natural-language-processing-9

Query-focused Summarization

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in query-focused-summarization-9

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find query-focused-summarization-9 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

QTSumm: Query-Focused Summarization over Tabular Data

Xiangru Tang, Zhenting Qi, Yilun Zhao, Arman Cohan, Dragomir R. Radev, Yumo Xu, Linyong Nan, Simeng Han, Boyu Mi, Yixin Liu, Weijin Zou, Ruizhe Chen•Mon May 22 2023

A new query-focused table summarization task, where text generation models have to perform human-like reasoning and analysis over the given table to generate a tailored summary, and proposes a new approach, named ReFactor, to retrieve and reason over query-relevant information from tabular data to generate several natural language facts.

Content

1

0

Paper Graph

Generating Query Focused Summaries from Query-Free Resources

Mirella Lapata, Yumo Xu•Mon Dec 28 2020

MaRGE is introduced, a Masked ROUGE Regression framework for evidence estimation and ranking which relies on a unified representation for summaries and queries, so that summaries in generic data can be converted into proxy queries for learning a query model.

40 0

Paper Graph

Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance

Tiezheng Yu, Dan Su, Pascale Fung•Wed May 26 2021

QFS-BART is proposed, a model that incorporates the explicit answer relevance of the source documents given the query via a question answering model, to generate coherent and answer-related summaries and achieves the new state-of-the-art performance.

33 0

Paper Graph

CLIP-It! Language-Guided Video Summarization

Trevor Darrell, Anna Rohrbach, Medhini Narasimhan•Wed Jun 30 2021

This work proposes CLIP-It, a language-guided multimodal transformer that learns to score frames in a video based on their importance relative to one another and their correlation with a user-defined query or an automatically generated dense video caption (for generic video summarization).

156 0

Paper Graph

ASPECTNEWS: Aspect-Oriented Summarization of News Documents

Greg Durrett, Jiacheng Xu, Ojas Ahuja, A. Gupta, Kevin Horecka•Thu Oct 14 2021

This paper collects a dataset of realistic aspect-oriented summaries, AspectNews, which covers different subtopics about articles in news sub-domains, and compares several training schemes that differ in how strongly keywords are used and how oracle summaries are extracted.

54 0

Paper Graph

Exploring Neural Models for Query-Focused Summarization

Alexander R. Fabbri, Wojciech Kryscinski, Jesse Vig•Mon Dec 13 2021

This paper conducts a systematic exploration of neural approaches to QFS, considering two general classes of methods: two-stage extractive-abstractive solutions and end-to-end models.

54 0

Paper Graph

SumREN: Summarizing Reported Speech about Events in News

Hou Pong Chan, R. Reddy, Heba Elfardy, Kevin Small, Heng Ji•Thu Dec 01 2022

This work proposes the novel task of summarizing the reactions of different speakers, as expressed by their reported statements, to a given event, and creates a new multi-document summarization benchmark, SumREN, comprising 745 summaries of reported statements from various public figures obtained from 633 news articles discussing 132 events.

5 0

Paper Graph

A Lightweight Constrained Generation Alternative for Query-focused Summarization

Zhichao Xu, Daniel Cohen•Sat Apr 22 2023

This work proposes leveraging a recently developed constrained generation model Neurological Decoding (NLD) as an alternative to current QFS regimes which rely on additional sub-architectures and training, and demonstrates the efficacy of this approach on two public QFS collections achieving near parity with the state-of-the-art model with substantially reduced complexity.

13 0

Paper Graph

Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering

Arman Cohan, Ido Dagan, J. Goldberger, Matthew E. Peters, Avi Caciularu•Tue May 23 2023

This work proposes pre- training a generic multi-document model from a novel cross-document question answering pre-training objective, and develops a novel multi- document QA formulation that directs the model to better recover cross-text informational relations, and introduces a natural augmentation that artificially increases the pre- Training data.

37 0

Paper Graph

QuOTeS: Query-Oriented Technical Summarization

E. Milios, Juan Ramirez-Orta, Eduardo Xamena, Ana Gabriela Maguitman, Axel J. Soto, Flavia P. Zanoto•Mon Jun 19 2023

The results show that QuOTeS provides a positive user experience and consistently provides query-focused summaries that are relevant, concise, and complete.

0 0

Paper Graph

Adding a benchmark result helps the community track progress.