A Study on Improving End-to-End Neural Coreference Resolution

Gu, Jia-Chen; Ling, Zhen-Hua; Indurkhya, Nitin

doi:10.1007/978-3-030-01716-3_14

Cited by 7 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The task of coreference resolution is to identify which pronouns are related to which entities in the sentence and cluster them correctly. Modern methods rely on deep neural networks as they perform better than syntactic parsers and feature-engineering based methods (Gu et al (2018)). The various coreference resolution models can be broadly categorized into mention pair classifiers, entity-level models, latent-tree models, mention-ranking models, and span-ranking models (Gu et al (2018); Lee et al (2017)).…”

Section: Coreference Resolutionmentioning

confidence: 99%

“…Modern methods rely on deep neural networks as they perform better than syntactic parsers and feature-engineering based methods (Gu et al (2018)). The various coreference resolution models can be broadly categorized into mention pair classifiers, entity-level models, latent-tree models, mention-ranking models, and span-ranking models (Gu et al (2018); Lee et al (2017)). The models proposed by Clark and Manning (2016a,b) are examples of a mention-ranking models.…”

Section: Coreference Resolutionmentioning

confidence: 99%

“…The models proposed by Clark and Manning (2016a,b) are examples of a mention-ranking models. The models by Lee et al (2017) and Gu et al (2018) are examples of span-ranking models. In our framework we use a mention-ranking model that is described in further detail in Section 2.2.3.…”

Section: Coreference Resolutionmentioning

confidence: 99%

See 2 more Smart Citations

Unified Representation of Twitter and Online News Using Graph and Entities

et al. 2021

View full text Add to dashboard Cite

To improve consumer engagement and satisfaction, online news services employ strategies for personalizing and recommending articles to their users based on their interests. In addition to news agencies’ own digital platforms, they also leverage social media to reach out to a broad user base. These engagement efforts are often disconnected with each other, but present a compelling opportunity to incorporate engagement data from social media to inform their digital news platform and vice-versa, leading to a more personalized experience for users. While this idea seems intuitive, there are several challenges due to the disparate nature of the two sources. In this paper, we propose a model to build a generalized graph of news articles and tweets that can be used for different downstream tasks such as identifying sentiment, trending topics, and misinformation, as well as sharing relevant articles on social media in a timely fashion. We evaluate our framework on a downstream task of identifying related pairs of news articles and tweets with promising results. The content unification problem addressed by our model is not unique to the domain of news, and thus can be applicable to other problems linking different content platforms.

show abstract

Section: Coreference Resolutionmentioning

confidence: 99%

Section: Coreference Resolutionmentioning

confidence: 99%

See 1 more Smart Citation

Unified Representation of Twitter and Online News Using Graph and Entities

et al. 2021

View full text Add to dashboard Cite

show abstract

“…To attempt and solve the common problem of globally inconsistent decisions amongst the mention-ranking models, without using global features or entities, a clustering algorithm is proposed in Gu et al (2018). Using the span ranking model as a baseline (Lee et al, 2017), they propose the use of indirect links via the scoring function and create sets that are considered during inference to dismiss clustering decisions during inference.…”

Section: Mention-ranking Modelsmentioning

confidence: 99%

A Neural Entity Coreference Resolution Review

Stylianou,

Vlahavas

2019

Preprint

View full text Add to dashboard Cite

Entity Coreference Resolution is the task of resolving all the mentions in a document that refer to the same real world entity and is considered as one of the most difficult tasks in natural language understanding. While in it is not an end task, it has been proved to improve downstream natural language processing tasks such as entity linking, machine translation, summarization and chatbots. We conducted a systematic a review of neural-based approached and provide a detailed appraisal of the datasets and evaluation metrics in the field. Emphasis is given on Pronoun Resolution, a subtask of Coreference Resolution, which has seen various improvements in the recent years. We conclude the study by highlight the lack of agreed upon standards and propose a way to expand the task even further.

show abstract

“…Since 2017, various extensions to the model have been proposed. ranging from using higher-order inference to directly optimizing evaluation metrics using reinforcement learning [10,11,12,13,14,15,16,17] (Figure 2). Despite improving the coreference resolution performance by a large margin, these extensions add a lot of extra complexity to the original model.…”

Section: Introductionmentioning

confidence: 99%

End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline

Lai¹,

Bui²,

Kim³

2021

Preprint

View full text Add to dashboard Cite

Since the first end-to-end neural coreference resolution model was introduced, many extensions to the model have been proposed, ranging from using higher-order inference to directly optimizing evaluation metrics using reinforcement learning. Despite improving the coreference resolution performance by a large margin, these extensions add a lot of extra complexity to the original model. Motivated by this observation and the recent advances in pre-trained Transformer language models, we propose a simple yet effective baseline for coreference resolution. Our model is a simplified version of the original neural coreference resolution model, however, it achieves impressive performance, outperforming all recent extended works on the public English OntoNotes benchmark. Our work provides evidence for the necessity of carefully justifying the complexity of existing or newly proposed models, as introducing a conceptual or practical simplification to an existing model can still yield competitive results.

show abstract

A Study on Improving End-to-End Neural Coreference Resolution

Cited by 7 publications

References 14 publications

Unified Representation of Twitter and Online News Using Graph and Entities

Unified Representation of Twitter and Online News Using Graph and Entities

A Neural Entity Coreference Resolution Review

End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline

Contact Info

Product

Resources

About