Better Modeling of Incomplete Annotations for Named Entity Recognition

Jie, Zhanming; Xie, Pengjun; Lu, Wei; Ding, Ruixue; Li, Linlin

doi:10.18653/v1/n19-1079

Cited by 67 publications

(85 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Partial annotation in various forms has also been studied in the contexts of POS-tagging (Mori et al, 2015), word sense disambiguation (Hovy and Hovy, 2012), temporal relation extraction (Ning et al, 2018), dependency parsing (Flannery et al, 2012), and named entity recognition (Jie et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

“…However, this formulation assumes that all possible sequences are equally likely. To address this, Jie et al (2019) introduced a way to weigh sequences.…”

Section: Neural Modelmentioning

confidence: 99%

“…One difference is that Jie et al (2019) use crossvalidation to train, while we follow Chang et al (2007) and retrain with the entire training set at each round. However, the main difference has to do with the focus of each algorithm.…”

Section: Difference From Prior Workmentioning

confidence: 99%

See 2 more Smart Citations

Named Entity Recognition with Partially Annotated Training Data

Mayhew¹,

Chaturvedi²,

Tsai³

et al. 2019

Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

View full text Add to dashboard Cite

Supervised machine learning assumes the availability of fully-labeled data, but in many cases, such as low-resource languages, the only data available is partially annotated. We study the problem of Named Entity Recognition (NER) with partially annotated training data in which a fraction of the named entities are labeled, and all other tokens, entities or otherwise, are labeled as non-entity by default. In order to train on this noisy dataset, we need to distinguish between the true and false negatives. To this end, we introduce a constraintdriven iterative algorithm that learns to detect false negatives in the noisy set and downweigh them, resulting in a weighted training set. With this set, we train a weighted NER model. We evaluate our algorithm with weighted variants of neural and non-neural NER models on data in 8 languages from several language and script families, showing strong ability to learn from partial data. Finally, to show real-world efficacy, we evaluate on a Bengali NER corpus annotated by non-speakers, outperforming the prior state-of-the-art by over 5 points F1.

show abstract

Section: Related Workmentioning

confidence: 99%

“…However, this formulation assumes that all possible sequences are equally likely. To address this, Jie et al (2019) introduced a way to weigh sequences.…”

Section: Neural Modelmentioning

confidence: 99%

See 1 more Smart Citation

Named Entity Recognition with Partially Annotated Training Data

Mayhew¹,

Chaturvedi²,

Tsai³

et al. 2019

Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

View full text Add to dashboard Cite

show abstract

“…This includes statistic methods, such as SVM (Isozaki and Kazawa, 2002), HMMs (Bikel et al, 1997) and CRF (Lafferty et al, 2001), suffering from feature engineering. There are also a number of recent neural network approaches applied to NER, such as (Collobert et al, 2011;Huang et al, 2015;Lample et al, 2016;Ma and Hovy, 2016;Chiu and Nichols, 2016;Akbik et al, 2018;Jie et al, 2019;Akbik et al, 2019 (Bastings et al, 2017;Yao et al, 2019;Wang et al, 2018;Mishra et al, 2019;Cao et al, 2019;Zhang et al, 2019). Cetoli et al (2017) use GCN to investigate the role of the dependency tree in English named entity recognition.…”

Section: Related Workmentioning

confidence: 99%

“…This includes statistic methods, such as SVM (Isozaki and Kazawa, 2002), HMMs (Bikel et al, 1997) and CRF (Lafferty et al, 2001), suffering from feature engineering. There are also a number of recent neural network approaches applied to NER, such as (Collobert et al, 2011;Huang et al, 2015;Lample et al, 2016;Ma and Hovy, 2016;Chiu and Nichols, 2016;Akbik et al, 2018;Jie et al, 2019;Akbik et al, 2019). Compared with English, Chinese is not featured with obvious word boundaries, but it is important to leverage word boundaries and semantic information in Chinese NER.…”

Section: Related Workmentioning

confidence: 99%

Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network

Sui

Chen

Liu

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

136

View full text Add to dashboard Cite

The lack of word boundaries information has been seen as one of the main obstacles to develop a high performance Chinese named entity recognition (NER) system. Fortunately, the automatically constructed lexicon contains rich word boundaries information and word semantic information. However, integrating lexical knowledge in Chinese NER tasks still faces challenges when it comes to self-matched lexical words as well as the nearest contextual lexical words. We present a Collaborative Graph Network to solve these challenges. Experiments on various datasets show that our model not only outperforms the stateof-the-art (SOTA) results, but also achieves a speed that is six to fifteen times faster than that of the SOTA model. 1

show abstract

Serial and Parallel Recurrent Convolutional Neural Networks for Biomedical Named Entity Recognition

Yang

et al. 2019

Database Systems for Advanced Applications

View full text Add to dashboard Cite

In this study, we aim to reduce generation latency for Named Entity Recognition (NER) with Large Language Models (LLMs). The main cause of high latency in LLMs is the sequential decoding process, which autoregressively generates all labels and mentions for NER, significantly increase the sequence length. To this end, we introduce Parallel Decoding in LLM for NER (PaDeLLM-NER), a approach that integrates seamlessly into existing generative model frameworks without necessitating additional modules or architectural modifications. PaDeLLM-NER allows for the simultaneous decoding of all mentions, thereby reducing generation latency. Experiments reveal that PaDeLLM-NER significantly increases inference speed that is 1.76 to 10.22 times faster than the autoregressive approach for both English and Chinese. Simultaneously it maintains the quality of predictions as evidenced by the performance that is on par with the state-of-the-art across various datasets.* Code is available at URL masked for anonymous review.* https://huggingface.co/meta-llama/Llama-2-7b * https://huggingface.co/baichuan-inc/ Baichuan2-7B-Base

show abstract

Better Modeling of Incomplete Annotations for Named Entity Recognition

Cited by 67 publications

References 17 publications

Named Entity Recognition with Partially Annotated Training Data

Named Entity Recognition with Partially Annotated Training Data

Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network

Serial and Parallel Recurrent Convolutional Neural Networks for Biomedical Named Entity Recognition

Contact Info

Product

Resources

About