Robust named entity disambiguation with random walks

By Zhaochen Guo, Denilson Barbosa. 2018

142 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research, Natural Language Processing

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 Natural Language Processing

Citations in the corpus

Autoregressive Entity Retrieval (2020, neutral): “For the out-of-domain scenario, we evaluate on ﬁve test sets: MSNBC, AQUAINT, ACE2004, WNED-CWEB (CWEB) and WNED-WIKI (WIKI) (Gabrilovich et al., 2013; Guo & Barbosa, 2018).”
CM3: A Causal Masked Multimodal Model of the Internet (2022, methodology): “We evaluate on the AIDA-CoNLL dataset for the in-domain scenario and the MSNBC, AQUAINT, ACE2004, WNED-CWEB (CWEB) and WNED-WIKI (WIKI) for the out-of-domain scenario (De Cao et al., 2020; Guo & Barbosa, 2018).”
KILT: a Benchmark for Knowledge Intensive Language Tasks (2020, methodology): “WNED-WIKI (Guo and Barbosa, 2018) is a dataset automatically created by sampling document from the 2013/06/06 Wikipedia dump, and balancing the difﬁculty of linking each mention (using a baseline as proxy).”
Towards Continual Knowledge Learning of Language Models (2021, background): “…OpenDomain Question Answering (Joshi et al., 2017; Kwiatkowski et al., 2019; Fan et al., 2019; Yang et al., 2018), Fact Checking (Thorne et al., 2018), Entity Linking (Hoffart et al., 2011; Guo & Barbosa, 2018), Slot-filling (Levy et al., 2017), and Knowledgeable Open Dialogue (Dinan et al., 2019).”
Deep Joint Entity Disambiguation with Local Neural Attention (2017, background): “…et al., 2016) 87.2 our (local, K=100, R=50) 88.8 Global models (Huang et al., 2015) 86.6 (Ganea et al., 2016) 87.6 (Chisholm and Hachey, 2015) 88.7 (Guo and Barbosa, 2016) 89.0 (Globerson et al., 2016) 91.0 (Yamada et al., 2016) 91.5 our (global) 92.22 ± 0.14 ﬁrst train each entity vector on the…”
Phrase Retrieval Learns Passage Retrieval, Too (2021, unknown): “Entity linking contains three datasets: AIDA CoNLL-YAGO (AY2) (Hoffart et al., 2011), WNED-WIKI (WnWi) (Guo and Barbosa, 2018), and WNED-CWEB (WnCw) (Guo and Barbosa, 2018).”
Collective Entity Disambiguation with Structured Gradient Tree Boosting (2018, methodology): “WIKI and CWEB are automatically annotated datasets built from the ClueWeb and Wikipedia corpora by Guo and Barbosa (2016).”
Improving Entity Linking by Modeling Latent Relations between Mentions (2018, methodology): “…the models trained on AIDA-train, on five popular test sets: MSNBC, AQUAINT, ACE2004, which were cleaned and updated by Guo and Barbosa (2016); WNEDCWEB (CWEB), WNED-WIKI (WIKI), which were automatically extracted from ClueWeb and Wikipedia (Guo and Barbosa, 2016; Gabrilovich et al., 2013).”
Improving Entity Linking by Modeling Latent Entity Type Information (2020, methodology): “Speciﬁcally, we randomly sample 100K entities from Wikipedia, and randomly split them into training set (80K), development set (10K) and test set (10K).”
Entity-aware ELMo: Learning Contextual Entity Representation for Entity Disambiguation (2019, background): “• MSNBC (MSB), AQUAINT (AQ) and ACE2004 (ACE) datasets (Guo and Barbosa, 2016) • WNED-WIKI (WW) and WNED-CWEB (CWEB): These datasets are bigger and are built from the ClueWeb and Wikipedia corpora by (Guo and Barbosa, 2016; Gabrilovich et al., 2013) • TAC 2010 (Hoffart et al., 2011) and TAC 2010…”
Learning Dynamic Context Augmentation for Global Entity Linking (2019, methodology): “However, the DCA-SL model shows poor performance on the CWEB dataset with Size order.”
Joint Entity Linking with Deep Reinforcement Learning (2019, methodology): “ size is 16. In the above two LSTM networks, Table 2: In-KB accuracy result on AIDA-B dataset. Methods 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)”
Boosting Entity Linking Performance by Leveraging Unlabeled Documents (2019, methodology): “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), Glober-son et al. (2016), Yamada et al. (2016), Ganea and Hofmann (2017), Le and Titov (2018).”