Plato: A Selective Context Model for Entity                     Resolution

Lazic, Nevena; Subramanya, Amarnag; Ringgaard, Michael; Pereira, Fernando

doi:10.1162/tacl_a_00154

Cited by 59 publications

(82 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…for each i ∈ {1, ..., n} (Bunescu and Paşca, 2006;Lazic et al, 2015;Yamada et al, 2017). A global model, besides using local context within Ψ(e i , c i ), takes into account entity coherency.…”

Section: Local and Global Modelsmentioning

confidence: 99%

“…NEL methods typically consider only coreference, relying either on off-the-shelf systems or some simple heuristics (Lazic et al, 2015), and exploit them in a pipeline fashion, though some (e.g., Cheng and Roth (2013); Ren et al (2017)) additionally exploit a range of syntactic-semantic relations such as apposition and possessives. Another line of work ignores relations altogether and models the predicted sequence of KB entities as a bag (Globerson et al, 2016;Yamada et al, 2016;Ganea and Hofmann, 2017).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Entity Linking by Modeling Latent Relations between Mentions

Le¹,

Titov²

2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

178

200

View full text Add to dashboard Cite

Entity linking involves aligning textual mentions of named entities to their corresponding entries in a knowledge base. Entity linking systems often exploit relations between textual mentions in a document (e.g., coreference) to decide if the linking decisions are compatible. Unlike previous approaches, which relied on supervised systems or heuristics to predict these relations, we treat relations as latent variables in our neural entity-linking model. We induce the relations without any supervision while optimizing the entity-linking system in an end-to-end fashion. Our multirelational model achieves the best reported scores on the standard benchmark (AIDA-CoNLL) and substantially outperforms its relation-agnostic version. Its training also converges much faster, suggesting that the injected structural bias helps to explain regularities in the training data.

show abstract

Section: Local and Global Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving Entity Linking by Modeling Latent Relations between Mentions

Le¹,

Titov²

2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

178

200

View full text Add to dashboard Cite

show abstract

“…(2011a)). This is also true of the only other method which, like ours, uses a combination of Wikipedia data and unlabeled texts (Lazic et al, 2015). We will refer to approaches using this form of supervision, including our approach, as Wikipedia-based linkers.…”

Section: Introductionmentioning

confidence: 84%

“…The resulting model is significantly less accurate than the one which used unlabeled documents. The score difference is larger (Chisholm and Hachey, 2015) 84.9 ------Wiki + unlab (Lazic et al, 2015) 86. (Chisholm and Hachey, 2015) 88.7 ------Fully-supervised (Wiki + AIDA CoNLL train) (Guo and Barbosa, 2016) 89.0 92 87 88 77 84.5 85.7 (Globerson et al, 2016) 91.0 ------ (Yamada et al, 2016) 91. for AIDA-CoNLL test set than for the other 5 test sets.…”

Section: Analysis and Ablationsmentioning

confidence: 99%

Boosting Entity Linking Performance by Leveraging Unlabeled Documents

Le¹,

Titov²

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

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).

show abstract

“…Though we experimented with local models, the local-global distinction is largely orthogonal as we can directly integrate coherence modeling components in our DL approach. Different types of supervision have been considered in previous work: full supervision (Yamada et al, 2017;Ganea and Hofmann, 2017;Le and Titov, 2018), using combinations of labeled and unlabeled data (Lazic et al, 2015), and even distant supervision (Fan et al, 2015). The approach of Fan et al (2015) is heavily Wikipediabased: they rely on a heuristic mapping from Freebase entities to Wikipedia entities, and learn features from Wikipedia articles.…”

Section: Related Workmentioning

confidence: 99%