Collective Entity Resolution with Multi-Focal Attention

By Amir Globerson, Nevena Lazic, Soumen Chakrabarti, A. Subramanya, Michael Ringgaard, Fernando C Pereira. 2016

107 citations recorded by the source corpus.

Entity resolution is the task of linking each mention of an entity in text to the corresponding record in a knowledge base (KB). Coherence models for entity resolution encourage all referring expressions in a document to resolve to entities that are related in the KB. We explore attention-like mechanisms for coherence, where the evidence for each candidate is based on a small set of strong relations, rather than relations to all other entities in the document. The rationale is that document-wide support may simply not exist for non-salient entities, or entities not densely connected in the KB. Our proposed sys-tem outperforms state-of-the-art systems on the CoNLL 2003, TAC KBP 2010, 2011 and 2012 tasks.

Subfields: Artificial Intelligence, Management Science and Operations Research, Information Extraction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

In Information Extraction

Citations in the corpus

Learning Dense Representations for Entity Retrieval (2019, neutral): “Extensions include joint resolution over all entities in a document (Ratinov et al., 2011; Globerson et al., 2016; Ganea and Hofmann, 2017), joint modeling with related tasks like textual similarity (Yamada et al., 2017b; Barrena et al., 2018) and cross-lingual modeling (Sil et al., 2018), for…”
Deep Joint Entity Disambiguation with Local Neural Attention (2017, methodology): “, 2015) since, as noted also by (Globerson et al., 2016), their mention index artificially includes the gold entity (guaranteed gold recall), which is not a realistic setting.”
Named Entity Disambiguation for Noisy Text (2017, methodology): “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.”
Neural Cross-Lingual Entity Linking (2017, methodology): “The current SOTA for English EL are (Globerson et al. 2016) and (Yamada et al.”
Collective Entity Disambiguation with Structured Gradient Tree Boosting (2018, unknown): “PPRforNED In-KB acc. 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”
DeepType: Multilingual Entity Linking by Neural Type System Evolution (2018, methodology): “EL Disambiguation accuracy is shown in Table 1c, where we compare with recent deep-learning based approaches (Globerson et al. 2016), or recent work by Yamada et al. for embedding word and entities (Yamada et al. 2016), or documents and entities (Yamada et al. 2017), along with count and coherence…”
Entity-aware ELMo: Learning Contextual Entity Representation for Entity Disambiguation (2019, unknown): “7 (Globerson et al., 2016) 92.”
Entity Linking via Joint Encoding of Types, Descriptions, and Context (2017, background): “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…”
Learning What’s Easy: Fully Differentiable Neural Easy-First Taggers (2017, methodology): “Others have proposed alternatives to softmax attention, including the sparsemax (Martins and Astudillo, 2016) and multi-focal attention (Globerson et al., 2016).”
Learning Text Representations for 500K Classification Tasks on Named Entity Disambiguation (2018, methodology): “Note that, contrary to us, many high-performing systems use in-domain training data (Ganea and Hofmann, 2017; Glober-son et al., 2016), and/or external candidates and link counts when building the dictionary (Lazic et al., 2015; Globerson et al., 2016; Yamada et al., 2016).”
Learning Dynamic Context Augmentation for Global Entity Linking (2019, background): “Many studies (Ratinov et al., 2011; Globerson et al., 2016; Yamada et al., 2016; Ganea and Hofmann, 2017; Le and Titov, 2018) obtain Φg by calculating all”
Improving Entity Linking by Modeling Latent Entity Type Information (2020, methodology): “model of Ganea and Hofmann (2017) are obtained from DeepED7. For each entity, we randomly sam7https://github.com/dalab/deep-ed/ Methods AIDA-B Local models prior p^(ejm) 71.9 Lazic et al. (2015) 86.4 Globerson et al. (2016) 87.9 Yamada et al. (2016) 87.2 Ganea and Hofmann (2017) 88.8 Ganea and Hofma”
Boosting Entity Linking Performance by Leveraging Unlabeled Documents (2019, methodology): “Exact MAP (or max marginal) inference, needed both at training and testing time, is NP-hard (Wainwright et al., 2008 is computationally efﬁcient and has been shown effective in the supervised setting by Globerson et al. (2016).”
Mention and Entity Description Co-Attention for Entity Disambiguation (2018, methodology): “(Globerson et al. 2016) apply an attention mechanism to select coherent entities using sparse features.”
Learning Distributed Representations of Texts and Entities from Knowledge Base (2017, background): “• Globerson (Globerson et al., 2016) improved the coherence model for EL by introducing an attention mechanism in order to focus only on strong relations of entities.”