Overview of DUC 2005

By Hoa Trang Dang. 2005

359 citations recorded by the source corpus.

Subfields: Natural Language Processing, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Evaluation & Benchmarks

Citations in the corpus

Pretrained Transformers for Text Ranking: BERT and Beyond (2020, methodology): “ goes in, summary comes out). Recent work includes Liu and Lapata [2019], Zhang et al. [2019], Subramanian et al. [2019], Zhang et al. [2020c]. In the query-focused summarization variant of the task [Dang, 2005], target summaries are designed speciﬁcally to address a user’s information need. Techniq”
On Faithfulness and Factuality in Abstractive Summarization (2020, methodology): “Following the Document Understanding Conference (DUC; Dang, 2005), a majority of work has focused on evaluating the content and the linguistic quality of summaries (Nenkova, 2005).”
Determinantal Point Processes for Machine Learning (2012, methodology): “We experiment with data from the multidocument summarization task (Task 2) of the 2003 and 2004 Document Understanding Conference (DUC) [34].”
Question Answering as an Automatic Evaluation Metric for News Article Summarization (2019, background): “The TAC 2011 Automatically Evaluating Summaries of Peers ( AESOP ) task (Owczarzak and Dang, 2011) has provided a dataset that includes, alongside the source documents and reference summaries, three manual metrics: Pyramid (Nenkova et al., 2007), Overall Responsiveness (Dang, 2005) and Overall Reada”
BARTScore: Evaluating Generated Text as Text Generation (2021, background): “Coherence (C OH ): Whether the text builds from sentence to sentence to a coherent body of information about a topic [7].”
CTRLsum: Towards Generic Controllable Text Summarization (2020, methodology): “CTRLsum is also related to query-focused 592 summarization (Dang, 2005; Wan et al., 2007; Xu 593 and Lapata, 2020), these methods often work with 594 datasets that provide annotated queries, and did not 595 focus on generic control tasks.”
Generating Image Descriptions Using Dependency Relational Patterns (2010, background): “Each criterion is scored on a ﬁve point scale with high scores indicating a better result (Dang, 2005).”
PRIMER: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization (2021, background): “DUC benchmarks (Dang, 2005) include multidocument summarization datasets in the news domain, with 10-30 documents and 3-4 human-”
Data Augmentation for Abstractive Query-Focused Multi-Document Summarization (2021, methodology): “2004), graph-based (Erkan and Radev 2004) or hierarchical LDA-style models (Haghighi and Vanderwende 2009), and variants of query-focused summarization (Dang 2005), that orient the summary around a given query (Daumé III and Marcu 2006; Zhao, Wu, and Huang 2009).”
Multi-document Summarization via Budgeted Maximization of Submodular Functions (2010, methodology): “One of the standard methods for this problem is called Maximum Marginal Rele-vance (MMR) (Dang, 2005)(Carbonell and Gold-stein, 1998), where a greedy algorithm selects the most relevant sentences, and at the same time avoids redundancy by removing sentences that are too similar to already selected o”
Multimodal Conditionality for Natural Language Generation (2021, background): “In403 spired by Dang (2005) we asked the raters to mea404 sure five linguistic qualities including grammar, 405 non-redundancy, consistency, attractiveness, and 406 overall scores.”
Multi-document multilingual summarization corpus preparation, Part 1: Arabic, English, Greek, Chinese, Romanian (2013, background): “Previously, especially within the Text Analysis Conference (TAC) series of workshops (Dang, 2005; Dang, 2006; Dang and Owczarzak, 2008), multi-document summarization has covered aspects of summarization such as update summarization, guided summarization and cross-lingual summarization.”
Transforming Wikipedia Into Augmented Data for Query-Focused Summarization (2019, background): “The task is first introduced in DUC 2005 (Dang, 2005), with human annotated data released until 2007.”
Diverse Sequential Subset Selection for Supervised Video Summarization (2014, neutral): “several sentences from a long document [18, 19].”