Joint Entity Recognition and Disambiguation

By Gang Luo, Xiaojiang Huang, Chin-Yew Lin, Zaiqing Nie. 2015

242 citations recorded by the source corpus.

Extracting named entities in text and linking extracted names to a given knowledge base are fundamental tasks in applications for text understanding. Existing systems typically run a named entity recognition (NER) model to extract entity names first, then run an entity linking model to link extracted names to a knowledge base. NER and linking models are usually trained separately, and the mutual dependency between the two tasks is ignored. We propose JERL, Joint Entity Recognition and Linking, to jointly model NER and linking tasks and capture the mutual dependency between them. It allows the information from each task to improve the performance of the other. To the best of our knowledge, JERL is the first model to jointly optimize NER and linking tasks together completely. In experiments on the CoNLL’03/AIDA data set, JERL outperforms state-of-art NER and linking systems, and we find improvements of 0.4% absolute F1 for NER on CoNLL’03, and 0.36% absolute precision@1 for linking on AIDA.

Subfields: Artificial Intelligence, Information Systems, 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 Information Systems

In Management Science and Operations Research

In Natural Language Processing

Citations in the corpus

Semi-supervised sequence tagging with bidirectional language models (2017, methodology): “s Without With Yang et al. (2017) transfer from CoNLL 2000/PTB-POS 91:2 91:26 +0:06 Chiu and Nichols (2016) with gazetteers 90:91 91:62 +0:71 Collobert et al. (2011) with gazetteers 88:67 89:59 +0:92 Luo et al. (2015) joint with entity linking 89:9 91:2 +1:3 Ours no LM vs TagLM unlabeled data only 9”
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF (2016, methodology): “20)5 reported on CoNLL 2003 data set is by the joint NER and entity linking model (Luo et al., 2015).”
Named Entity Recognition with Bidirectional LSTM-CNNs (2015, methodology): “90.10 - - - Ratinov and Roth (2009)11 91.20 90.50 90.80 82.00 84.95 83.45 Lin and Wu (2009) - - 90.90 - - - Passos et al. (2014)12 - - 90.90 - - 82.24 Durrett and Klein (2014) - - - 85.22 82.89 84.04 Luo et al. (2015)13 91.50 91.40 91.20 - - - Table 4: Results of our models, with various feature set”
Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer (2020, unknown): “…features, followed by feeding them to different linear classi-ﬁers such as maximum entropy, conditional random ﬁelds (CRFs), and support vector machines (Chieu and Ng, 2002; Florian et al., 2003; Finkel et al., 2005; Ratinov and Roth, 2009; Lin and Wu, 2009; Passos et al., 2014; Luo et al., 2015).”
Improving Entity Linking by Modeling Latent Entity Type Information (2020, background): “Speciﬁcally, a line of work (Durrett and Klein 2014; Luo et al. 2015; Nguyen, Theobald, and Weikum 2016) jointly model entity linking and named entity recognition to capture the mutual dependency between them using structured CRF.”
Visual Attention Model for Name Tagging in Multimodal Social Media (2018, background): “…2016; Ma and Hovy, 2016) proposed several neural network architectures for named tagging that outperform traditional explicit features based methods (Chieu and Ng, 2002; Florian et al., 2003; Ando and Zhang, 2005; Ratinov and Roth, 2009; Lin and Wu, 2009; Passos et al., 2014; Luo et al., 2015).”
Knowledge Graphs (2020, unknown): “A common trend, for example, is to combine interdependent tasks, jointly performing WSD and EL [361], or NER and EL [329, 381], or NER and RE [437, 578], etc.”
Deep Neural Architectures for Joint Named Entity Recognition and Disambiguation (2019, background): “[8] are the first to jointly optimize NER and ED.”
GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling (2019, methodology): “More notably, our GCDT surpasses the models that exploit additional task-speciﬁc resources or annotated corpora (Luo et al., 2015; Yang et al., 2017b; Chiu and Nichols, 2016).”
Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme (2017, methodology): “Classical NER models are linear statistical models, such as Hidden Markov Models (HMM) and Conditional Random Fields (CRF) (Passos et al., 2014; Luo et al., 2015).”
End-to-End Neural Entity Linking (2018, methodology): “However, we did not compare with (Luo et al., 2015) and other models outside Gerbil that do not use end-to-end EL metrics.”
Joint Learning of Named Entity Recognition and Entity Linking (2019, background): “Sil and Yates (2013), Luo et al. (2015), and Nguyen et al. (2016) introduced models that do joint learning of NER and EL using hand-engineered features.”
Chinese NER Using Lattice LSTM (2018, methodology): “In particular, lexicon features have been widely used (Collobert et al., 2011; Passos et al., 2014; Huang et al., 2015; Luo et al., 2015).”