End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
arXiv:1603.01354
Abstract
State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing. In this paper, we introduce a novel neutral network architecture that benefits from both word- and character-level representations automatically, by using combination of bidirectional LSTM, CNN and CRF. Our system is truly end-to-end, requiring no feature engineering or data pre-processing, thus making it applicable to a wide range of sequence labeling tasks. We evaluate our system on two data sets for two sequence labeling tasks --- Penn Treebank WSJ corpus for part-of-speech (POS) tagging and CoNLL 2003 corpus for named entity recognition (NER). We obtain state-of-the-art performance on both the two data --- 97.55\% accuracy for POS tagging and 91.21\% F1 for NER.
arXiv comment10 pages, 3 figures. To appear on ACL 2016
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- ADADELTA: An Adaptive Learning Rate Method
- Natural Language Processing (almost) from Scratch
- On the difficulty of training Recurrent Neural Networks
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
- Transition-Based Dependency Parsing with Stack Long Short-Term Memory
- Harnessing Deep Neural Networks with Logic Rules
- Multi-Task Cross-Lingual Sequence Tagging from Scratch
- Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning
- Probabilistic Models for High-Order Projective Dependency Parsing
- Unsupervised Ranking Model for Entity Coreference Resolution
Cited by in corpus (24)
- OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]
- Soft-Label Dataset Distillation and Text Dataset Distillation
- On the Origin of Deep Learning
- Neural Chinese Named Entity Recognition via CNN-LSTM-CRF and Joint Training with Word Segmentation
- Near-lossless Binarization of Word Embeddings
- End-to-end named entity extraction from speech
- Robust Lexical Features for Improved Neural Network Named-Entity Recognition
- Abstractive Information Extraction from Scanned Invoices (AIESI) using End-to-end Sequential Approach
- Towards Open Intent Discovery for Conversational Text
- Morphological Embeddings for Named Entity Recognition in Morphologically Rich Languages
- DocTag2Vec: An Embedding Based Multi-label Learning Approach for Document Tagging
- Context-Aware Classification of Legal Document Pages
- Application of Pre-training Models in Named Entity Recognition
- Chinese User Service Intention Classification Based on Hybrid Neural Network
- Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition
- Information Extraction from Scientific Literature for Method Recommendation
- Empirical Study of Named Entity Recognition Performance Using Distribution-aware Word Embedding
- Parsing Early Modern English for Linguistic Search
- A Hierarchical Deep Learning Natural Language Parser for Fashion
- Detecting Potential Topics In News Using BERT, CRF and Wikipedia
- De-identification of medical records using conditional random fields and long short-term memory networks
- Syllable-based Neural Named Entity Recognition for Myanmar Language
- ICDM 2020 Knowledge Graph Contest: Consumer Event-Cause Extraction
- Semantic Loss Application to Entity Relation Recognition