paper-with-me

홈 › Papers

Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter

2021-05-15 · ACL 2021 5 · Wei Liu, Xiyan Fu, Yue Zhang, Wenming Xiao

Lexicon information and pre-trained models, such as BERT, have been combined to explore Chinese sequence labelling tasks due to their respective strengths. However, existing methods solely fuse lexicon features via a shallow and random initialized sequence layer and do not integrate them into the bottom layers of BERT. In this paper, we propose Lexicon Enhanced BERT (LEBERT) for Chinese sequence labelling, which integrates external lexicon knowledge into BERT layers directly by a Lexicon Adapter layer. Compared with the existing methods, our model facilitates deep lexicon knowledge fusion at the lower layers of BERT. Experiments on ten Chinese datasets of three tasks including Named Entity Recognition, Word Segmentation, and Part-of-Speech tagging, show that LEBERT achieves the state-of-the-art results.

📄 PDF Abstract BibTeX arXiv:2105.07148

Code (1)

liuwei1206/LEBERT 공식 구현 tf

Tasks

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Part-Of-Speech Tagging

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling

2022-10-27 · Peijie Jiang, Dingkun Long, Yanzhao Zhang, Pengjun Xie 외

Boundary information is critical for various Chinese language processing tasks, such as word segmentation, part-of-speech tagging, and named entity recognition. Previous studies usually resorted to the use of a high-qual…

Chinese Named Entity RecognitionChinese Word SegmentationLanguage ModelingLanguage Modelling+3

Entity Enhanced BERT Pre-training for Chinese NER

2020-11-01 · EMNLP 2020 11 · Chen Jia, Yuefeng Shi, Qinrong Yang, Yue Zhang

Character-level BERT pre-trained in Chinese suffers a limitation of lacking lexicon information, which shows effectiveness for Chinese NER. To integrate the lexicon into pre-trained LMs for Chinese NER, we investigate a …

NER

DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling

2021-09-18 · EMNLP 2021 11 · Baojun Wang, Zhao Zhang, Kun Xu, Guang-Yuan Hao 외

Incorporating lexical knowledge into deep learning models has been proved to be very effective for sequence labeling tasks. However, previous works commonly have difficulty dealing with large-scale dynamic lexicons which…

DenoisingTAG

Chinese Sequence Labeling with Semi-Supervised Boundary-Aware Language Model Pre-training

2024-04-08 · Longhui Zhang, Dingkun Long, Meishan Zhang, Yanzhao Zhang 외

Chinese sequence labeling tasks are heavily reliant on accurate word boundary demarcation. Although current pre-trained language models (PLMs) have achieved substantial gains on these tasks, they rarely explicitly incorp…

Language ModelingLanguage ModellingNatural Language Understanding

Simplify the Usage of Lexicon in Chinese NER

2019-08-16 · ACL 2020 6 · Ruotian Ma, Minlong Peng, Qi Zhang, Xuanjing Huang

Recently, many works have tried to augment the performance of Chinese named entity recognition (NER) using word lexicons. As a representative, Lattice-LSTM (Zhang and Yang, 2018) has achieved new benchmark results on sev…

Chinese Named Entity Recognitionnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+1