing. In this paper, we propose an attention-enhanced graph convolutional networks (AEGCNs) for sign language recognition (SLR). First, there are four kinds of adaptive graphs for graph convolution and each graph topology can be either uniformly or individually learned based on the skeleton data in an end-to-end manner. In addition, we employ the spatial-temporal-channel attention mechanisms to give higher weight to the relative important joints, frames and features, and the higher-order connection with Chebychev polynomial approximation to enlarge the receptive field of graph convolution. Meanwhile, the information of both the joints and bones is simultaneously modeled in a framework, which further improves the representation of the movement about hand and finger. Finally, experiments on the DEVISIGN-D, DSL50 and ASL20 datasets show that the accuracies for top1 of three datasets reach 82.96%, 95.09% and 90.23% respectively and the accuracies for top5 of three datasets achieve 96.07%, 99.18% and 100% respectively. Compared with st-GCN and BHOF, the accuracy of AEGCNs obtains significant improvements of +33.5% and +5.32% on ASL20 datasets, respectively, which demonstrates the effectiveness of our method on SLR. © 2021, Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Youdao's Winning Solution to the nlpcc-2018 Task 2 Challenge: A Neural Machine Translation Approach to chinese Grammatical Error Correction 7th

Youdao's Winning Solution to the NLPCC-2018 Task 2 Challenge...

引用

7th ccf International conference on natural language processing and chinese computing, nlpcc

作者： Fu, Kai Huang, Jin Duan, Yitao NetEase Youdao Informat Technol Beijing Co LTD Beijing Peoples R China

ISBN: (纸本)9783319994956;9783319994949

The nlpcc 2018 chinese Grammatical Error Correction (CGEC) shared task seeks the best solution to detecting and correcting grammatical errors in chinese essays written by non-native chinese speakers. This paper describes Youdao NLP team's approach to this challenge, which won the 1st place in the contest. Overall, we cast the problem as a machine translation task. We use a staged approach and design specific modules targeting at particular errors, including spelling, grammatical, etc. The task uses M-2 Scorer [5] to evaluate every system's performance, and our final solution achieves the highest recall and F-0.5.

关键词： Grammatical error correction Machine translation

来源：评论

学校读者我要写书评

暂无评论

A Novel Community Detection Method Based on Cluster Density Peaks 6th

A Novel Community Detection Method Based on Cluster Density ...

引用

6th ccf International conference on natural language processing and chinese computing (nlpcc)

作者： Liu, Donglei Su, Yipeng Li, Xudong Niu, Zhendong Beijing Inst Technol Sch Comupter Sci 5 South Zhongguancun St Beijing Peoples R China

ISBN: (纸本)9783319736181;9783319736174

Community structure is the basic structure of a social network. Nodes of a social network can naturally form communities. More specifically, nodes are densely connected with each other within the same community while sparsely between different communities. Community detection is an important task in understanding the features of networks and graph analysis. At present there exist many community detection methods which aim to reveal the latent community structure of a social network, such as graph-based methods and heuristic-information-based methods. However, the approaches based on graph theory are complex and with high computing expensive. In this paper, we extend the density concept and propose a density peaks based community detection method. This method firstly computes two metrics-the local density p and minimum climb distance delta-for each node in a network, then identify the nodes with both higher rho and delta in local fields as each community center. Finally, rest nodes are assigned with corresponding community labels. The complete process of this method is simple but efficient. We test our approach on four classic baseline datasets. Experimental results demonstrate that the proposed method based on density peaks is more accurate and with low computational complexity.

关键词： Social network Community detection Density peak

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4页 << < 1 2 3 4 > >>

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：