检索结果-内蒙古大学图书馆

CitationAS： A Tool of Automatic Survey Generation Based on Citation Content

Journal of data and Information science 2018年第2期3卷 20-37页

作者： jie wang chengzhi zhang mengying zhang sanhong deng School of Information Management Nanjing University Nanjing 210023 China Department of Information Management Nanjing University of Science and Technology Nanjing 210094 China Jiangsu Key Laboratory of Data Engineering and Knowledge Service Nanjing University Nanjing 210023 China

Purpose： This study aims to build an automatic survey generation tool, named CitationAS, based on citation content as represented by the set of citing sentences in the original ***/methodology/approach： Firstly, we apply LDA to analyse topic distribution of citation content. Secondly, in CitationAS, we use bisecting K-means, Lingo and STC to cluster retrieved citation content. Then Word2Vec, Word Net and combination of them are applied to generate cluster labels. Next, we employ TF-IDF, MMR, as well as considering sentence location information, to extract important sentences, which are used to generate surveys. Finally, we adopt manual evaluation for the generated ***： In experiments, we choose 20 high-frequency phrases as search terms. Results show that Lingo-Word2Vec, STC-Word Net and bisecting K-means-Word2Vec have better clustering effects. In 5 points evaluation system, survey quality scores obtained by designing methods are close to 3, indicating surveys are within acceptable limits. When considering sentence location information, survey quality will be improved. Combination of Lingo, Word2Vec, TF-IDF or MMR can acquire higher survey *** limitations： The manual evaluation method may have a certain subjectivity. We use a simple linear function to combine Word2Vec and Word Net that may not bring out their strengths. The generated surveys may not contain some newly created knowledge of some articles which may concentrate on sentences with no *** implications： CitationAS tool can automatically generate a comprehensive, detailed and accurate survey according to user’s search terms. It can also help researchers learn about research status in a certain ***/value： Citaiton AS tool is of practicability. It merges cluster labels from semantic level to improve clustering results. The tool also considers sentence location information when calculating sentence score by TF-IDF and MMR.

关键词： Automatic survey system Citation content Clustering algorithms Labelgeneration approaches Sentence extraction methods

来源：评论

学校读者我要写书评

暂无评论

IRank: A term-based innovation ranking system for conferences and scholars

IRank: A term-based innovation ranking system for conference...

引用

Joint International Conference on Advances in data and Web Management, APWeb/WAIM 2009

作者： Li, Zhixu Du, Xiaoyong Liu, Hongyan He, Jun Zhou, Xiaofang Key Labs of Data Engineering and Knowledge Engineering Ministry of Education China School of Information Renmin University of China Beijing China Department of Management Science and Engineering Tsinghua University Beijing China University of Queensland QLD Australia

ISBN: (纸本)9783642006715

Since the proposition of Journal Impact Factor [1] in 1963, the classical citation-based ranking scheme has been a standard criterion to rank journals and conferences. However, the reference of a paper cannot list all relevant publications and the citation relationships are not always available especially when related to copyright problem. Besides, we cannot evaluate a newly published paper before it is cited by others. Therefore, we propose an alternative method, term-based evaluation scheme which can evaluate publications by terms they use. Then we can rank conferences, journals and scholars accordingly. We think this term-based ranking scheme can be used to evaluate innovation quality for conferences and scholars. To evaluate our scheme and to facilitate its application, we develop an innovation ranking system called IRank to rank conferences and authors in the field of database Systems. The performance of IRank demonstrates the effectiveness of our scheme. © Springer-Verlag Berlin Heidelberg 2009.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

A Retrieval-Based Dialogue System Utilizing Utterance and Context Embeddings

A Retrieval-Based Dialogue System Utilizing Utterance and Co...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Alexander Bartl Gerasimos Spanakis Department of Data Science and Knowledge Engineering Maastricht University MD Netherlands

Finding semantically rich and computer-understandable representations for textual dialogues, utterances and words is crucial for dialogue systems (or conversational agents), as their performance mostly depends on understanding the context of conversations. In recent research approaches, responses have been generated utilizing a decoder architecture, given the distributed vector representation (embedding) of the current conversation. In this paper, the utilization of embeddings for answer retrieval is explored by using Locality-Sensitive Hashing Forest (LSH Forest), an Approximate Nearest Neighbor (ANN) model, to find similar conversations in a corpus and rank possible candidates. Experimental results on the well-known Ubuntu Corpus (in English) and a customer service chat dataset (in Dutch) show that, in combination with a candidate selection method, retrieval-based approaches outperform generative ones and reveal promising future research directions towards the usability of such a system.

关键词： Decoding Logic gates Context modeling Encoding Pipelines Training databases

来源：评论

学校读者我要写书评

暂无评论

High-performance and lightweight real-time deep face emotion recognition

High-performance and lightweight real-time deep face emotion...

引用

International Workshop on Semantic Media Adaptation and Personalization (SMAP)

作者： Justus Schwan Esam Ghaleb Enrique Hortal Stylianos Asteriadis Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

ISBN: (纸本)9781538607572

Deep learning is used for all kinds of tasks which require human-like performance, such as voice and image recognition in smartphones, smart home technology, and self-driving cars. While great advances have been made in the field, results are often not satisfactory when compared to human performance. In the field of facial emotion recognition, especially in the wild, Convolutional Neural Networks (CNN) are employed because of their excellent generalization properties. However, while CNNs can learn a representation for certain object classes, an amount of (annotated) training data roughly proportional to the class's complexity is needed and seldom available. This work describes an advanced pre-processing algorithm for facial images and a transfer learning mechanism, two potential candidates for relaxing this requirement. Using these algorithms, a lightweight face emotion recognition application for Human-Computer Interaction with TurtleBot units was developed.

关键词： Face Training Feature extraction Real-time systems Emotion recognition Training data Face detection

来源：评论

学校读者我要写书评

暂无评论

LibriS2S: A German-English Speech-to-Speech Translation Corpus

arXiv

引用

arXiv 2022年

作者： Jeuris, Pedro Niehues, Jan Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

Recently, we have seen an increasing interest in the area of speech-to-text translation. This has led to astonishing improvements in this area. In contrast, the activities in the area of speech-to-speech translation is still limited, although it is essential to overcome the language barrier. We believe that one of the limiting factors is the availability of appropriate training data. We address this issue by creating LibriS2S, to our knowledge the first publicly available speech-to-speech training corpus between German and English. For this corpus, we used independently created audio for German and English leading to an unbiased pronunciation of the text in both languages. This allows the creation of a new text-to-speech and speech-to-speech translation model that directly learns to generate the speech signal based on the pronunciation of the source language. Using this created corpus, we propose Text-to-Speech models based on the example of the recently proposed FastSpeech 2 model that integrates source language information. We do this by adapting the model to take information such as the pitch, energy or transcript from the source speech as additional input. © 2022, CC BY-NC-SA.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

AA-TransUNet: Attention Augmented TransUNet For Nowcasting Tasks

arXiv

引用

arXiv 2022年

作者： Yang, Yimin Mehrkanoon, Siamak Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

data driven modeling based approaches have recently gained a lot of attention in many challenging meteorological applications including weather element forecasting. This paper introduces a novel data-driven predictive model based on TransUNet for precipitation nowcasting task. The TransUNet model which combines the Transformer and U-Net models has been previously successfully applied in medical segmentation tasks. Here, TransUNet is used as a core model and is further equipped with Convolutional Block Attention Modules (CBAM) and Depthwise-separable Convolution (DSC). The proposed Attention Augmented TransUNet (AA-TransUNet) model is evaluated on two distinct datasets: the Dutch precipitation map dataset and the French cloud cover dataset. The obtained results show that the proposed model outperforms other examined models on both tested datasets. Furthermore, the uncertainty analysis of the proposed AA-TransUNet is provided to give additional insights on its predictions. © 2022, CC BY-SA.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Improving zero-shot translation by disentangling positional information

arXiv

引用

arXiv 2020年

作者： Liu, Danni Niehues, Jan Cross, James Guzmán, Francisco Li, Xian Department of Data Science and Knowledge Engineering Maastricht University Facebook AI

Multilingual neural machine translation has shown the capability of directly translating between language pairs unseen in training, i.e. zero-shot translation. Despite being conceptually attractive, it often suffers from low output quality. The difficulty of generalizing to new translation directions suggests the model representations are highly specific to those language pairs seen in training. We demonstrate that a main factor causing the language-specific representations is the positional correspondence to input tokens. We show that this can be easily alleviated by removing residual connections in an encoder layer. With this modification, we gain up to 18.5 BLEU points on zero-shot translation while retaining quality on supervised directions. The improvements are particularly prominent between related languages, where our proposed model outperforms pivot-based translation. Moreover, our approach allows easy integration of new languages, which substantially expands translation coverage. By thorough inspections of the hidden layer outputs, we show that our approach indeed leads to more language-independent representations.1 Copyright © 2020, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Manipulating the Distributions of Experience used for Self-Play Learning in Expert Iteration

arXiv

引用

arXiv 2020年

作者： Soemers, Dennis J.N.J. Piette, Éric Stephenson, Matthew Browne, Cameron Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

—Expert Iteration (ExIt) is an effective framework for learning game-playing policies from self-play. ExIt involves training a policy to mimic the search behaviour of a tree search algorithm - such as Monte-Carlo tree search - and using the trained policy to guide it. The policy and the tree search can then iteratively improve each other, through experience gathered in self-play between instances of the guided tree search algorithm. This paper outlines three different approaches for manipulating the distribution of data collected from self-play, and the procedure that samples batches for learning updates from the collected data. Firstly, samples in batches are weighted based on the durations of the episodes in which they were originally experienced. Secondly, Prioritized Experience Replay is applied within the ExIt framework, to prioritise sampling experience from which we expect to obtain valuable training signals. Thirdly, a trained exploratory policy is used to diversify the trajectories experienced in self-play. This paper summarises the effects of these manipulations on training performance evaluated in fourteen different board games. We find major improvements in early training performance in some games, and minor improvements averaged over fourteen games. Copyright © 2020, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

‘Thy algorithm shalt not bear false witness’: An Evaluation of Multiclass Debiasing Methods on Word Embeddings

arXiv

引用

arXiv 2020年

作者： Schlender, Thalea Spanakis, Gerasimos Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

With the vast development and employment of artificial intelligence applications, research into the fairness of these algorithms has been increased. Specifically, in the natural language processing domain, it has been shown that social biases persist in word embeddings and are thus in danger of amplifying these biases when used. As an example of social bias, religious biases are shown to persist in word embeddings and the need for its removal is highlighted. This paper investigates the state-of-the-art multiclass debiasing techniques: Hard debiasing, SoftWEAT debiasing and Conceptor debiasing. It evaluates their performance when removing religious bias on a common basis by quantifying bias removal via the Word Embedding Association Test (WEAT), Mean Average Cosine Similarity (MAC) and the Relative Negative Sentiment Bias (RNSB). By investigating the religious bias removal on three widely used word embeddings, namely: Word2Vec, GloVe, and ConceptNet, it is shown that the preferred method is ConceptorDebiasing. Specifically, this technique manages to decrease the measured religious bias on average by 82,42%, 96,78% and 54,76% for the three word embedding sets respectively. Copyright © 2020, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Biasing MCTS with features for general games

arXiv

引用

arXiv 2019年

作者： Soemers, Dennis J.N.J. Piette, Éric Browne, Cameron Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

This paper proposes using a linear function approximator, rather than a deep neural network (DNN), to bias a Monte Carlo tree search (MCTS) player for general games. This is unlikely to match the potential raw playing strength of DNNs, but has advantages in terms of generality, interpretability and resources (time and hardware) required for training. Features describing local patterns are used as inputs. The features are formulated in such a way that they are easily interpretable and applicable to a wide range of general games, and might encode simple local strategies. We gradually create new features during the same self-play training process used to learn feature weights. We evaluate the playing strength of an MCTS player biased by learnt features against a standard upper confidence bounds for trees (UCT) player in multiple different board games, and demonstrate significantly improved playing strength in the majority of them after a small number of self-play training games. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：