检索结果-内蒙古大学图书馆

Media Watermarking, Security, and Forensics 2016

作者： Schäfer, Marcel Berchtold, Waldemar Stark, Teetje Reimers, Nils Steinebach, Martin Fraunhofer-Institute SIT Darmstadt Germany Department of Mathematics and Computer Science Freie Universität Berlin Berlin Germany Ubiquitous Knowledge Processing Lab - Department of Computer Science Technische Universitat Darmstadt Darmstadt Germany

Probabilistic or bias-based fingerprinting codes to counter collusion attacks are applied to enhance the security of transaction watermarking applications. Into every media copy to be distributed is embedded a unique fingerprint via watermarking techniques. With it a distributor is able to trace back unauthorized redistributed versions to its source with a high probability even if the media was subject to a collusion attack. The seminal Tardos fingerprinting codes and all its derivatives rely on position independent fingerprints. Hence in most work it is assumed that the attackers also rely on the position independence when creating the media forgery containing a manipulated fingerprint. However, they need not follow this assumption. In this work we present a novel iterative attack model that does not rely on the position independence but could be applied in practice. The corresponding attacks iteratively adapt the manipulated fingerprint with the intention to maximally reduce their accusation scores in order to escape the accusation. For practical collusion sizes, the attacks show better performance than other attacks typically discussed in literature. In other words, the attacks result in manipulated fingerprints that lead to higher error rates of the fingerprinting scheme, compared to the attacks discussed in literature. © 2016 Society for Imaging science and Technology.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Multi-task learning for argumentation mining

arXiv

引用

arXiv 2019年

作者： Eger, Steffen Gurevych, Iryna Computer Science Department Ubiquitous Knowledge Processing

Multi-task learning has recently become a very active field in deep learning research. In contrast to learning a single task in isolation, multiple tasks are learned at the same time, thereby utilizing the training signal of related tasks to improve the performance on the respective machine learning tasks. Related work shows various successes in different domains when applying this paradigm and this thesis extends the existing empirical results by evaluating multi-task learning in four different scenarios: argumentation mining, epistemic segmentation, argumentation component segmentation, and grapheme-to-phoneme conversion. We show that multi-task learning can, indeed, improve the performance compared to single-task learning in all these scenarios, but may also hurt the performance. Therefore, we investigate the reasons for successful and less successful applications of this paradigm and find that dataset properties such as entropy or the size of the label inventory are good indicators for a potential multi-task learning success and that multi-task learning is particularly useful if the task at hand suffers from data sparsity, i.e. a lack of training data. Moreover, multi-task learning is particularly effective for long input sequences in our experiments. We have observed this trend in all evaluated scenarios. Finally, we develop a highly configurable and extensible sequence tagging framework which supports multi-task learning to conduct our empirical experiments and to aid future research regarding the multitask learning paradigm and natural language processing. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Diversity Over Size: On the Effect of Sample and Topic Sizes for Topic-Dependent Argument Mining Datasets

Diversity Over Size: On the Effect of Sample and Topic Sizes...

引用

2024 Conference on Empirical Methods in Natural Language processing, EMNLP 2024

作者： Schiller, Benjamin Daxenberger, Johannes Waldis, Andreas Gurevych, Iryna summetix GmbH Germany Ubiquitous Knowledge Processing Lab Department of Computer Science Technical University of Darmstadt Germany Information Systems Research Lab Lucerne University of Applied Sciences and Arts Switzerland

ISBN: (纸本)9798891761643

Topic-Dependent Argument Mining (TDAM), that is extracting and classifying argument components for a specific topic from large document sources, is an inherently difficult task for machine learning models and humans alike, as large TDAM datasets are rare and recognition of argument components requires expert knowledge. The task becomes even more difficult if it also involves stance detection of retrieved arguments. In this work, we investigate the effect of TDAM dataset composition in few- and zero-shot settings. Our findings show that, while fine-tuning is mandatory to achieve acceptable model performance, using carefully composed training samples and reducing the training sample size by up to almost 90% can still yield 95% of the maximum performance. This gain is consistent across three TDAM tasks on three different datasets. We also publish a new dataset and code for future benchmarking. © 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

Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model

Controllable Factuality in Document-Grounded Dialog Systems ...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Daheim, Nico Thulke, David Dugast, Christian Ney, Hermann Ubiquitous Knowledge Processing Lab Department of Computer Science Technical University of Darmstadt Germany Human Language Technology and Pattern Recognition RWTH Aachen University Germany AppTek GmbH

In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes' theorem. One component is a traditional ungrounded response generation model and the other component models the reconstruction of the grounding document based on the dialog context and generated response. We propose different approximate decoding schemes and evaluate our approach on multiple open-domain and task-oriented document-grounded dialog datasets. Our experiments show that the model is more factual in terms of automatic factuality metrics than the baseline model. Furthermore, we outline how introducing scaling factors between the components allows for controlling the tradeoff between factuality and fluency in the model output. Finally, we compare our approach to a recently proposed method to control factuality in grounded dialog, CTRL (Rashkin et al., 2021), and show that both approaches can be combined to achieve additional improvements. © 2022 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

Automatically assigning research methods to journal articles in the domain of social sciences

引用

Proceedings of the Association for Information science and Technology 2014年第1期50卷 1-8页

作者： Judith Eckle-Kohler Tri-Duc Nghiem Iryna Gurevych Ubiquitous Knowledge Processing (UKP) Lab Department of Computer Science Technische Universität Darmstadt Germany

We investigate the automatic assignment of research methods to journal articles from the domain of Social sciences. We employ computer science and Computational Linguistics methodology to perform this automatic assignment of metadata. The multi-label classification system we present uses only abstracts and titles of journal articles as input. Our best system is able to assign the important research methods empirical and quantitative empirical with F-scores of 0.67 and 0.68. These research methods are in the focus of many recent manual analyses of publications databases. Our classification approach could be applied to automatically analyze large publications databases and databases of bibliographic references according to the use of empirical and quantitative empirical methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The impact of topic bias on quality flaw prediction in Wikipedia

The impact of topic bias on quality flaw prediction in Wikip...

引用

51st Annual Meeting of the Association for Computational Linguistics, ACL 2013

作者： Ferschke, Oliver Gurevych, Iryna Rittberger, Marc Ubiquitous Knowledge Processing Lab. Department of Computer Science Technische Universität Darmstadt Germany Information Center for Education German Institute for Educational Research and Educational Information Germany

ISBN: (纸本)9781937284503

With the increasing amount of user generated reference texts in the web, automatic quality assessment has become a key challenge. However, only a small amount of annotated data is available for training quality assessment systems. Wikipedia contains a large amount of texts annotated with cleanup templates which identify quality flaws. We show that the distribution of these labels is topically biased, since they cannot be applied freely to any arbitrary article. We argue that it is necessary to consider the topical restrictions of each label in order to avoid a sampling bias that results in a skewed classifier and overly optimistic evaluation results. We factor out the topic bias by extracting reliable training instances from the revision history which have a topic distribution similar to the labeled articles. This approach better reflects the situation a classifier would face in a real-life application. © 2013 Association for Computational Linguistics.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Automatically classifying edit categories in wikipedia revisions

Automatically classifying edit categories in wikipedia revis...

引用

2013 Conference on Empirical Methods in Natural Language processing, EMNLP 2013

作者： Daxenberger, Johannes Gurevych, Iryna Ubiquitous Knowledge Processing Lab. Department of Computer Science Technische Universität Darmstadt Germany Information Center for Education German Institute for Educational Research and Educational Information Germany

ISBN: (纸本)9781937284978

In this paper, we analyze a novel set of features for the task of automatic edit category classification. Edit category classification assigns categories such as spelling error correction, paraphrase or vandalism to edits in a document. Our features are based on differences between two versions of a document including meta data, textual and language properties and markup. In a supervised machine learning experiment, we achieve a micro-averaged F1 score of 62 on a corpus of edits from the English Wikipedia. In this corpus, each edit has been multi-labeled according to a 21-category taxonomy. A model trained on the same data achieves state-of-the-art performance on the related task of fluency edit classification. We apply pattern mining to automatically labeled edits in the revision histories of different Wikipedia articles. Our results suggest that high-quality articles show a higher degree of homogeneity with respect to their collaboration patterns as compared to random articles. © 2013 Association for Computational Linguistics.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Assessing SRL frameworks with automatic training data expansion

Assessing SRL frameworks with automatic training data expans...

引用

11th Linguistic Annotation Workshop, LAW XI 2017

作者： Hartmann, Silvana Mújdricza-Maydt, Éva Kuznetsov, Ilia Gurevych, Iryna Frank, Anette Ubiquitous Knowledge Processing Lab Department of Computer Science Technische Universität Darmstadt Germany Research Training School AIPHES Germany Department of Computational Linguistics Heidelberg University Germany

ISBN: (纸本)9781945626395

We present the first experiment-based study that explicitly contrasts the three major semantic role labeling frameworks. As a prerequisite, we create a dataset labeled with parallel FrameNet-, PropBank-, and VerbNet-style labels for German. We train a state-of-the-art SRL tool for German for the different annotation styles and provide a comparative analysis across frameworks. We further explore the behavior of the frameworks with automatic training data generation. VerbNet provides larger semantic expressivity than PropBank, and we find that its generalization capacity approaches PropBank in SRL training, but it benefits less from training data expansion than the sparse-data affected FrameNet. © 2017 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Behind the Article: Recognizing Dialog Acts in Wikipedia Talk Pages 12

Behind the Article: Recognizing Dialog Acts in Wikipedia Tal...

引用

Conference of The European Chapter of The Association for Computational Linguistics

作者： Oliver Ferschke Iryna Gurevych Yevgen Chebotar Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science Technische Universitaet Darmstadt Ubiquitous Knowledge Processing Lab (UKP-DIPF)German Institute for Educational Research and Educational Information Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science Technische Universitaet Darmstadt

ISBN: (纸本)9781622760428

In this paper, we propose an annotation schema for the discourse analysis of Wikipedia Talk pages aimed at the coordination efforts for article improvement. We apply the annotation schema to a corpus of 100 Talk pages from the Simple English Wikipedia and make the resulting dataset freely available for download~1. Furthermore, we perform automatic dialog act classification on Wikipedia discussions and achieve an average F_1 -score of 0.82 with our classification pipeline.

关键词： Wikipedia Speaking Conversation Discourse Analysis schema ANNOTATIONS Taxonomy

来源：评论

学校读者我要写书评

暂无评论

UKP: Computing Semantic Textual Similarity by Combining Multiple Content Similarity Measures 12

UKP: Computing Semantic Textual Similarity by Combining Mult...

引用

Joint Conference on Lexical and Computational Semantics

作者： Daniel Baer Chris Biemann Iryna Gurevych Torsten Zesch Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science Technische Universitaet Darmstadt Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science Technische Universitaet DarmstadtUbiquitous Knowledge Processing Lab (UKP-DIPF) German Institute for Educational Research and Educational Information

ISBN: (纸本)9781622765027

We present the UKP system which performed best in the Semantic Textual Similarity (STS) task at SemEval-2012 in two out of three metrics. It uses a simple log-linear regression model, trained on the training data, to combine multiple text similarity measures of varying complexity. These range from simple character and word n-grams and common subsequences to complex features such as Explicit Semantic Analysis vector comparisons and aggregation of word similarity based on lexical-semantic resources. Further, we employ a lexical substitution system and statistical machine translation to add additional lexemes, which alleviates lexical gaps. Our final models, one per dataset, consist of a log-linear combination of about 20 features, out of the possible 300+ features implemented.

关键词： machine translation similar measure Semantics Dataset simple regression (model) Linear Combination Word

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：