Collective Entity Resolution with Multi-Focal Attention

Globerson, Amir; Lazic, Nevena; Chakrabarti, Soumen; Subramanya, Amarnag; Ringaard, Michael; Pereira, Fernando

doi:10.18653/v1/p16-1059

Cited by 106 publications

(137 citation statements)

References 26 publications

Supporting

Mentioning

137

Contrasting

Order By: Relevance

“…Many approaches perform joint inference over the linking decisions in a document (Milne and Witten, 2008;Ratinov et al, 2011;Hoffart et al, 2011;Globerson et al, 2016), identify mentions that do not link to any existing entity (NIL) (Bunescu and Pasca, 2006;Ratinov et al, 2011), and cluster NIL-mentions (Wick et al, 2013;Lazic et al, 2015) to discover new entities. Few approaches jointly model entity linking, and other related NLP tasks to improve linking, such as, coreference resolution (Hajishirzi et al, 2013), relational inference (Cheng and Roth, 2013), and joint coreference with typing (Durrett and Klein, 2014 Figure 1: Overview of the Model ( § 3): Each entity has a Wikipedia description, linked mentions in Wikipedia (only one shown), and fine-grained types from Freebase (only one shown).…”

Section: Related Workmentioning

confidence: 99%

Entity Linking via Joint Encoding of Types, Descriptions, and Context

Gupta¹,

Singh²,

Roth³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

202

195

View full text Add to dashboard Cite

For accurate entity linking, we need to capture various information aspects of an entity, such as its description in a KB, contexts in which it is mentioned, and structured knowledge. Additionally, a linking system should work on texts from different domains without requiring domain-specific training data or hand-engineered features.In this work we present a neural, modular entity linking system that learns a unified dense representation for each entity using multiple sources of information, such as its description, contexts around its mentions, and its fine-grained types. We show that the resulting entity linking system is effective at combining these sources, and performs competitively, sometimes out-performing current state-of-theart systems across datasets, without requiring any domain-specific training data or hand-engineered features. We also show that our model can effectively "embed" entities that are new to the KB, and is able to link its mentions accurately.

show abstract

Section: Related Workmentioning

confidence: 99%

Entity Linking via Joint Encoding of Types, Descriptions, and Context

Gupta¹,

Singh²,

Roth³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

202

195

View full text Add to dashboard Cite

show abstract

“…Lazic et al (2015) 86. 4 Huang et al (2015) 86.6 Chisholm and Hachey (2015) 88.7 Ganea et al (2016) 87.6 Guo and Barbosa (2016) 89.0 Globerson et al (2016) 91.0 Yamada et al (2016) 91.5 Ganea and Hofmann (2017) 92.2…”

Section: Systemmentioning

confidence: 99%

Collective Entity Disambiguation with Structured Gradient Tree Boosting

Yang¹,

İrsoy²,

Rahman³

2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

View full text Add to dashboard Cite

We present a gradient-tree-boosting-based structured learning model for jointly disambiguating named entities in a document. Gradient tree boosting is a widely used machine learning algorithm that underlies many topperforming natural language processing systems. Surprisingly, most works limit the use of gradient tree boosting as a tool for regular classification or regression problems, despite the structured nature of language. To the best of our knowledge, our work is the first one that employs the structured gradient tree boosting (SGTB) algorithm for collective entity disambiguation. By defining global features over previous disambiguation decisions and jointly modeling them with local features, our system is able to produce globally optimized entity assignments for mentions in a document. Exact inference is prohibitively expensive for our globally normalized model. To solve this problem, we propose Bidirectional Beam Search with Gold path (BiBSG), an approximate inference algorithm that is a variant of the standard beam search algorithm. BiBSG makes use of global information from both past and future to perform better local search. Experiments on standard benchmark datasets show that SGTB significantly improves upon published results. Specifically, SGTB outperforms the previous state-of-the-art neural system by near 1% absolute accuracy on the popular AIDA-CoNLL dataset.

show abstract

“…For example the local component of the GLOW algorithm (Ratinov et al, 2011) was used as part of the relational inference system suggested by Cheng and Roth (2013). Similarly, Globerson et al (2016) achieved state-of-the-art results by extending the local-based selective-context model of Lazic et al (2015) with an attention-like coherence model.…”

Section: Related Workmentioning

confidence: 84%

Named Entity Disambiguation for Noisy Text

Eshel¹,

Cohen²,

Radinsky³

et al. 2017

Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)

110

View full text Add to dashboard Cite

We address the task of Named Entity Disambiguation (NED) for noisy text. We present WikilinksNED, a large-scale NED dataset of text fragments from the web, which is significantly noisier and more challenging than existing newsbased datasets. To capture the limited and noisy local context surrounding each mention, we design a neural model and train it with a novel method for sampling informative negative examples. We also describe a new way of initializing word and entity embeddings that significantly improves performance. Our model significantly outperforms existing state-ofthe-art methods on WikilinksNED while achieving comparable performance on a smaller newswire dataset.

show abstract

Collective Entity Resolution with Multi-Focal Attention

Cited by 106 publications

References 26 publications

Entity Linking via Joint Encoding of Types, Descriptions, and Context

Entity Linking via Joint Encoding of Types, Descriptions, and Context

Collective Entity Disambiguation with Structured Gradient Tree Boosting

Named Entity Disambiguation for Noisy Text

Contact Info

Product

Resources

About