The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Deep Semantic Role Labeling: What Works and What’s Next
Open accessAbstract
We introduce a new deep learning model for semantic role labeling (SRL) that significantly improves the state of the art, along with detailed analyses to reveal its strengths and limitations.We use a deep highway BiLSTM architecture with constrained decoding, while observing a number of recent best practices for initialization and regularization.Our 8-layer ensemble model achieves 83.2 F1 on the CoNLL 2005 test set and 83.4 F1 on CoNLL 2012, roughly a 10% relative error reduction over the previous state of the art.Extensive empirical analysis of these gains show that (1) deep models excel at recovering long-distance dependencies but can still make surprisingly obvious errors, and (2) that there is still room for syntactic parsers to improve these results.
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.
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
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
ADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322
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
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 1×
“Ensembling We use a product of experts (Hinton, 2002) to combine predictions of 5 models, each trained on 80% of the training corpus and validated on the remaining 20%.”
Method(1999) · Cited by 1,521
Srivastava, R. K., Greff, K., & Schmidhuber, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1507.06228 · Cited by 1,246
A theoretically grounded application of dropout in recurrent neural networks
Gal, Y., & Ghahramani, Z. (2016) · Cambridge University Engineering Department Publications Database · Cited by 1,089
Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
Saxe, A., McClelland, J. L., & Ganguli, S. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1312.6120 · Cited by 931
A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
Gal, Y., & Ghahramani, Z. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.05287 · Cited by 766
Introduction to the CoNLL-2005 shared task: semantic role labeling
Carreras, X., & Màrquez, L. (2005) · Proceedings of the Ninth Conference on Computational Natural Language Learning - CONLL '05 · doi:10.3115/1706543.1706571 · Cited by 642
Introduction to the CoNLL-2004 Shared Task: Semantic Role Labeling
Carreras, X., & Màrquez, L. (2004) · Cited by 395
The Importance of Syntactic Parsing and Inference in Semantic Role Labeling
Punyakanok, V., Roth, D., & Yih, W.-T. (2008) · Computational Linguistics · doi:10.1162/coli.2008.34.2.257 · Cited by 391
(2013) · Iris (University of Trento) · Cited by 360
End-to-end learning of semantic role labeling using recurrent neural networks
Zhou, J., & Xu, W. (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/p15-1109 · Cited by 333
Highway long short-term memory RNNS for distant speech recognition
Zhang, Y., Chen, G., Yu, D., Yao, K., Khudanpur, S., & Glass, J. (2016) · 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2016.7472780 · Cited by 290
Shparberg, A. L. (2023) · The Charleston Advisor · doi:10.5260/chara.24.3.41 · Cited by 260
Neural Semantic Role Labeling with Dependency Path Embeddings
Roth, M., & Lapata, M. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1113 · Cited by 170
Generalized inference with multiple semantic role labeling systems
Koomen, P., Punyakanok, V., Roth, D., et al. (2005) · doi:10.3115/1706543.1706576 · Cited by 127
Semantic Role Labeling with Neural Network Factors
FitzGerald, N., Täckström, O., Ganchev, K., & Das, D. (2015) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d15-1112 · Cited by 127
Choe, D. K., & Eugene Charniak, D. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1257 · Cited by 101
Kummerfeld, J. K., Hall, D., Curran, J., & Klein, D. (2012) · Cited by 82
Efficient Inference and Structured Learning for Semantic Role Labeling
Täckström, O., Ganchev, K., & Das, D. (2015) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00120 · Cited by 81
PropBank Annotation Guidelines
Bonial, C., Babko-Malaya, O., Choi, J. D., & Hwang, J. D. (2010) · Cited by 76
Semantic role chunking combining complementary syntactic views
Pradhan, S., Hacıoğlu, K., Ward, W., Martin, J., & Jurafsky, D. S. (2005) · Conference on Computational Natural Language Learning · doi:10.3115/1706543.1706585 · Cited by 72
Multilingual Joint Parsing of Syntactic and Semantic Dependencies with a Latent Variable Model
Henderson, J., Merlo, P., Titov, I., & Musillo, G. (2013) · Computational Linguistics · doi:10.1162/coli_a_00158 · Cited by 67
Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs
Swayamdipta, S., Ballesteros, M., Dyer, C., & Smith, N. A. (2016) · Conference on Computational Natural Language Learning · doi:10.18653/v1/k16-1019 · Cited by 52
Global Neural CCG Parsing with Optimality Guarantees
Lee, K., Lewis, M., & Zettlemoyer, L. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1262 · Cited by 46
Self-citationChinese Semantic Role Labeling with Bidirectional Recurrent Neural Networks
Wang, Z., Jiang, T., Chang, B., & Sui, Z. (2015) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d15-1186 · Cited by 42
A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling
Marcheggiani, D., Frolov, A., & Titov, I. (2017) · Conference on Computational Natural Language Learning · doi:10.18653/v1/k17-1041 · Cited by 42
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
Self-citationRecent Trends in Deep Learning Based Natural Language Processing [Review Article]
Young, T., Hazarika, D., Poria, S., & Cambria, E. (2018) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2018.2840738 · Cited by 2,921
AllenNLP: A Deep Semantic Natural Language Processing Platform
Gardner, M., Grus, J., Neumann, M., Tafjord, O., Dasigi, P., Liu, N. F., Peters, M., Schmitz, M., & Zettlemoyer, L. (2018) · Proceedings of Workshop for NLP Open Source Software (NLP-OSS) · doi:10.18653/v1/w18-2501 · Cited by 1,252
Self-citationRecent Trends in Deep Learning Based Natural Language Processing
Young, T., Hazarika, D., Poria, S., & Cambria, E. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.02709 · Cited by 1,192
Neural Motifs: Scene Graph Parsing with Global Context
Zellers, R., Yatskar, M., Thomson, S., & Choi, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00611 · Cited by 1,052
Metadata
- Authors
- He, L., Lee, K., Lewis, M., & Zettlemoyer, L.
- Venue
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2017
- Pages
- 473-483
- OpenAlex
- W2740765036
- Cited by
- 420
- References
- 29
- FWCI
- 35.95
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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.