Semi-supervised sequence tagging with bidirectional language models
Open accessThe DOI matches its Crossref record; 48 of the 51 references it cites were found in a registry or an index.
Abstract
Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks.However, in most cases, the recurrent network that operates on word-level representations to produce context sensitive representations is trained on relatively little labeled data.In this paper, we demonstrate a general semi-supervised approach for adding pretrained context embeddings from bidirectional language models to NLP systems and apply it to sequence labeling tasks.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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Prompt-based methods have shown great power in few-shot setting [199, 200, 70, 72], zero-shot setting [129, 201], and even fully-supervised setting [74, 75].”
From Pre-trained models for natural language processing: A survey (2020) · cites this paper as [200]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“LSTM LMs have been shown to discover high-level semantic and contextual representations that are useful for many natural language processing tasks (18; 13; 19).”
From Incorporating Context into Language Encoding Models for fMRI (2018) · cites this paper as [18]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The key difference between our system and the previous state of the art from Peters et al. (2017) is that we allowed the task model to learn a weighted average of all biLM layers, whereas Peters et al. (2017) only use the top biLM layer.”
From Deep Contextualized Word Representations (2018) · cites this paper as Peters et al., 2017
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
Lafferty, J., McCallum, A., & Pereira, F. C. N. (2001) · ScholarlyCommons (University of Pennsylvania) · Cited by 12,935
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
Cho, K., van Merrienboer, B., Bahdanau, D., & Bengio, Y. (2014) · Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation · doi:10.3115/v1/w14-4012 · Cited by 7,099
Combining labeled and unlabeled data with co-training
Blum, A., & Mitchell, T. (1998) · Proceedings of the eleventh annual conference on Computational learning theory · doi:10.1145/279943.279962 · Cited by 5,495
Recurrent neural network based language model
Mikolov, T., Karafiát, M., Burget, L., Černocký, J., & Khudanpur, S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-343 · Cited by 5,390
Natural Language Processing (almost) from Scratch
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., & Kuksa, P. P. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1103.0398 · Cited by 4,962
Distributed Representations of Sentences and Documents
Le, Q. V., & Mikolov, T. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.4053 · Cited by 4,934
Neural Architectures for Named Entity Recognition
Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., & Dyer, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1030 · Cited by 4,401 · cited 5×
“Our baseline sequence tagging model is a hierarchical neural tagging model, closely following a number of recent studies (Ma and Hovy, 2016; Lample et al., 2016; Yang et al., 2017; Chiu and Nichols, 2016) (left side of Figure 2).”
BackgroundMethodInfluentialLong short-term memory recurrent neural network architectures for large scale acoustic modeling
Sak, H., Senior, A., & Beaufays, F. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-80 · Cited by 2,973
Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition
Tjong Kim Sang, E. F., & De Meulder, F. (2003) · Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - · doi:10.3115/1119176.1119195 · Cited by 2,788
Text classification from labeled and unlabeled documents using EM
Nigam, K., Mccallum, A. K., Thrun, S., & Mitchell, T. (2000) · Machine Learning · doi:10.1023/a:1007692713085 · Cited by 2,736 · cited 2×
“…methods for structured prediction problems include co-training (Blum and Mitchell, 1998; Pierce and Cardie, 2001), expectation maximization (Nigam et al., 2000; Mohit and Hwa, 2005), structural learning (Ando and Zhang, 2005) and maximum discriminant functions (Suzuki et al., 2007; Suzuki…”
MethodA neural probabilistic language model
BengioYoshua, DucharmeRéjean, VincentPascal, & JanvinChristian (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944966 · Cited by 2,644
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
Ma, X., & Hovy, E. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1101 · Cited by 2,567 · cited 12×
“The baseline sequence tagger uses 30 dimensional character embeddings and a CNN with 30 filters of width 3 characters followed by a tanh non-linearity for the token character encoder.”
BackgroundMethodInfluentialNamed Entity Recognition with Bidirectional LSTM-CNNs
Chiu, J. P. C., & Nichols, E. (2016) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00104 · Cited by 1,909
Collins, M. (2002) · Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02 · doi:10.3115/1118693.1118694 · Cited by 1,862
Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition
Sang, E. T. K. (2002) · arXiv (Cornell University) · doi:10.48550/arxiv.cs/0209010 · Cited by 1,560
Design challenges and misconceptions in named entity recognition
Ratinov, L., & Roth, D. (2009) · Proceedings of the Thirteenth Conference on Computational Natural Language Learning - CoNLL '09 · doi:10.3115/1596374.1596399 · Cited by 1,448
Statistical machine translation
(2010) · Choice Reviews Online · doi:10.5860/choice.47-6293 · Cited by 1,309
Kiros, R., Zhu, Y., Salakhutdinov, R., Zemel, R. S., Torralba, A., Urtasun, R., & Fidler, S. (2015) · arXiv · doi:10.48550/arxiv.1506.06726 · Cited by 1,293 · cited 2×
“LM embeddings are related to a class of meth-ods (e.g., Le and Mikolov, 2014; Kiros et al., 2015; Hill et al., 2016) for learning sentence and document encoders from unlabeled data, which can be used for text classification and textual entailment among other tasks.”
BackgroundMethodRecurrent Continuous Translation Models
Kalchbrenner, N., & Blunsom, P. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1176 · Cited by 1,232
One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling
Chelba, C., Mikolov, T., Schuster, M., Ge, Q., Brants, T., Koehn, P., & Robinson, T. (2013) · arXiv · doi:10.48550/arxiv.1312.3005 · Cited by 1,051
Semi-supervised Sequence Learning
Dai, A. M., & Le, Q. V. (2015) · arXiv · doi:10.48550/arxiv.1511.01432 · Cited by 994 · cited 1×
“Dai and Le (2015) pre-trained LSTMs using language models and sequence autoencoders then fine tuned the weights for classification tasks.”
MethodStatistical Machine Translation
Koehn, P. (2009) · Cambridge University Press eBooks · doi:10.1017/cbo9780511815829 · Cited by 871
Visualizing and Understanding Recurrent Networks
Karpathy, A., Johnson, J., & Fei-Fei, L. (2015) · arXiv · doi:10.48550/arxiv.1506.02078 · Cited by 845 · cited 1×
“Karpathy et al. (2015) visualized character level LSTM states and showed that individual cells capture long-range dependencies such as line lengths, quotes and brackets.”
BackgroundExploring the Limits of Language Modeling
Józefowicz, R., Vinyals, O., Schuster, M., Shazeer, N., & Wu, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.02410 · Cited by 823
Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies
Linzen, T., Dupoux, E., & Goldberg, Y. (2016) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00115 · Cited by 737
Introduction to the CoNLL-2000 shared task: chunking
Tjong Kim Sang, E. F., & Buchholz, S. (2000) · Proceedings of the 2nd workshop on Learning language in logic and the 4th conference on Computational natural language learning - · doi:10.3115/1117601.1117631 · Cited by 705
One billion word benchmark for measuring progress in statistical language modeling
Chelba, C., Mikolov, T., Schuster, M., Ge, Q., Brants, T., Koehn, P., & Robinson, T. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-564 · Cited by 627 · cited 3×
“The primary bidirectional LMs we used in this study were trained on the 1B Word Benchmark (Chelba et al., 2014), a publicly available benchmark for large-scale language modeling.”
MethodInfluentialLearning Distributed Representations of Sentences from Unlabelled Data
Hill, F., Cho, K., & Korhonen, A. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1162 · Cited by 566 · cited 2×
“LM embeddings are related to a class of meth-ods (e.g., Le and Mikolov, 2014; Kiros et al., 2015; Hill et al., 2016) for learning sentence and document encoders from unlabeled data, which can be used for text classification and textual entailment among other tasks.”
BackgroundMethodA Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
Hashimoto, K., xiong, C., Tsuruoka, Y., & Socher, R. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1206 · Cited by 535 · cited 5×
“75 improvement in F1 when including supervised labels from the PTB POS tags or CoNLL 2003 entities (Yang et al., 2017; Søgaard and Goldberg, 2016; Hashimoto et al., 2016).”
BackgroundMethodInfluentialcontext2vec: Learning Generic Context Embedding with Bidirectional LSTM
Melamud, O., Goldberger, J., & Dagan, I. (2016) · Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning · doi:10.18653/v1/k16-1006 · Cited by 513
Fast and Robust Neural Network Joint Models for Statistical Machine Translation
Devlin, J., Zbib, R., Huang, Z., Lamar, T., Schwartz, R., & Makhoul, J. (2014) · Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.3115/v1/p14-1129 · Cited by 481 · cited 2×
“Recently, neural LMs (Bengio et al., 2003; Mikolov et al., 2010) have also been integrated in neural machine translation systems (e.g., Kalchbrenner and Blunsom, 2013; Devlin et al., 2014) to score candidate translations.”
BackgroundDeep multi-task learning with low level tasks supervised at lower layers
Søgaard, A., & Goldberg, Y. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p16-2038 · Cited by 445 · cited 4×
“Previous work has explored meth-ods for jointly learning the bidirectional RNN with supplemental labeled data from other tasks (e.g., Søgaard and Goldberg, 2016; Yang et al., 2017).”
MethodResultInfluentialJoint Entity Recognition and Disambiguation
Luo, G., Huang, X., Lin, C.-Y., & Nie, Z. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1104 · Cited by 248
A high-performance semi-supervised learning method for text chunking
Ando, R. K., & Zhang, T. (2005) · Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05 · doi:10.3115/1219840.1219841 · Cited by 223
Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks
Yang, Z., Salakhutdinov, R., & Cohen, W. W. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.06345 · Cited by 194
Limitations of Co-Training for Natural Language Learning from Large Datasets
Pierce, D. R., & Cardie, C. (2001) · Cited by 161
Semi-Supervised Sequential Labeling and Segmentation Using Giga-Word Scale Unlabeled Data
Suzuki, J., & Isozaki, H. (2008) · Cited by 149
Ammar, W., Peters, M. E., Bhagavatula, C., & Power, R. (2017) · International Workshop on Semantic Evaluation (SemEval) · doi:10.18653/v1/s17-2097 · Cited by 70
Self-citationSemi-Supervised Learning and Domain Adaptation in Natural Language Processing
Søgaard, A. (2013) · Synthesis lectures on human language technologies · doi:10.2200/s00497ed1v01y201304hlt021 · Cited by 59
Semi-supervised sequence modeling with syntactic topic models
Li, W., & McCallum, A. (2005) · Cited by 53
Semi-Supervised Structured Output Learning Based on a Hybrid Generative and Discriminative Approach
Suzuki, J., Fujino, A., & Isozaki, H. (2007) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · Cited by 35
Syntax-based semi-supervised named entity tagging
Mohit, B., & Hwa, R. (2005) · doi:10.3115/1225753.1225768 · Cited by 23
A Bidirectional Recurrent Neural Language Model for Machine Translation
Peris, Á., & Casacuberta, F. (2015) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 14
Bidirectional Language Model for Handwriting Recognition
Frinken, V., Fornés, A., Lladós, J., & Ogier, J.-M. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-34166-3_67 · Cited by 8
Research works printed but not linked: 1
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Cor- rado, and Jeff Dean. 2013. Distributed representa- tions of words and phrases and their compositional- ity. In NIPS.
Cited by
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
“ELMo (Peters et al., 2017) generalizes traditional word embedding research along a different dimension.”
BackgroundMethodDeep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
Self-citationKirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., et al. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00371 · Cited by 11,953
Universal Language Model Fine-tuning for Text Classification
Howard, J., & Ruder, S. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1031 · Cited by 4,100
“Recent approaches that concatenate embeddings derived from other tasks with the input at different layers (Peters et al., 2017; McCann et al., 2017; Peters et al., 2018) still train the main task model from scratch and treat pretrained embeddings as fixed parameters, limiting their usefulness.”
BackgroundMethodInfluential
Metadata
- Authors
- Peters, M., Ammar, W., Bhagavatula, C., & Power, R.
- Affiliations
- Allen Institute for Artificial Intelligence (US)
- Venue
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2017
- Pages
- 1756-1765
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W2610748790
- Cited by
- 655
- References
- 51
- Citations by year
- 2026: 5 · 2025: 30 · 2024: 38 · 2023: 68 · 2022: 66 · 2021: 102 · 2020: 116 · 2019: 149 · 2018: 75 · 2017: 6
- FWCI
- 42.23
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- semi-supervised learning, sequence labeling, bidirectional language models, pre-trained word embeddings, context embedding, named entity recognition, chunking, transfer learning, unlabeled text
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.