Semi-supervised sequence tagging with bidirectional language models

@inproceedings{Peters2017SemisupervisedST,
  title={Semi-supervised sequence tagging with bidirectional language models},
  author={Matthew E. Peters and Waleed Ammar and Chandra Bhagavatula and R. Power},
  booktitle={ACL},
  year={2017}
}
  • Matthew E. Peters, Waleed Ammar, +1 author R. Power
  • Published in ACL 2017
  • Computer Science
  • Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks. [...] Key Result We evaluate our model on two standard datasets for named entity recognition (NER) and chunking, and in both cases achieve state of the art results, surpassing previous systems that use other forms of transfer or joint learning with additional labeled data and task specific gazetteers.Expand Abstract
    373 Citations
    A Comparison of Architectures and Pretraining Methods for Contextualized Multilingual Word Embeddings
    • 3
    • Highly Influenced
    • PDF
    Improved Dependency Parsing using Implicit Word Connections Learned from Unlabeled Data
    • 19
    • PDF
    Deep contextualized word embeddings from character language models for neural sequence labeling
    • 1
    • Highly Influenced
    Semi-Supervised Sequence Modeling with Cross-View Training
    • 157
    • PDF
    Deep contextualized word representations
    • 5,231
    • PDF
    Empower Sequence Labeling with Task-Aware Neural Language Model
    • 194
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 48 REFERENCES
    context2vec: Learning Generic Context Embedding with Bidirectional LSTM
    • 291
    • PDF
    Semi-Supervised Sequential Labeling and Segmentation Using Giga-Word Scale Unlabeled Data
    • 152
    • PDF
    Semi-Supervised Sequence Modeling with Syntactic Topic Models
    • 66
    • PDF
    Natural Language Processing (Almost) from Scratch
    • 5,849
    • Highly Influential
    • PDF
    Skip-Thought Vectors
    • 1,632
    • PDF
    End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
    • 1,517
    • Highly Influential
    • PDF
    Learning Distributed Representations of Sentences from Unlabelled Data
    • 383
    • PDF
    A Bidirectional Recurrent Neural Language Model for Machine Translation
    • 12
    • PDF
    Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks
    • 232
    • Highly Influential
    • PDF
    A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
    • 377
    • Highly Influential
    • PDF