“…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)…”
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.
“…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)…”
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.
“…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…”
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.
“…We carried out our experiments in the standard setting but used other (unlabeled) data for training, as described below. We used six test sets: AIDA CoNLL 'testb' (Hoffart et al, 2011) (aka AIDA-B); MSNBC, AQUAINT, ACE2004, cleaned and updated by Guo and Barbosa (2016); CWEB, WIKI, automatically extracted from Clueweb (Guo and Barbosa, 2016;Gabrilovich et al, 2013). We use AIDA CoNLL 'testa' data (aka AIDA-A) as our development set (216 documents).…”
Section: Settingmentioning
confidence: 99%
“…We also compare to recent state-of-the-art systems trained supervisedly on Wikipedia and extra supervision or on AIDA CoNLL: Chisholm and Hachey (2015), Guo and Barbosa (2016), Globerson et al (2016), Yamada et al (2016), Ganea and Hofmann (2017), Le and Titov (2018). Chisholm and Hachey (2015) used supervision in the form of links to Wikipedia from non-Wikipedia pages, Wikilinks (Singh et al, 2012)).…”
Modern entity linking systems rely on large collections of documents specifically annotated for the task (e.g., AIDA CoNLL). In contrast, we propose an approach which exploits only naturally occurring information: unlabeled documents and Wikipedia. Our approach consists of two stages. First, we construct a high recall list of candidate entities for each mention in an unlabeled document. Second, we use the candidate lists as weak supervision to constrain our document-level entity linking model. The model treats entities as latent variables and, when estimated on a collection of unlabelled texts, learns to choose entities relying both on local context of each mention and on coherence with other entities in the document. The resulting approach rivals fully-supervised state-of-the-art systems on standard test sets. It also approaches their performance in the very challenging setting: when tested on a test set sampled from the data used to estimate the supervised systems. By comparing to Wikipedia-only training of our model, we demonstrate that modeling unlabeled documents is beneficial. 1 The best reported in-domain scores are 93.1% F1 (Le and Titov, 2018), whereas the best previous out-of-domain score is only 85.7% F1 (Guo and Barbosa, 2016) (an average over 5 standard out-of-domain test sets, Table 1).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.