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

11 篇 会议

馆藏范围

11 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

10 篇 工学
- 10 篇 计算机科学与技术...
- 9 篇 软件工程
- 2 篇 信息与通信工程
- 1 篇 控制科学与工程
- 1 篇 化学工程与技术
3 篇 理学
- 1 篇 数学
- 1 篇 化学
- 1 篇 生物学
3 篇 管理学
- 3 篇 图书情报与档案管...
1 篇 医学
- 1 篇 基础医学(可授医学...

主题

3 篇 embeddings
2 篇 recurrent neural...
1 篇 semantics
1 篇 natural language...
1 篇 forecasting
1 篇 supervised learn...

机构

1 篇 fuji xerox co. l...
1 篇 limsi-cnrs / ors...
1 篇 semantic computi...
1 篇 department of co...
1 篇 university of go...
1 篇 chalmers univers...
1 篇 lmu munich
1 篇 lipn paris xiii ...
1 篇 school of comput...
1 篇 facultad de cien...
1 篇 departamento de ...
1 篇 samsung electron...

作者

1 篇 oncevay-marcos a...
1 篇 allauzen alexand...
1 篇 johansson richar...
1 篇 miura yasuhide
1 篇 labeau matthieu
1 篇 shin youhyun
1 篇 brooke julian
1 篇 baldwin timothy
1 篇 cartier emmanuel
1 篇 ohkuma tomoko
1 篇 misawa shotaro
1 篇 kim jihie
1 篇 lee haejun
1 篇 alva carlo
1 篇 lejeune gael
1 篇 kulkarni nilesh
1 篇 nguyen viet
1 篇 cimiano philipp
1 篇 jebbara soufian
1 篇 lee sang-goo

语言

11 篇 英文

检索条件"任意字段=EMNLP 2017 1st Workshop on Subword and Character Level Models in NLP, SCLeM 2017"

共 11 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：

emnlp 2017 - 1st workshop on subword and character level models in nlp, sclem 2017 - Proceedings of the workshop

EMNLP 2017 - 1st Workshop on Subword and Character Level Mod...

引用

emnlp 2017 1st workshop on subword and character level models in nlp, sclem 2017

ISBN: (纸本)9781945626913

The proceedings contain 24 papers. The topics discussed include: character and subword-based word representation for neural language modeling prediction;character and subword-based word representation for neural language modeling prediction;character based pattern mining for neology detection;automated word stress detection in Russian;a syllable-based technique for word embeddings of Korean words;supersense tagging with a combination of character, subword, and word-level representations;weakly supervised learning of allomorphy;character-based recurrent neural networks for morphological relational reasoning;and character-based recurrent neural networks for morphological relational reasoning..

关键词：

来源：评论

学校读者我要写书评

暂无评论

Supersense tagging with a combination of character, subword, and word-level representations 1

Supersense tagging with a combination of character, subword,...

引用

emnlp 2017 1st workshop on subword and character level models in nlp, sclem 2017

作者： Shin, Youhyun Lee, Sang-Goo Department of Computer Science and Engineering Seoul National University Korea Republic of

ISBN: (纸本)9781945626913

Recently, there has been increased interest in utilizing characters or subwords for natural language processing (nlp) tasks. However, the effect of utilizing character, subword, and word-level information simultaneously has not been examined so far. In this paper, we propose a model to leverage various levels of input features to improve on the performance of an supersense tagging task. Detailed analysis of experimental results show that different levels of input representation offer distinct characteristics that explain performance discrepancy among different tasks. © emnlp *** right reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Sub-character neural language modelling in japanese 1

Sub-character neural language modelling in japanese

引用

emnlp 2017 1st workshop on subword and character level models in nlp, sclem 2017

作者： Nguyen, Viet Brooke, Julian Baldwin, Timothy School of Computing and Information Systems University of Melbourne Australia

ISBN: (纸本)9781945626913

In East Asian languages such as Japanese and Chinese, the semantics of a character are (somewhat) reflected in its sub-character elements. This paper examines the effect of using subcharacters for language modeling in Japanese. This is achieved by decomposing characters according to a range of character decomposition datasets, and training a neural language model over variously decomposed character representations. Our results indicate that language modelling can be improved through the inclusion of subcharacters, though this result depends on a good choice of decomposition dataset and the appropriate granularity of decomposition. © emnlp *** right reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Syllable-level neural language model for agglutinative language 1

Syllable-level neural language model for agglutinative langu...

引用

emnlp 2017 1st workshop on subword and character level models in nlp, sclem 2017

作者： Yu, Seunghak Kulkarni, Nilesh Lee, Haejun Kim, Jihie Samsung Electronics Co. Ltd. Korea Republic of

ISBN: (纸本)9781945626913

Language models for agglutinative languages have always been hindered in past due to myriad of agglutinations possible to any given word through various affixes. We propose a method to diminish the problem of out-of-vocabulary words by introducing an embedding derived from syllables and morphemes which leverages the agglutinative property. Our model outperforms character-level embedding in perplexity by 16.87 with 9.50M parameters. Proposed method achieves state of the art performance over existing input prediction methods in terms of Key stroke Saving and has been commercialized. © emnlp *** right reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

character based pattern mining for neology detection 1

Character based pattern mining for neology detection

引用

emnlp 2017 1st workshop on subword and character level models in nlp, sclem 2017

作者： Lejeune, Gael Cartier, Emmanuel Lipn Paris Xiii University 99 avenue Jean-Baptiste Clement Villetaneuse93430 France

ISBN: (纸本)9781945626913

Detecting neologisms is essential in real-time natural language processing applications. Not only can it enable to follow the lexical evolution of languages, but it is also essential for updating linguistic resources and parsers. In this paper, neology detection is considered as a classification task where a system has to assess whether a given lexical item is an actual neologism or not. We propose a combination of an unsupervised data mining technique and a supervised machine learning approach. It is inspired by current researches in stylometry and on tokenlevel and character-level patterns. We train and evaluate our system on a manually designed reference dataset in French and Russian. We show that this approach is able to outperform stateof- the-art neology detection systems. Furthermore, character-level patterns exhibit good properties for multilingual extensions of the system. © emnlp *** right reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Unlabeled data for morphological generationwith character-based sequence-to-sequence models 1

Unlabeled data for morphological generationwith character-ba...

引用

emnlp 2017 1st workshop on subword and character level models in nlp, sclem 2017

作者： Kann, Katharina Schutze, Hinrich Lmu Munich Germany

ISBN: (纸本)9781945626913

We present a semi-supervised way of training a character-based encoderdecoder recurrent neural network for morphological reinflection, the task of generating one inflected word form from another. This is achieved by using unlabeled tokens or random strings as training data for an autoencoding task, adapting a network for morphological reinflection, and performing multi-task training. We thus use limited labeled data more effectively, obtaining up to 9.9% improvement over state-of-the-art baselines for 8 different languages. © emnlp *** right reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

character and subword-based word representation for neural language modeling prediction 1

Character and subword-based word representation for neural l...

引用

emnlp 2017 1st workshop on subword and character level models in nlp, sclem 2017

作者： Labeau, Matthieu Allauzen, Alexandre LIMSI-CNRS / Orsay France

ISBN: (纸本)9781945626913

Most of neural language models use different kinds of embeddings for word prediction. While word embeddings can be associated to each word in the vocabulary or derived from characters as well as factored morphological decomposition, these word representations are mainly used to parametrize the input, i.e. the context of prediction. This work investigates the effect of using subword units (character and factored morphological decomposition) to build output representations for neural language modeling. We present a case study on Czech, a morphologically-rich language, experimenting with different input and output representations. When working with the full training vocabulary, despite unstable training, our experiments show that augmenting the output word representations with character-based embeddings can significantly improve the performance of the model. Moreover, reducing the size of the output look-up table, to let the character-based embeddings represent rare words, brings further improvement. © emnlp *** right reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Improving opinion-target extraction with character-level word embeddings 1

Improving opinion-target extraction with character-level wor...

引用

emnlp 2017 1st workshop on subword and character level models in nlp, sclem 2017

作者： Jebbara, Soufian Cimiano, Philipp Semantic Computing Group Bielefeld University Germany

ISBN: (纸本)9781945626913

Fine-grained sentiment analysis received increasing attention in recent years. Extracting opinion target expressions (OTE) in reviews is often an important step in fine-grained, aspect-based sentiment analysis. Retrieving this information from user-generated text, however, can be difficult. Customer reviews, for instance, are prone to contain misspelled words and are difficult to process due to their domainspecific language. In this work, we investigate whether character-level models can improve the performance for the identification of opinion target expressions. We integrate information about the character structure of a word into a sequence labeling system using character-level word embeddings and show their positive impact on the systems performance. Specifically, we obtain an increase by 3.3 points F1- score with respect to our baseline model. In further experiments, we reveal encoded character patterns of the learned embeddings and give a nuanced view of the performance differences of both models. © emnlp *** right reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

character-based bidirectional lstm-crf with words and characters for japanese named entity recognition 1

Character-based bidirectional lstm-crf with words and charac...

引用

emnlp 2017 1st workshop on subword and character level models in nlp, sclem 2017

作者： Misawa, Shotaro Taniguchi, Motoki Miura, Yasuhide Ohkuma, Tomoko Fuji Xerox Co. Ltd.

ISBN: (纸本)9781945626913

Recently, neural models have shown superior performance over conventional models in NER tasks. These models use CNN to extract sub-word information along with RNN to predict a tag for each word. However, these models have been tested almost entirely on English texts. It remains unclear whether they perform similarly in other languages. We worked on Japanese NER using neural models and discovered two obstacles of the state-ofthe- art model. First, CNN is unsuitable for extracting Japanese sub-word information. Secondly, a model predicting a tag for each word cannot extract an entity when a part of a word composes an entity. The contributions of this work are (i) verifying the effectiveness of the state-of-theart NER model for Japanese, (ii) proposing a neural model for predicting a tag for each character using word and character information. Experimentally obtained results demonstrate that our model outperforms the state-of-the-art neural English NER model in Japanese. © emnlp *** right reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Spell-checking based on syllabification and character-level graphs for a peruvian agglutinative language 1

Spell-checking based on syllabification and character-level ...

引用

emnlp 2017 1st workshop on subword and character level models in nlp, sclem 2017

作者： Alva, Carlo Oncevay-Marcos, Arturo Facultad de Ciencias e Ingenieria Pontificia Universidad Católica Del Perú Peru Departamento de Ingenieria Grpiaa Pontificia Universidad Católica Del Perú Peru

ISBN: (纸本)9781945626913

There are several native languages in Peru which are mostly agglutinative. These languages are transmitted from generation to generation mainly in oral form, causing different forms of writing across different communities. For this reason, there are recent efforts to standardize the spelling in the written texts, and it would be beneficial to support these tasks with an automatic tool such as a spell-checker. In this way, this spelling corrector is being developed based on two steps: An automatic rule-based syllabification method and a character-level graph to detect the degree of error in a misspelled word. The experiments were realized on Shipibo-konibo, a highly agglutinative and Amazonian language, and the results obtained have been promising in a dataset built for the purpose. © emnlp *** right reserved.

关键词：

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2页 << < 1 2 > >>

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：