Entity Disambiguation with Web Links

Chisholm, Andrew M.; Hachey, Ben

doi:10.1162/tacl_a_00129

Cited by 68 publications

(75 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accuracy Chisholm and Hachey (2015) 88.7 Guo and Barbosa (2018) 89.0 Globerson et al (2016) 91.0 Yamada et al (2016) 91.5 Ganea and Hofmann (2017) 92.22 ± 0.14 Yang et al (2018) 93.0 Le and Titov (2018) 93.07 ± 0.27 Our 94.0 ± 0.28 Our (+pseudo entities)…”

Section: Methodsmentioning

confidence: 99%

Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation

Yamada¹,

Shindo

Takeda

et al. 2016

Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning

300

457

View full text Add to dashboard Cite

Named Entity Disambiguation (NED) refers to the task of resolving multiple named entity mentions in a document to their correct references in a knowledge base (KB) (e.g., Wikipedia). In this paper, we propose a novel embedding method specifically designed for NED. The proposed method jointly maps words and entities into the same continuous vector space. We extend the skip-gram model by using two models. The KB graph model learns the relatedness of entities using the link structure of the KB, whereas the anchor context model aims to align vectors such that similar words and entities occur close to one another in the vector space by leveraging KB anchors and their context words. By combining contexts based on the proposed embedding with standard NED features, we achieved state-of-theart accuracy of 93.1% on the standard CoNLL dataset and 85.2% on the TAC 2010 dataset.

show abstract

Section: Methodsmentioning

confidence: 99%

Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation

Yamada¹,

Shindo

Takeda

et al. 2016

Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning

300

457

View full text Add to dashboard Cite

show abstract

“…AIDA-B Huang and Heck (2015) [21] 86.6% Chisholm and Hachey (2015) [6] 88.7% Guo and Barbosa (2016) [16] 89.0% Globerson et al (2016) [15] 91.0% Yamada et al (2016) [40] 91.5% Ganea and Hofmann (2017) [14] 92.2% Phong and Titov (2018) [37] 93.1% our 94.3%…”

Section: Methodsmentioning

confidence: 99%

Joint Entity Linking with Deep Reinforcement Learning

Fang

Cao

Li³

et al. 2019

The World Wide Web Conference

View full text Add to dashboard Cite

Entity linking is the task of aligning mentions to corresponding entities in a given knowledge base. Previous studies have highlighted the necessity for entity linking systems to capture the global coherence. However, there are two common weaknesses in previous global models. First, most of them calculate the pairwise scores between all candidate entities and select the most relevant group of entities as the nal result. In this process, the consistency among wrong entities as well as that among right ones are involved, which may introduce noise data and increase the model complexity. Second, the cues of previously disambiguated entities, which could contribute to the disambiguation of the subsequent mentions, are usually ignored by previous models. To address these problems, we convert the global linking into a sequence decision problem and propose a reinforcement learning model which makes decisions from a global perspective. Our model makes full use of the previous referred entities and explores the long-term in uence of current selection on subsequent decisions. We conduct experiments on di erent types of datasets, the results show that our model outperforms state-of-the-art systems and has be er generalization performance.

show abstract

“…R@1 Entities AT-Prior 71.9 5.7M AT-Ext 73.3 5.7M Chisholm and Hachey (2015) 80.7 800K He et al (2013) 81.0 1.5M Sun et al (2015) 83.9 818K Yamada et al (2016) 85.2 5.0M Nie et al (2018) 86.4 5.0M Barrena et al (2018) 87.3 523K DEER (this work) 87.0 5.7M to a re-ranking system) or a combination of the two, we include results using the standard BM25 retrieval algorithm (the Gensim implementation 4 ). We found that indexing each entity using its title gave much better results than indexing with the first paragraph text (or the full document text).…”

Section: Systemmentioning

confidence: 99%

Learning Dense Representations for Entity Retrieval

Gillick¹,

Kulkarni²,

Lansing³

et al. 2019

Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

167

View full text Add to dashboard Cite

We show that it is feasible to perform entity linking by training a dual encoder (two-tower) model that encodes mentions and entities in the same dense vector space, where candidate entities are retrieved by approximate nearest neighbor search. Unlike prior work, this setup does not rely on an alias table followed by a re-ranker, and is thus the first fully learned entity retrieval model. We show that our dual encoder, trained using only anchor-text links in Wikipedia, outperforms discrete alias table and BM25 baselines, and is competitive with the best comparable results on the standard TACKBP-2010 dataset. In addition, it can retrieve candidates extremely fast, and generalizes well to a new dataset derived from Wikinews. On the modeling side, we demonstrate the dramatic value of an unsupervised negative mining algorithm for this task.

show abstract

Entity Disambiguation with Web Links

Cited by 68 publications

References 11 publications

Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation

Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation

Joint Entity Linking with Deep Reinforcement Learning

Learning Dense Representations for Entity Retrieval

Contact Info

Product

Resources

About