A Joint Model for Entity Analysis: Coreference, Typing, and                     Linking

Durrett, Greg; Klein, Dan

doi:10.1162/tacl_a_00197

Cited by 206 publications

(180 citation statements)

References 21 publications

Supporting

Mentioning

179

Contrasting

Unclassified

Order By: Relevance

“…We also report the entity extraction results on the OntoNotes 5.0 test set in Table 4. We compare our models with the existing feature-based models Ratinov and Roth (2009) and Durrett and Klein (2014), which both employ heavy feature engineering to bring in external knowledge. BiLSTM-CNN (Chiu and Nichols, 2016) employs a hybrid BiLSTM and Convolutional neural network (CNN) architecture and incorporates rich lexicon features derived from SENNA and DBPedia.…”

Section: Resultsmentioning

confidence: 99%

Leveraging Knowledge Bases in LSTMs for Improving Machine Reading

Yang¹,

Mitchell²

2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers)

223

160

View full text Add to dashboard Cite

This paper focuses on how to take advantage of external knowledge bases (KBs) to improve recurrent neural networks for machine reading. Traditional methods that exploit knowledge from KBs encode knowledge as discrete indicator features. Not only do these features generalize poorly, but they require task-specific feature engineering to achieve good performance. We propose KBLSTM, a novel neural model that leverages continuous representations of KBs to enhance the learning of recurrent neural networks for machine reading. To effectively integrate background knowledge with information from the currently processed text, our model employs an attention mechanism with a sentinel to adaptively decide whether to attend to background knowledge and which information from KBs is useful. Experimental results show that our model achieves accuracies that surpass the previous state-of-the-art results for both entity extraction and event extraction on the widely used ACE2005 dataset.

show abstract

Section: Resultsmentioning

confidence: 99%

Leveraging Knowledge Bases in LSTMs for Improving Machine Reading

Yang¹,

Mitchell²

2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers)

223

160

View full text Add to dashboard Cite

show abstract

“…Regarding the selection of the set of tasks, our work is closest to (Durrett and Klein 2014;Singh et al 2013). Durrett and Klein (2014) combine coreference resolution, entity linking (sometimes referred to as Wikification) and mention detection.…”

Section: Related Workmentioning

confidence: 99%

A Hierarchical Multi-Task Approach for Learning Embeddings from Semantic Tasks

Sanh

Wolf

Ruder

2019

AAAI

181

170

View full text Add to dashboard Cite

Much effort has been devoted to evaluate whether multi-task learning can be leveraged to learn rich representations that can be used in various Natural Language Processing (NLP) down-stream applications. However, there is still a lack of understanding of the settings in which multi-task learning has a significant effect. In this work, we introduce a hierarchical model trained in a multi-task learning setup on a set of carefully selected semantic tasks. The model is trained in a hierarchical fashion to introduce an inductive bias by supervising a set of low level tasks at the bottom layers of the model and more complex tasks at the top layers of the model. This model achieves state-of-the-art results on a number of tasks, namely Named Entity Recognition, Entity Mention Detection and Relation Extraction without hand-engineered features or external NLP tools like syntactic parsers. The hierarchical training supervision induces a set of shared semantic representations at lower layers of the model. We show that as we move from the bottom to the top layers of the model, the hidden states of the layers tend to represent more complex semantic information.

show abstract

“…Entity Linking Durrett and Klein (2014) is the work that is closest to our approach, although not neural. In their approach they model interactions between the MD, CG and ED tasks jointly.…”

Section: Related Workmentioning

confidence: 99%

“…• Entity disambiguation (ED): (typically) a mix of useful coreference and coherence features together with a classifier determine the entity link. Durrett and Klein (2014) were the first to propose jointly modelling MD, CG and ED in a graphical model and could show that each of those steps are interdependent and benefit from a joint objective. Other approaches only model MD and ED jointly (Nguyen et al, 2016;Kolitsas et al, 2018), thus these architectures depend on a CG step after mention detection.…”

Section: Introductionmentioning

confidence: 99%