咨询与建议

限定检索结果

文献类型

  • 37 篇 会议
  • 27 篇 期刊文献

馆藏范围

  • 64 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 45 篇 工学
    • 40 篇 计算机科学与技术...
    • 35 篇 软件工程
    • 8 篇 信息与通信工程
    • 4 篇 控制科学与工程
    • 1 篇 机械工程
    • 1 篇 光学工程
    • 1 篇 材料科学与工程(可...
    • 1 篇 电气工程
    • 1 篇 建筑学
    • 1 篇 化学工程与技术
    • 1 篇 轻工技术与工程
    • 1 篇 生物医学工程(可授...
    • 1 篇 生物工程
  • 16 篇 理学
    • 12 篇 数学
    • 3 篇 统计学(可授理学、...
    • 2 篇 物理学
    • 2 篇 系统科学
    • 1 篇 化学
    • 1 篇 生物学
  • 12 篇 管理学
    • 11 篇 图书情报与档案管...
    • 1 篇 管理科学与工程(可...
    • 1 篇 工商管理
  • 2 篇 医学
    • 2 篇 基础医学(可授医学...
    • 2 篇 临床医学
    • 1 篇 药学(可授医学、理...
  • 1 篇 教育学
    • 1 篇 教育学

主题

  • 7 篇 semantics
  • 4 篇 natural language...
  • 3 篇 knowledge based ...
  • 2 篇 indexes
  • 2 篇 transparency
  • 2 篇 search engines
  • 2 篇 contrastive lear...
  • 2 篇 computational li...
  • 2 篇 left-sided displ...
  • 2 篇 crowdsourcing
  • 2 篇 bayesian network...
  • 2 篇 anterior interve...
  • 2 篇 laser doppler an...
  • 1 篇 similar measure
  • 1 篇 machine translat...
  • 1 篇 sweeps
  • 1 篇 springs
  • 1 篇 reinforcement le...
  • 1 篇 model parameters
  • 1 篇 deep learning

机构

  • 9 篇 ubiquitous knowl...
  • 9 篇 ubiquitous knowl...
  • 3 篇 information cent...
  • 3 篇 ubiquitous knowl...
  • 3 篇 ubiquitous knowl...
  • 3 篇 ubiquitous knowl...
  • 2 篇 ubiquitous knowl...
  • 2 篇 department of co...
  • 2 篇 dept. of compute...
  • 2 篇 computer science...
  • 2 篇 ubiquitous knowl...
  • 2 篇 department of co...
  • 2 篇 apptek gmbh
  • 2 篇 department of co...
  • 2 篇 trustworthy huma...
  • 2 篇 ubiquitous knowl...
  • 2 篇 information syst...
  • 2 篇 ubiquitous knowl...
  • 2 篇 ubiquitous knowl...
  • 2 篇 institute for nu...

作者

  • 38 篇 gurevych iryna
  • 11 篇 zesch torsten
  • 5 篇 dagan ido
  • 5 篇 simpson edwin
  • 4 篇 iryna gurevych
  • 4 篇 eger steffen
  • 4 篇 daxenberger joha...
  • 4 篇 schiller benjami...
  • 4 篇 kuznetsov ilia
  • 3 篇 stowe kevin
  • 3 篇 reimers nils
  • 3 篇 gao yang
  • 3 篇 levy omer
  • 3 篇 kramer stefan
  • 3 篇 chris biemann
  • 2 篇 biemann chris
  • 2 篇 frank anette
  • 2 篇 waldis andreas
  • 2 篇 habernal ivan
  • 2 篇 miyao yusuke

语言

  • 62 篇 英文
  • 2 篇 其他
检索条件"机构=Ubiquitous Knowledge Processing Lab Department of Computer Science"
64 条 记 录,以下是1-10 订阅
排序:
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...
收藏 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
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 a... 详细信息
来源: 评论
DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting  29
DP-Rewrite: Towards Reproducibility and Transparency in Diff...
收藏 引用
29th International Conference on Computational Linguistics, COLING 2022
作者: Igamberdiev, Timour Arnold, Thomas Habernal, Ivan Trustworthy Human Language Technologies Ubiquitous Knowledge Processing Lab Department of Computer Science Technical University of Darmstadt Germany
Text rewriting with differential privacy (DP) provides concrete theoretical guarantees for protecting the privacy of individuals in textual documents. In practice, existing systems may lack the means to validate their... 详细信息
来源: 评论
The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Learning Capabilities
arXiv
收藏 引用
arXiv 2025年
作者: Bigoulaeva, Irina Madabushi, Harish Tayyar Gurevych, Iryna Ubiquitous Knowledge Processing Lab Technical University of Darmstadt Germany Department of Computer Science The University of Bath United Kingdom
Large Language Models (LLMs), trained on extensive web-scale corpora, have demonstrated remarkable abilities across diverse tasks, especially as they are scaled up. Nevertheless, even state-of-the-art models struggle ... 详细信息
来源: 评论
Constrained C-Test Generation via Mixed-Integer Programming
arXiv
收藏 引用
arXiv 2024年
作者: Lee, Ji-Ung Pfetsch, Marc E. Gurevych, Iryna Ubiquitous Knowledge Processing Lab Department of Computer Science Germany Research Group Optimization Department of Mathematics Technical University of Darmstadt Germany Hessian AI
This work proposes a novel method to generate C-Tests;a deviated form of cloze tests (a gap filling exercise) where only the last part of a word is turned into a gap. In contrast to previous works that only consider v... 详细信息
来源: 评论
Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model
Controllable Factuality in Document-Grounded Dialog Systems ...
收藏 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 generatio... 详细信息
来源: 评论
Are Emergent Abilities in Large Language Models just In-Context Learning?
arXiv
收藏 引用
arXiv 2023年
作者: Lu, Sheng Bigoulaeva, Irina Sachdeva, Rachneet Madabushi, Harish Tayyar Gurevych, Iryna Ubiquitous Knowledge Processing Lab Technical University of Darmstadt Germany Department of Computer Science The University of Bath United Kingdom
Large language models, comprising billions of parameters and pre-trained on extensive web-scale corpora, have been claimed to acquire certain capabilities without having been specifically trained on them. These capabi... 详细信息
来源: 评论
ArgumenText: Argument Classification and Clustering in a Generalized Search Scenario
收藏 引用
Datenbank-Spektrum 2020年 第2期20卷 115-121页
作者: Daxenberger, Johannes Schiller, Benjamin Stahlhut, Chris Kaiser, Erik Gurevych, Iryna Ubiquitous Knowledge Processing Lab Department of Computer Science Technische Universität Darmstadt Darmstadt Germany
The ArgumenText project creates argument mining technology for big and heterogeneous data and aims to evaluate its use in real-world applications. The technology mines and clusters arguments from a variety of tex... 详细信息
来源: 评论
DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting
arXiv
收藏 引用
arXiv 2022年
作者: Igamberdiev, Timour Arnold, Thomas Habernal, Ivan Trustworthy Human Language Technologies Ubiquitous Knowledge Processing Lab Department of Computer Science Technical University of Darmstadt Germany
Text rewriting with differential privacy (DP) provides concrete theoretical guarantees for protecting the privacy of individuals in textual documents. In practice, existing systems may lack the means to validate their... 详细信息
来源: 评论
UKP-SQUARE: An Online Platform for Question Answering Research
arXiv
收藏 引用
arXiv 2022年
作者: Baumgärtner, Tim Wang, Kexin Sachdeva, Rachneet Eichler, Max Geigle, Gregor Poth, Clifton Sterz, Hannah Puerto, Haritz Ribeiro, Leonardo F.R. Pfeiffer, Jonas Reimers, Nils Şahin, Gözde Gül Gurevych, Iryna Ubiquitous Knowledge Processing Lab Department of Computer Science Technical University of Darmstadt Germany Hugging Face Koç University Computer Science and Engineering Department Turkey
Recent advances in NLP and information retrieval have given rise to a diverse set of question answering tasks that are of different formats (e.g., extractive, abstractive), require different model architectures (e.g.,... 详细信息
来源: 评论
Ranking Creative Language Characteristics in Small Data Scenarios  13
Ranking Creative Language Characteristics in Small Data Scen...
收藏 引用
13th International Conference on Computational Creativity, ICCC 2022
作者: Siekiera, Julia Köppel, Marius Simpson, Edwin Stowe, Kevin Gurevych, Iryna Kramer, Stefan Dept. of Computer Science Johannes Gutenberg-Universität Mainz Germany Institute for Nuclear Physics Johannes Gutenberg-Universität Mainz Germany Dept. of Computer Science University of Bristol United Kingdom Ubiquitous Knowledge Processing Lab. Technische Universität Darmstadt Germany
The ability to rank creative natural language provides an important general tool for downstream language understanding and generation. However, current deep ranking models require substantial amounts of labeled data t... 详细信息
来源: 评论