End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
Open accessThe DOI matches its Crossref record; 64 of the 65 references it cites were found in a registry or an index.
Abstract
State-of-the-art sequence labeling systems traditionally require large amounts of taskspecific knowledge in the form of handcrafted 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 preprocessing, 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 datasets -97.55% accuracy for POS tagging and 91.21% F1 for NER.
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 cited source says what the claim attributes to it.
In the citing paper
“Empirically, for those token [81] or span [30] prediction tasks (e.g., NER), prompt decomposition can be considered, while for those span relation prediction [66] tasks (e.g., entity coreference), prompts composition would be a better choice.”
From Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing (2023) · cites this paper as [81]
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 · cited 2×
“Recently, recurrent neural networks (RNN) (Goller and Kuchler, 1996), together with its variants such as long-short term memory (LSTM) (Hochreiter and Schmidhuber, 1997; Gers et al., 2000) and gated recurrent unit (GRU) (Cho et al., 2014), have shown great success in modeling sequential data.”
BackgroundAdam: 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 · cited 1×
“glove/ trained on 6 billion words from Wikipedia and web text (Pennington et al., 2014)”
Background(2014) · Cited by 33,419
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 · cited 2×
“, 2011), and Google’s Word2Vec 300 dimensional embeddings3 trained on 100 billion words from Google News (Mikolov et al., 2013).”
BackgroundDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“To test the effectiveness of pretrained word embeddings, we experimented with randomly initialized embeddings with 100 dimensions, where embeddings are uniformly sampled from range [ − where dim is the dimension of embeddings (He et al., 2015).”
Method(2010) · Cited by 14,134
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
Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891 · cited 2×
“We first use convolutional neural networks (CNNs) (LeCun et al., 1989) to encode character-level information of a word into its character-level representation.”
MethodSpeech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 4×
“Several RNN-based neural network models have been proposed to solve sequence labeling tasks like speech recognition (Graves et al., 2013), POS tagging (Huang et al., 2015) and NER (Chiu and Nichols, 2015; Hu et al., 2016), achieving competitive performance against traditional models.”
MethodInfluentialLearning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542 · cited 2×
“Though, in theory, RNNs are capable to capturing long-distance dependencies, in practice, they fail due to the gradient varnishing/exploding problems (Bengio et al., 1994; Pascanu et al., 2012).”
BackgroundBuilding a Large Annotated Corpus of English: The Penn Treebank
Marcus, M. (1993) · doi:10.21236/ada273556 · Cited by 7,405
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
ADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322 · cited 2×
“We explored other more sophisticated optimization algorithms such as AdaDelta (Zeiler, 2012), Adam (Kingma and Ba, 2014) or RMSProp (Dauphin et al.”
MethodNatural 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 · cited 12×
“This is consistent with results reported by previous work (Collobert et al., 2011; Huang et al., 2015; Chiu and Nichols, 2015).”
MethodResultInfluentialLearning to forget: Continual prediction with LSTM
Gers, F. A., Schmidhuber, J., & Cummins, F. (2000) · Neural Computation · doi:10.1162/089976600300015015 · Cited by 4,823 · cited 1×
“It should be noted that we do not include peephole connections (Gers et al., 2003) in the our LSTM formulation.”
BackgroundNeural 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 2×
“, 2015) and NER (Chiu and Nichols, 2015; Lample et al., 2016), achieving competitive performance against traditional models.”
BackgroundMethodOn the difficulty of training recurrent neural networks
Pascanu, R., Mikolov, T., & Bengio, Y. (2012) · arXiv · doi:10.48550/arxiv.1211.5063 · Cited by 4,310 · cited 1×
“Though, in theory, RNNs are capable to capturing long dependencies, in practice, they fail due to the gradient varnishing/exploding problems (Bengio et al., 1994; Pascanu et al., 2012).”
BackgroundIntroduction 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
Learning to forget: continual prediction with LSTM
Gers, F. A. (1999) · 9th International Conference on Artificial Neural Networks: ICANN '99 · doi:10.1049/cp:19991218 · Cited by 2,337
Named 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 · cited 10×
“Among these neural architectures, the three approaches most similar to our model are the BLSTM-CRF model proposed by Huang et al. (2015), the LSTM-CNNs model by Chiu and Nichols (2015) and the BLSTM-CRF by Lample et al. (2016).”
BackgroundMethodResultInfluentialA Fast and Accurate Dependency Parser using Neural Networks
Chen, D., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1082 · Cited by 1,795 · cited 1×
“…(NLP) systems, like syntactic parsing (Nivre and Scholz, 2004; McDonald et al., 2005; Koo and Collins, 2010; Ma and Zhao, 2012a; Ma and Zhao, 2012b; Chen and Manning, 2014; Ma and Hovy, 2015) and entity coreference resolution (Ng, 2010; Ma et al., 2016), are becoming more sophisticated, in part…”
BackgroundIntroduction 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
An Empirical Exploration of Recurrent Network Architectures
Józefowicz, R., Zaremba, W., & Sutskever, I. (2015) · International Conference on Machine Learning · Cited by 1,459
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 · cited 1×
“Most traditional high performance sequence labeling models are linear statistical models, including Hidden Markov Models (HMM) and Conditional Random Fields (CRF) (Ratinov and Roth, 2009; Passos et al., 2014; Luo et al., 2015), which rely heavily on hand-crafted features and task-specific resources.”
BackgroundA Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data
Ando, R. K., & Zhang, T. (2005) · doi:10.5555/1046920.1194905 · Cited by 1,311
Overfitting in Neural Nets: Backpropagation, Conjugate Gradient, and Early Stopping
Caruana, R., Lawrence, S., & Giles, C. L. (2000) · Cited by 906
Online large-margin training of dependency parsers
McDonald, R., Crammer, K., & Pereira, F. (2005) · Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05 · doi:10.3115/1219840.1219852 · Cited by 791
Learning task-dependent distributed representations by backpropagation through structure
Goller, C., & Kuchler, A. (2002) · Proceedings of International Conference on Neural Networks (ICNN'96) · doi:10.1109/icnn.1996.548916 · Cited by 581
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
Dyer, C., Ballesteros, M., Ling, W., Matthews, A., & Smith, N. A. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1033 · Cited by 553 · cited 1×
“An elegant solution whose effectiveness has been proven by previous work (Dyer et al., 2015) is bi-directional LSTM (BLSTM).”
BackgroundHarnessing Deep Neural Networks with Logic Rules
Hu, Z., Ma, X., Liu, Z., Hovy, E., & Xing, E. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1228 · Cited by 545 · cited 7×
“Huang et al. (2015) used BLSTM for word-level representations and CRF for jointly label decoding, which is similar to our model.”
MethodResultInfluentialSelf-citationFinding Function in Form: Compositional Character Models for Open Vocabulary Word Representation
Ling, W., Dyer, C., Black, A. W., Trancoso, I., Fermandez, R., Amir, S., Marujo, L., & Luis, T. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1176 · Cited by 541 · cited 1×
“A similar model has also been applied to Spanish and Portuguese NER (dos Santos et al., 2015) Ling et al. (2015) and Yang et al. (2016) also used BSLTM to compose character embeddings to word’s representation, which is similar to Lample et al. (2016).”
MethodLearning Character-level Representations for Part-of-Speech Tagging
dos Santos, C., & Zadrozny, B. (2014) · Cited by 519
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
Dyer, C., Ballesteros, M., Ling, W., Matthews, A., & Smith, N. A. (2015) · RECERCAT (Consorci de Serveis Universitaris de Catalunya) · doi:10.48550/arxiv.1505.08075 · Cited by 470 · cited 1×
“An elegant solution whose effectiveness has been proven by previous work (Dyer et al., 2015) is bi-directional LSTM (BLSTM).”
BackgroundSang, E. F. T. K., & Veenstra, J. (1999) · Proceedings of the ninth conference on European chapter of the Association for Computational Linguistics - · doi:10.3115/977035.977059 · Cited by 456
Part-of-Speech Tagging from 97% to 100%: Is It Time for Some Linguistics?
Manning, C. D. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-19400-9_14 · Cited by 408 · cited 1×
“In order to compare with previous work, we adopt the standard splits — section 0-18 as training data, section 1921 as development data and section 22-24 as test data (Manning, 2011; Søgaard, 2011).”
MethodNamed entity recognition through classifier combination
Florian, R., Ittycheriah, A., Jing, H., & Zhang, T. (2003) · Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - · doi:10.3115/1119176.1119201 · Cited by 399
Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings
Peng, N., & Dredze, M. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1064 · Cited by 394
Equilibrated adaptive learning rates for non-convex optimizationPreprint
Dauphin, Y., de Vries, H., & Bengio, Y. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.04390 · Cited by 389
SVMTool: A general POS Tagger Generator Based on Support Vector Machines
Giménez, J., & Màrquez, L. (2004) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/52pkqry5zu2h · Cited by 339
Supervised Noun Phrase Coreference Research: The First Fifteen Years
Ng, V. (2010) · Cited by 318
Boosting Named Entity Recognition with Neural Character Embeddings
dos Santos, C., & Guimarães, V. (2015) · Proceedings of the Fifth Named Entity Workshop · doi:10.18653/v1/w15-3904 · Cited by 309
Named entity recognition: a maximum entropy approach using global information
Chieu, H. L., & Ng, H. T. (2002) · Proceedings of the 19th international conference on Computational linguistics - · doi:10.3115/1072228.1072253 · Cited by 309
Lexicon Infused Phrase Embeddings for Named Entity Resolution
Passos, A., Kumar, V., & McCallum, A. (2015) · Cited by 277
Joint 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 · cited 6×
“20)5 reported on CoNLL 2003 data set is by the joint NER and entity linking model (Luo et al., 2015).”
BackgroundMethodInfluentialPeng, N., & Dredze, M. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p16-2025 · Cited by 230 · cited 1×
“Peng and Dredze (2016) Improved NER for Chinese Social Media with Word Segmentation.”
BackgroundPhrase clustering for discriminative learning
Lin, D., & Wu, X. (2009) · Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - ACL-IJCNLP '09 · doi:10.3115/1690219.1690290 · Cited by 226
Deterministic dependency parsing of English text
Nivre, J., & Scholz, M. (2004) · Proceedings of the 20th international conference on Computational Linguistics - COLING '04 · doi:10.3115/1220355.1220365 · Cited by 220 · cited 1×
“Natural language processing (NLP) systems, like syntactic parsing (Nivre and Scholz, 2004; McDonald et al., 2005; Koo and Collins, 2010; Ma and Zhao, 2012a; Ma and Zhao, 2012b; Chen and Manning, 2014; Ma and Hovy, 2015) and entity coreference resolution (Ng, 2010; Ma et al., 2016), are becoming…”
BackgroundEfficient Third-Order Dependency Parsers
Koo, T., & Collins, M. (2010) · Cited by 206
(2015) · arXiv (Cornell University) · Cited by 182
Multi-Task Cross-Lingual Sequence Tagging from Scratch
Yang, Z., Salakhutdinov, R., & Cohen, W. W. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.06270 · Cited by 178 · cited 1×
“A similar model has also been applied to Spanish and Portuguese NER (dos Santos et al., 2015) Ling et al. (2015) and Yang et al. (2016) also used BSLTM to compose character embeddings to word’s representation, which is similar to Lample et al. (2016).”
MethodGuided Learning for Bidirectional Sequence Classification
Shen, L., Satta, G., & Joshi, A. K. (2007) · Cited by 158
Lexicon Infused Phrase Embeddings for Named Entity Resolution
Passos, A., Kumar, V., & McCallum, A. (2014) · Conference on Computational Natural Language Learning · doi:10.3115/v1/w14-1609 · Cited by 130 · cited 1×
“Most traditional high performance sequence labeling models are linear statistical models, including Hidden Markov Models (HMM) and Conditional Random Fields (CRF) (Ratinov and Roth, 2009; Passos et al., 2014; Luo et al., 2015), which rely heavily on hand-crafted features and taskspecific resources.”
BackgroundSemi-supervised condensed nearest neighbor for part-of-speech tagging
Søgaard, A. (2011) · Research at the University of Copenhagen (University of Copenhagen) · Cited by 88
Ma, X., & Xia, F. (2014) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.3115/v1/p14-1126 · Cited by 85 · cited 1×
“However, such task-specific knowledge is costly to develop (Ma and Xia, 2014), making sequence labeling models difficult to adapt to new tasks or new domains.”
BackgroundSelf-citationDai, H.-J., Lai, P., Chang, Y., & Tsai, R. T. (2015) · Journal of Cheminformatics · doi:10.1186/1758-2946-7-s1-s14 · Cited by 72 · cited 1×
“We use the BIOES tagging scheme instead of standard BIO2, as previous studies have reported meaningful improvement with this scheme (Ratinov and Roth, 2009; Dai et al., 2015; Lample et al., 2016).”
MethodFourth-Order Dependency Parsing
Ma, X., & Zhao, H. (2012) · International Conference on Computational Linguistics · Cited by 66
Self-citationStructure Regularization for Structured Prediction
Sun, X. (2014) · neural information processing systems · Cited by 63
Non-lexical neural architecture for fine-grained POS Tagging
Labeau, M., Löser, K., & Allauzen, A. (2015) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d15-1025 · Cited by 62
Unsupervised Ranking Model for Entity Coreference Resolution
Ma, X., Liu, Z., & Hovy, E. H. (2016) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n16-1116 · Cited by 21 · cited 2×
“, 2005; Koo and Collins, 2010; Ma and Zhao, 2012a; Ma and Zhao, 2012b; Chen and Manning, 2014; Ma and Hovy, 2015) and entity coreference resolution (Ng, 2010; Ma et al., 2016), are becoming more sophisticated, in part because of utilizing output information of POS tagging or NER systems.”
BackgroundSelf-citationProbabilistic Models for High-Order Projective Dependency ParsingPreprint
Ma, X., & Zhao, H. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.04174 · Cited by 9 · cited 1×
“…language processing (NLP) systems, like syntactic parsing (Nivre and Scholz, 2004; McDonald et al., 2005; Koo and Collins, 2010; Ma and Zhao, 2012a; Ma and Zhao, 2012b; Chen and Manning, 2014; Ma and Hovy, 2015) and entity coreference resolution (Ng, 2010; Ma et al., 2016), are becoming more…”
Self-citationEfficient Inner-to-outer Greedy Algorithm for Higher-order Labeled Dependency Parsing
Ma, X., & Hovy, E. H. (2015) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d15-1154 · Cited by 8 · cited 1×
“…parsing (Nivre and Scholz, 2004; McDonald et al., 2005; Koo and Collins, 2010; Ma and Zhao, 2012a; Ma and Zhao, 2012b; Chen and Manning, 2014; Ma and Hovy, 2015) and entity coreference resolution (Ng, 2010; Ma et al., 2016), are becoming more sophisticated, in part because of utilizing…”
BackgroundSelf-citationUnsupervised Ranking Model for Entity Coreference ResolutionPreprint
Ma, X., Liu, Z., & Hovy, E. H. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.04553 · Cited by 8 · cited 2×
“, 2005; Koo and Collins, 2010; Ma and Zhao, 2012a; Ma and Zhao, 2012b; Chen and Manning, 2014; Ma and Hovy, 2015) and entity coreference resolution (Ng, 2010; Ma et al., 2016), are becoming more sophisticated, in part because of utilizing output information of POS tagging or NER systems.”
BackgroundSelf-citation(2015) · doi:10.4230/oasics.slate.2021.8 · Cited by 1 · cited 9×
“Huang et al. (2015) used BLSTM for word-level representations and CRF for jointly label decoding, which is similar to our model.”
BackgroundMethodResultInfluential
Research works printed but not linked: 6
- [3]3. James Bergstra, Olivier Breuleux, Frédéric Bastien, Pascal Lamblin, Razvan Pascanu, Guillaume Des- jardins, Joseph Turian, David Warde-Farley, and Yoshua Bengio. 2010. Theano: a cpu and gpu math expression compiler. In Proceedings of the Python for scientific computing conference (SciPy), volume 4, page 3. Austin, TX.
- [15]15. Felix A Gers, Nicol N Schraudolph, and Jürgen Schmidhuber. 2003. Learning precise timing with lstm recurrent networks. The Journal of Machine Learning Research, 3:115-143.
- [37]37. Xuezhe Ma and Hai Zhao. 2012a. Fourth-order depen- dency parsing. In Proceedings of COLING 2012: Posters, pages 785-796, Mumbai, India, December.
- [43]43. 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 Advances in neural information processing systems, pages 3111-3119.
- [58]58. Erik F. Tjong Kim Sang and Jorn Veenstra. 1999. Rep- resenting text chunks. In Proceedings of EACL'99, pages 173-179. Bergen, Norway.
- [59]59. Kristina Toutanova, Dan Klein, Christopher D Man- ning, and Yoram Singer. 2003. Feature-rich part- of-speech tagging with a cyclic dependency net- work. In Proceedings of NAACL-HLT-2003, Volume 1, pages 173-180.
Cited by
Deep 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
“Similar to WSD, the biLM representations are competitive with carefully tuned, task specific biLSTMs (Ling et al., 2015; Ma and Hovy, 2016).”
MethodLiu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023) · ACM Computing Surveys · doi:10.1145/3560815 · Cited by 4,361
Contextual String Embeddings for Sequence Labeling
Akbik, A., Blythe, D. A. J., & Vollgraf, R. (2018) · International Conference on Computational Linguistics · Cited by 1,716
A Survey on Deep Learning for Named Entity Recognition
Li, J., Sun, A., Han, J., & Li, C. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2981314 · Cited by 1,567
“In addition, GloVe [96], [97] and fastText [98] are also widely used in NER tasks.”
BackgroundMethodInfluentialChinese NER Using Lattice LSTM
Zhang, Y., & Yang, J. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1144 · Cited by 878
“The current stateof-the-art for English NER has been achieved by using LSTM-CRF models (Lample et al., 2016; Ma and Hovy, 2016; Chiu and Nichols, 2016; Liu et al., 2018) with character information being integrated into word representations.”
BackgroundMethodInfluential
Metadata
- Authors
- Ma, X., & Hovy, E.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2016
- Pages
- 1064-1074
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W2962902328
- Cited by
- 2,567
- References
- 65
- Citations by year
- 2026: 63 · 2025: 120 · 2024: 153 · 2023: 271 · 2022: 291 · 2021: 408 · 2020: 424 · 2019: 434 · 2018: 280 · 2017: 96 · 2016: 26
- FWCI
- 150.15
- 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)
- Funders
- Defense Advanced Research Projects Agency (FA8750, FA8750-12-2-0342)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Handwritten Text Recognition Techniques
- Keywords
- sequence labeling, end-to-end learning, bidirectional LSTM, convolutional neural networks, conditional random fields, part-of-speech tagging, named entity recognition, CoNLL-2003
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.