natural-language-processing

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 coreference-resolution-1

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find coreference-resolution-1 models and implementations

Datasets

OntoNotes 5.0

DaNE

Subtasks

No subtasks available.

Most implemented papers

Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods

Mark Yatskar, Vicente Ordonez, Jieyu Zhao, Tianlu Wang, Kai-Wei Chang•Tue Apr 17 2018

A data-augmentation approach is demonstrated that, in combination with existing word-embedding debiasing techniques, removes the bias demonstrated by rule-based, feature-rich, and neural coreference systems in WinoBias without significantly affecting their performance on existing datasets.

1091

Content

0

Paper Graph

Gender Bias in Coreference Resolution

Rachel Rudinger, Benjamin Van Durme, Jason Naradowsky, Brian Leonard•Tue Apr 24 2018

A novel, Winograd schema-style set of minimal pair sentences that differ only by pronoun gender are introduced, and systematic gender bias in three publicly-available coreference resolution systems is evaluated and confirmed.

705 0

Paper Graph

They Exist! Introducing Plural Mentions to Coreference Resolution and Entity Linking

Jinho D. Choi, Ethan Zhou•Tue Jul 31 2018

This paper analyzes arguably the most challenging yet under-explored aspect of resolution tasks such as coreference resolution and entity linking, that is the resolution of plural mentions, taking the character identification corpus from the SemEval 2018 shared task and adding annotation for plural mentions.

41 0

Paper Graph

The MultiBERTs: BERT Reproductions for Robustness Analysis

A. D'Amour, Jacob Eisenstein, Steve Yadlowsky, Ellie Pavlick, Ian Tenney, Dipanjan Das, Thibault Sellam, Jason Wei, Iulia Turc, Naomi Saphra, Tal Linzen, Jasmijn Bastings•Tue Jun 29 2021

The MultiBERTs are introduced, a set of 25 BERT-Base checkpoints trained with similar hyper-parameters as the original BERT model but differing in random weight initialization and shuffling of training data, and the Multi-Bootstrap is defined, a non-parametric bootstrap method for statistical inference designed for settings where there are multiple pre-trained models and limited test data.

101 0

Paper Graph

DWIE: an entity-centric dataset for multi-task document-level information extraction

Klim Zaporojets, Johannes Deleu, Chris Develder, Thomas Demeester•Fri Sep 25 2020

This paper proposes a new entity-driven metric that takes into account the number of mentions that compose each of the predicted and ground truth entities in DWIE, and proposes to use graph-based neural message passing techniques between document-level mention spans to stimulate further research in graph neural networks for representation learning in multi-task IE.

77 0

Paper Graph

WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia

Ido Dagan, Alon Eirew, Arie Cattan•Sat Apr 10 2021

Wikipedia Event Coreference (WEC) is presented, an efficient methodology for gathering a large-scale dataset for cross-document event coreference from Wikipedia, where coreference links are not restricted within predefined topics.

34 0

Paper Graph

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 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

Moving on from OntoNotes: Coreference Resolution Model Transfer

Benjamin Van Durme, Patrick Xia•Fri Apr 16 2021

This work examines eleven target datasets and finds that continued training is consistently effective and especially beneficial when there are few target documents, and establishes new benchmarks across several datasets, including state-of-the-art results on PreCo.

32 0

Paper Graph

Paraphrasing vs Coreferring: Two Sides of the Same Coin

Ido Dagan, Avi Caciularu, Vered Shwartz, Y. Meged•Wed Apr 29 2020

This work used annotations from an event coreference dataset as distant supervision to re-score heuristically-extracted predicate paraphrases, and used the same re-ranking features as additional inputs to a state-of-the-art eventcoreference resolution model, which yielded modest but consistent improvements to the model’s performance.

30 0

Paper Graph

Adding a benchmark result helps the community track progress.