natural-language-processing

Cross Document Coreference Resolution

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 cross-document-coreference-resolution

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find cross-document-coreference-resolution models and implementations

Datasets

WEC-Eng

SciCo

CoreSearch

Subtasks

No subtasks available.

Most implemented papers

Streamlining Cross-Document Coreference Resolution: Evaluation and Modeling

Gabriel Stanovsky, Ido Dagan, Alon Eirew, Mandar Joshi, Arie Cattan•Tue Sep 22 2020

This work proposes a pragmatic evaluation methodology which assumes access to only raw text -- rather than assuming gold mentions, disregards singleton prediction, and addresses typical targeted settings in CD coreference resolution.

37

Content

0

Paper Graph

SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts

Daniel S. Weld, Ido Dagan, Iz Beltagy, Doug Downey, Arie Cattan, Sophie Johnson, Tom Hope•Sat Apr 17 2021

SciCo, an expert-annotated dataset for H-CDCR in scientific papers, is created, 3X larger than the prominent ECB+ resource, and is studied to study strong baseline models that are customize for H -CDCR, and highlight challenges for future work.

25 0

Paper Graph

CoRefi: A Crowd Sourcing Suite for Coreference Annotation

Ido Dagan, Arie Cattan, A. Bornstein•Wed Sep 30 2020

CoRefi is a web-based coreference annotation suite, oriented for crowdsourcing, that provides guided onboarding for the task as well as a novel algorithm for a reviewing phase.

19 0

Paper Graph

Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution

Ido Dagan, Nils Reimers, Alon Eirew, Vered Shwartz, Shany Barhom, M. Bugert•Sun May 26 2019

This work jointly model entity and event coreference, and proposes a neural architecture for cross-document coreference resolution using its lexical span, surrounding context, and relation to entity (event) mentions via predicate-arguments structures.

100 0

Paper Graph

Predicate Argument Alignment using a Global Coherence Model

Mark Dredze, Benjamin Van Durme, Travis Wolfe•Wed Dec 31 2014

A joint model for predicate argument alignment is presented that leverages multiple sources of semantic information, including temporal ordering constraints between events, in a max-margin framework to find a globally consistent view of entities and events across multiple documents.

11 0

Paper Graph

Cross-document Coreference Resolution over Predicted Mentions

Gabriel Stanovsky, Ido Dagan, Alon Eirew, Mandar Joshi, Arie Cattan•Tue Jun 01 2021

This work introduces the first end-to-end model for CD coreference resolution from raw text, which extends the prominent model for within-document coreference to the CD setting and achieves competitive results for event and entity coreference Resolution on gold mentions.

50 0

Paper Graph

Towards Evaluation of Cross-document Coreference Resolution Models Using Datasets with Diverse Annotation Schemes

Bela Gipp, Anastasia Zhukova, Felix Hamborg•Fri Sep 10 2021

A phrasing diversity metric (PD) is proposed that encounters for the diversity of full phrases unlike the previously proposed metrics and allows to evaluate lexical diversity of the CDCR datasets in a higher precision.

1 0

Paper Graph

Cross-document Event Coreference Search: Task, Dataset and Modeling

Ido Dagan, Alon Eirew, Avi Caciularu•Sat Oct 22 2022

A novel model is presented that integrates a powerful coreference scoring scheme into the DPR architecture, yielding improved performance and adapting the prominent Deep Passage Retrieval model to the setting, as an appealing baseline.

14 0

Paper Graph

Realistic Evaluation Principles for Cross-document Coreference Resolution

Gabriel Stanovsky, Ido Dagan, Alon Eirew, Mandar Joshi, Arie Cattan•Mon Jun 07 2021

It is argued that models should not exploit the synthetic topic structure of the standard ECB+ dataset, forcing models to confront the lexical ambiguity challenge, as intended by the dataset creators.

23 0

Paper Graph

CHAMP: Efficient Annotation and Consolidation of Cluster Hierarchies

Ido Dagan, Arie Cattan, Tom Hope, Doug Downey, Roy Bar-Haim, Lilach Eden, Yoav Kantor•Sat Nov 18 2023

CHAMP is an open source tool allowing to incrementally construct both clusters and hierarchy simultaneously over any type of texts, which significantly reduces annotation time compared to the common pairwise annotation approach and also guarantees maintaining transitivity at the cluster and hierarchy levels.

0 0

Paper Graph

Adding a benchmark result helps the community track progress.