Challenge: despite significant progress on entity coreference resolution, there is a general lack of understanding of what has been improved.
Approach: They present an empirical analysis of entity coreference resolvers to provide an understanding of what has been improved.
Outcome: The proposed model improves the performance of entity coreference resolvers.

Similar Papers

Conundrums in Event Coreference Resolution: Making Sense of the State of the Art (2021.emnlp-main)

Copied to clipboard

Challenge: Recent years have seen the successful application of span-based neural models to entity-based information extraction tasks such as entity coreference resolution (CR) Existing event coreference resolvers focused on feature engineering are few and far between, let alone event corefers.
Approach: They propose to adapt existing span-based event reference systems to event coreference by adapting the models originally developed for entity coreference to event CR.
Outcome: The proposed model improves the representations of entity mentions in entity-based IE tasks compared to non-span models .
Bridging Resolution: A Survey of the State of the Art (2020.coling-main)

Copied to clipboard

Challenge: bridging resolution is an anaphora resolution task that is less studied than entity coreference resolution.
Approach: This paper presents a survey of the current state of research on bridging resolution . it identifies and resolves bridling/associative anaphors, which are anamorphic references to non-identical associated antecedents.
Outcome: The proposed task is more difficult than entity coreference resolution because of the lack of annotated corpora and lack of standardized evaluation protocols.
End-to-End Neural Bridging Resolution (2022.coling-1)

Copied to clipboard

Challenge: state-of-the-art resolvers for bridging resolution are weaker than entity coreference resolution.
Approach: They evaluate bridging resolvers in an end-to-end setting and strengthen them with better encoders . they also try to gain a better understanding of them through perturbation experiments .
Outcome: bridging resolvers are evaluated in an end-to-end setting and strengthened with better encoders . bribridging resolution is the task of identifying briating anaphors and linking them to their antecedents - a paper by the journal bribing resolution argues .
A Primer in BERTology: What We Know About How BERT Works (2020.tacl-1)

Copied to clipboard

Challenge: a new study examines the current state of knowledge about the BERT model . the model is a stack of transformer encoder layers that are based on multiple self-attention ''heads''
Approach: They present a survey of over 150 studies of the popular Transformer-based model BERT . they discuss the current state of knowledge about how BERT works and how it is represented .
Outcome: The proposed model is based on the Transformer-based model with state-of-the-art results . the proposed model has little cognitive motivation and is too small to perform ablation studies .
Event Coreference Resolution with Non-Local Information (2020.aacl-main)

Copied to clipboard

Challenge: Existing joint models for event coreference resolution are understudied and underexploited . current models only learn trigger detection and event coreference from annotated training data .
Approach: They propose to add a topic-based trigger detection module and a preprocessing module to improve event coreference.
Outcome: The proposed model yields the best results on the KBP 2017 English and Chinese datasets.
They Exist! Introducing Plural Mentions to Coreference Resolution and Entity Linking (C18-1)

Copied to clipboard

Challenge: Unlike singular mentions each of which represents one entity, plural mentions stand for multiple entities.
Approach: They propose a novel coreference resolution algorithm that selectively creates clusters to handle both singular and plural mentions and a deep learning-based entity linking model that jointly handles both types of mentions through multi-task learning.
Outcome: The proposed model outperforms existing models designed for singular mentions and plural mentions.
The Coreference under Transformation Labeling Dataset: Entity Tracking in Procedural Texts Using Event Models (2023.findings-acl)

Copied to clipboard

Challenge: et al., 2023) show that entity coreference resolution is improved when events bring about changes in entities that are not reflected in text mentions.
Approach: They propose to perform transformation-based entity linking prior to coreference relation identification to improve entity coreference.
Outcome: The proposed model improves coreference resolution of entities mentioned under a process-oriented model of events.
A Controlled Reevaluation of Coreference Resolution Models (2024.lrec-main)

Copied to clipboard

Challenge: a pretrained language model is used in state-of-the-art coreference resolution models.
Approach: They evaluate five coreference resolution models and control for language model used . they find that encoder-based CR models outperform decoder--based models in accuracy .
Outcome: The encoder-based model outperforms the decoder--based models in accuracy and speed . older model generalizes the best to out-of-domain textual genres .
Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance (2021.naacl-main)

Copied to clipboard

Challenge: Recent work on entity coreference resolution (CR) follows current trends in Deep Learning . traditional approaches do not make use of hierarchical representations of discourse structure .
Approach: They propose to leverage automatically constructed discourse parse trees within a neural approach to generate anaphoric mentions.
Outcome: The proposed model improves on two benchmark entity coreference-resolution datasets.
End-to-End Neural Discourse Deixis Resolution in Dialogue (2022.emnlp-main)

Copied to clipboard

Challenge: Lexical overlap is a strong indicator of entity coreference, both among names and in the resolution of nominals.
Approach: They propose to extend their span-based entity coreference model to exploit task-specific characteristics of discourse deixis resolution in dialogue.
Outcome: The proposed model achieves state-of-the-art results on the four datasets in the CODI-CRAC 2021 shared task.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations