Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

@inproceedings{Wang2021ImprovingNE,
  title={Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning},
  author={Xinyu Wang and Yong Jiang and Nguyen Bach and Tao Wang and Zhongqiang Huang and Fei Huang and Kewei Tu},
  booktitle={ACL},
  year={2021}
}
Recent advances in Named Entity Recognition (NER) show that document-level contexts can significantly improve model performance. In many application scenarios, however, such contexts are not available. In this paper, we propose to find external contexts of a sentence by retrieving and selecting a set of semantically relevant texts through a search engine, with the original sentence as the query. We find empirically that the contextual representations computed on the retrieval-based input view… 

Figures and Tables from this paper

Parallel Instance Query Network for Named Entity Recognition
TLDR
Parallel Instance Query Network (PIQN) is proposed, which sets up global and learnable instance queries to extract entities from a sentence in a parallel manner and outperforms previous state-of-the-art models.
DAMO-NLP at SemEval-2022 Task 11: A Knowledge-based System for Multilingual Named Entity Recognition
TLDR
DAMO-NLP proposes a knowledge-based system, where it builds a multilingual knowledge base based on Wikipedia to provide related context information to the named entity recognition (NER) model, and effectively retrieves related contexts from the knowledge base.
Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning
TLDR
Thorough experiments on two benchmark datasets labeled by various external knowledge demonstrate the superiority of the proposed Conf-MPU over existing DS-NER methods.
KARL-Trans-NER: Knowledge Aware Representation Learning for Named Entity Recognition using Transformers
TLDR
Experimental results show that the augmentation done using KARL can considerably boost the performance of the NER system and achieve significantly better results than existing approaches in the literature on three publicly available NER datasets, namely coNLL 2003, CoNLL++, and OntoNotes v5.
Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER
TLDR
Results on in-domain learning and domain adaptation show that the model’s performance in low-resource settings can be largely improved with a suitable demonstration strategy, and good demonstration can save many labeled examples and consistency in demonstration contributes to better performance.
TURNER: The Uncertainty-based Retrieval Framework for Chinese NER
TLDR
The idea behind TURNER is to imitate human behavior: the authors frequently retrieve auxiliary knowledge as assistance when encountering an unknown or uncertain entity and it outperforms existing lexiconbased approaches and achieves the new SOTA.
S-NER: A Concise and Efficient Span-Based Model for Named Entity Recognition
TLDR
This work proposes S-NER, a span-based NER model that directly obtains the types of spans by conducting entity type classifications on span semantic representations, which eliminates the requirement for label dependency.
Context-Aware Bidirectional Neural Model for Sindhi Named Entity Recognition
TLDR
A deep context-aware bidirectional long short-term memory (CaBiLSTM) model for the Sindhi NER task that incorporates task-oriented CRL based on joint character-level and word-level representations and employs the CRF for the prediction of label sequences.
Regularization for Long Named Entity Recognition
TLDR
This work proposes a novel debiasing method RegLER to improve predictions for entities of varying lengths, and shows significant improvement over long-named entities that can predict throughdebiasing on conjunction or special characters within entities.
ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition
TLDR
ITA is proposed to align image features into the textual space, so that the attention mechanism in transformer-based pretrained textual embeddings can be better utilized and the MNER model can be more practical in dealing with text-only inputs and robust to noises from images.
...
...

References

SHOWING 1-10 OF 60 REFERENCES
Exploring Cross-sentence Contexts for Named Entity Recognition with BERT
TLDR
It is found that adding context as additional sentences to BERT input systematically increases NER performance, and a straightforward method is proposed, Contextual Majority Voting (CMV), to combine these different predictions and increase N ER performance.
Named Entity Recognition as Dependency Parsing
TLDR
Ideas from graph-based dependency parsing are used to provide the model a global view on the input via a biaffine model and show that the model works well for both nested and flat NER, through evaluation on 8 corpora and achieving SoTA performance on all of them.
LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention
TLDR
New pretrained contextualized representations of words and entities based on the bidirectional transformer, and an entity-aware self-attention mechanism that considers the types of tokens (words or entities) when computing attention scores are proposed.
Pooled Contextualized Embeddings for Named Entity Recognition
TLDR
This work proposes a method in which it dynamically aggregate contextualized embeddings of each unique string that the authors encounter and uses a pooling operation to distill a ”global” word representation from all contextualized instances.
Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing
TLDR
An approach to incorporate retrieved datapoints as supporting evidence for context-dependent semantic parsing, such as generating source code conditioned on the class environment, and shows that both the context-aware retriever and the meta-learning strategy improve accuracy.
Named Entity Recognition for Social Media Texts with Semantic Augmentation
TLDR
A neural-based approach to NER for social media texts where both local and augmented semantics are taken into account, and an attentive semantic augmentation module and a gate module to encode and aggregate such information are proposed.
Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition
TLDR
The goal of this task is to provide a definition of emerging and of rare entities, and based on that, also datasets for detecting these entities and to evaluate the ability of participating entries to detect and classify novel and emerging named entities in noisy text.
Retrieval-Augmented Controllable Review Generation
TLDR
This paper proposes to additionally leverage references, which are selected from a large pool of texts labeled with one of the attributes, as textual information that enriches inductive biases of given attributes.
Semi-Supervised Sequence Modeling with Cross-View Training
TLDR
Cross-View Training (CVT), a semi-supervised learning algorithm that improves the representations of a Bi-LSTM sentence encoder using a mix of labeled and unlabeled data, is proposed and evaluated, achieving state-of-the-art results.
Multi-View Cross-Lingual Structured Prediction with Minimum Supervision
TLDR
This paper proposes a multi-view framework, by leveraging a small number of labeled target sentences, to effectively combine multiple source models into an aggregated source view at different granularity levels (language, sentence, or sub-structure), and transfer it to a target view based on a task-specific model.
...
...