Leveraging Document-Level Label Consistency for Named Entity Recognition

Gui, Tao; Ye, Jiacheng; Zhang, Qi; Zhou, Yiming; Gong, Yeyun; Huang, Xuanjing

doi:10.24963/ijcai.2020/550

Cited by 15 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Document-level EMD systems like HIRE-NER [38] utilize this tendency to distill non-local information for each unique token, from the entire scope of the document, using a memory-structure and append them to sentence-level contextual embeddings before an EMD decoder draws final output labels. DocL-NER [39] additionally includes a label refinement network to enforce label consistency across documents and improve EMD results. We compare EMD Globalizer with HIRE-NER [38] to test how effectively global information for EMD is compiled in each system.…”

Section: Related Workmentioning

confidence: 99%

Boosting Entity Mention Detection for Targetted Twitter Streams with Global Contextual Embeddings

Bhowmick¹,

Dragut²,

Meng³

2022

Preprint

View full text Add to dashboard Cite

Microblogging sites, like Twitter, have emerged as ubiquitous sources of information. Two important tasks related to the automatic extraction and analysis of information in Microblogs are Entity Mention Detection (EMD) and Entity Detection (ED). The state-of-the-art EMD systems aim to model the non-literary nature of microblog text by training upon offline static datasets. They extract a combination of surface-level features -orthographic, lexical, and semantic -from individual messages for noisy text modeling and entity extraction. But given the constantly evolving nature of microblog streams, detecting all entity mentions from such varying yet limited context of short messages remains a difficult problem. To this end, we propose a framework named EMD Globalizer, better suited for the execution of EMD learners on microblog streams. It deviates from the processing of isolated microblog messages by existing EMD systems, where learned knowledge from the immediate context of a message is used to suggest entities. Instead, it recognizes that messages within a microblog stream are topically related and often repeat entity mentions, thereby leaving the scope for EMD systems to go beyond the localized processing of individual messages. After an initial extraction of entity candidates by an EMD system, the proposed framework leverages occurrence mining to find additional candidate mentions that are missed during this first detection. Aggregating the local contextual representations of these mentions, a global embedding is drawn from the collective context of an entity candidate within a stream. The global embeddings are then utilized to separate entities within the candidates from false positives. All mentions of said entities from the stream are produced in the framework's final outputs. Our experiments show that EMD Globalizer can enhance the effectiveness of all existing EMD systems that we tested (on average by 25.61%) with a small additional computational overhead.

show abstract

Section: Related Workmentioning

confidence: 99%

Boosting Entity Mention Detection for Targetted Twitter Streams with Global Contextual Embeddings

Bhowmick¹,

Dragut²,

Meng³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…NER with document-level label propagation is usually approached using a two-stage framework [18]- [20]. In the first stage, draft labels for tokens or candidate NEs are predicted by a base model.…”

Section: B Document-level Label Propagation For Named Entity Recognimentioning

confidence: 99%

“…Gui et al [20] introduce a label refinement approach to handle document-level label consistency. In this approach, a key-value memory network is first used to record draft labels predicted by the base model, and then a multi-channel Transformer refines these draft predictions based on the explicit cooccurrence relationship derived from the memory network.…”

Section: B Document-level Label Propagation For Named Entity Recognimentioning

confidence: 99%

Learning Document-Level Label Propagation and Instance Selection by Deep Q-Network for Interactive Named Entity Annotation

Gui

Gao

2021

IEEE Access

View full text Add to dashboard Cite

High quality annotated named entity corpora are essential language resources, but fully manual annotation is time-consuming. Interactive annotation offers an efficient alternative where humans and machines collaborate. Instances of named entity mentions tend to share the same label, when they cooccur in the same document and have similar surface forms. After selecting an instance in one sentence for manual annotation, the label of the instance can be propagated to instances in other sentences. This kind of document-level label propagation can be used to reduce human effort and improve annotation quality in interactive annotation. However, most existing literature assumes instances within different sentences are independent, and ignores document-level label propagation. This paper proposes a reinforcement learningbased approach, which learns to propagate labels among the instances within a document for interactive named entity annotation. In addition, our approach also learns instance selection for manual annotation. We optimize the objective which is a trade-off between human effort and annotation quality by training a deep Q-network. Our approach reduces human effort by more than 42% compared to baseline approaches, for achieving the same annotation quality (0.95 measured by F1 averaged on three datasets).

show abstract

“…Indeed, there exist several attempts to utilize global information besides single sentence for NER [1], [23], [11], [4]. However, these methods still easily fail to achieve the above task due to the following facts.…”

Section: Introductionmentioning

confidence: 99%

“…First, they [1], [23], [4] don't provide a sufficiently effective method to address the potential noise problems while introducing global information. Second, they [1], [23], [11] only utilize extra information at the word-level, but ignore the modeling at the sentence level.…”

Section: Introductionmentioning

confidence: 99%

Exploiting Global Contextual Information for Document-level Named Entity Recognition

Wang,

Wei,

Mao

et al. 2021

Preprint

View full text Add to dashboard Cite

Most existing named entity recognition (NER) approaches are based on sequence labeling models, which focus on capturing the local context dependencies. However, the way of taking one sentence as input prevents the modeling of nonsequential global context, which is useful especially when local context information is limited or ambiguous. To this end, we propose a model called Global Context enhanced Document-level NER (GCDoc) to leverage global contextual information from two levels, i.e., both word and sentence. At word-level, a document graph is constructed to model a wider range of dependencies between words, then obtain an enriched contextual representation for each word via graph neural networks (GNN). To avoid the interference of noise information, we further propose two strategies. First we apply the epistemic uncertainty theory to find out tokens whose representations are less reliable, thereby helping prune the document graph. Then a selective auxiliary classifier is proposed to effectively learn the weight of edges in document graph and reduce the importance of noisy neighbour nodes. At sentence-level, for appropriately modeling wider context beyond single sentence, we employ a cross-sentence module which encodes adjacent sentences and fuses it with the current sentence representation via attention and gating mechanisms. Extensive experiments on two benchmark NER datasets (CoNLL 2003 and Ontonotes 5.0 English dataset) demonstrate the effectiveness of our proposed model. Our model reaches F1 score of 92.22±0.02 (93.40±0.02 with BERT) on CoNLL 2003 dataset and 88.32±0.04 (90.49±0.09 with BERT) on Ontonotes 5.0 dataset, achieving new state-of-the-art performance.

show abstract

Leveraging Document-Level Label Consistency for Named Entity Recognition

Cited by 15 publications

References 14 publications

Boosting Entity Mention Detection for Targetted Twitter Streams with Global Contextual Embeddings

Boosting Entity Mention Detection for Targetted Twitter Streams with Global Contextual Embeddings

Learning Document-Level Label Propagation and Instance Selection by Deep Q-Network for Interactive Named Entity Annotation

Exploiting Global Contextual Information for Document-level Named Entity Recognition

Contact Info

Product

Resources

About