---
title: "Linguistically-Informed Self-Attention for Semantic Role Labeling"
description: "The authors present LISA, a Transformer-style encoder that reads raw tokens once. 3.5 F1 on Brown. 65 references, cited by 195 papers here."
authors: ["Emma Strubell", "Patrick Verga", "Daniel Andor", "David Weiss", "Andrew McCallum"]
year: 2018
venue: "arXiv:1804.08199"
source: "https://arxiv.org/abs/1804.08199"
doi: "10.48550/arxiv.1804.08199"
arxiv: "1804.08199"
licence: "arXiv — non-exclusive licence to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/strubell-2018-linguistically-informed-self-attention-semantic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/strubell-2018-linguistically-informed-self-attention-semantic/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2018](https://md.research.elamur.ai/free/en/papers/2018/) / Linguistically-Informed Self-Attention for Semantic Role Labeling

# Linguistically-Informed Self-Attention for Semantic Role Labeling

**Authors:** [Emma Strubell](https://md.research.elamur.ai/free/en/authors/emma-strubell/), [Patrick Verga](https://md.research.elamur.ai/free/en/authors/patrick-verga/), [Daniel Andor](https://md.research.elamur.ai/free/en/authors/daniel-andor/), [David Weiss](https://md.research.elamur.ai/free/en/authors/david-weiss/) and [Andrew McCallum](https://md.research.elamur.ai/free/en/authors/andrew-mccallum/) · **Year:** 2018 · **Venue:** [arXiv:1804.08199](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2018](https://md.research.elamur.ai/free/en/venues/emnlp/2018/)) · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1804.08199) · [PDF](https://arxiv.org/pdf/1804.08199) · [DOI 10.48550/arxiv.1804.08199](https://doi.org/10.48550/arxiv.1804.08199) · [arXiv 1804.08199](https://arxiv.org/abs/1804.08199) · [OpenAlex](https://openalex.org/W2798638375)

**Citations:** 406 citations (OpenAlex, 2026-10-14) · [195](https://md.research.elamur.ai/free/en/papers/strubell-2018-linguistically-informed-self-attention-semantic/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Semantic role labeling (SRL) identifies who did what to whom in a sentence. The strongest neural SRL systems of the time ignored syntax, although earlier work showed that gold trees could help a lot. The authors present LISA, a Transformer-style encoder that reads raw tokens once. It learns four tasks together: POS tagging, predicate detection, dependency parsing and SRL. Syntax enters the network directly: one self-attention head is replaced by a Dozat and Manning biaffine parser, which is trained to point each token at its syntactic head. An earlier layer predicts POS and predicates as a single combined label. A bilinear scorer then assigns BIO role tags for every predicate at once. Because the parse head acts as an interface, a stronger external parse can be plugged in at test time without retraining. On CoNLL-2005 and CoNLL-2012, LISA beats the syntax-free state of the art, with the largest gains on out-of-domain Brown text. The work shows that explicit syntax still helps neural SRL when it is built in carefully.

## Key points
- On CoNLL-2005 with predicted predicates and GloVe-type embeddings, LISA gains 2.5 F1 on WSJ and more than 3.5 F1 on Brown, nearly 10% error reduction. On CoNLL-2012 it gains more than 2.5 F1.
- With ELMo, LISA still beats the previous best by nearly 1.0 F1 on news and by more than 2.0 F1 out of domain. On CoNLL-2012, a gold parse still adds about 4 F1 even with ELMo.
- Predicate detection reaches 98.4 F1 on WSJ, 93.7 on Brown and 97.2 on CoNLL-12. On Brown it outperforms He et al. (2017) by 1.5–2 F1.
- LISA's internal GloVe parser has a UAS comparable to spaCy (94.48 UAS reported by spaCy). The standalone D&M parser scores higher, and injecting D&M parses improves SRL.
- Error analysis shows that most of the gap to gold parses comes from span boundary errors. About 50% of these corrections involve PP attachment, and that share stays the same even with correct attachments.

## Interesting ideas
- One attention head is trained to put its weight on each token's syntactic parent, so the tree becomes an explicit, inspectable channel inside the network rather than something left implicit.
- The parse is consumed through a fixed interface, so a better parser can be swapped in at inference with no retraining of the role labeler.
- POS and predicate-hood are predicted as one combined label, because the two are strongly correlated and sharing them simplifies training.
- Each sentence is encoded once, and every predicate is scored against all tokens with a bilinear predicate×role function, instead of re-encoding the sentence per predicate.
- Errors are diagnosed with oracle fixes (fix labels, merge/split spans) and by grouping sentences by whether each parser was fully correct, with a gold-parse run as an upper bound.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (tree): gparse could expose a parent-attention head whose argmax is the UD head, which keeps the transformer parser's structure readable and checkable against the perceptron parser.
- **I2** (frames): prag's role assignment should read only the UD tree, so that each upgrade to the parsers or their silver consensus improves frames automatically.
- **I3** (tokens): the tagger in crate en could emit a "verb-is-predicate" flag together with the tag, giving frames a cheap, early predicate list.
- **I4** (frames): the VerbNet role scorer could handle all predicates of a sentence in one pass, which is cheaper and keeps the frames consistent with each other.
- **I5** (learn): the evaluation harness could add gold-tree upper bounds and oracle-fix breakdowns, to show whether a frame error comes from the tree (e.g. PP attachment) or from role logic.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Google](https://md.research.elamur.ai/free/en/companies/google/) — Company, Mountain View, United States · 353 works · 364,806 citations
- [University of Massachusetts Amherst](https://md.research.elamur.ai/free/en/universities/university-of-massachusetts-amherst/) — University, Amherst Center, United States · 67 works · 64,591 citations
- [University of Minnesota](https://md.research.elamur.ai/free/en/universities/university-of-minnesota/) — University, Minneapolis, United States · 9 works · 1,833 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

🧭 Topics (1): [🎭 Semantic role labeling](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/) · 132 works

💡 Concepts (1): [🎭 Semantic role labeling](https://md.research.elamur.ai/free/en/concepts/semantic-role-labeling/) · 30 works

## Cite

Cite as: Emma Strubell, Patrick Verga, Daniel Andor, David Weiss and Andrew McCallum. 2018. Linguistically-Informed Self-Attention for Semantic Role Labeling. arXiv:1804.08199.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{strubell2018linguistically,
  title = {{Linguistically-Informed Self-Attention for Semantic Role Labeling}},
  author = {Emma Strubell, Patrick Verga, Daniel Andor, David Weiss and Andrew McCallum},
  year = {2018},
  doi = {10.48550/arxiv.1804.08199},
  eprint = {1804.08199},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1804.08199}
}
```

- [← previous Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism](https://md.research.elamur.ai/free/en/papers/zeng-2018-extracting-relational-facts-end-end/)
- [next → Transformation Networks for Target-Oriented Sentiment Classification](https://md.research.elamur.ai/free/en/papers/li-2018-transformation-networks-target-oriented-sentiment/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/)

## References

65 references, 31 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Martın Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et al. 2015. Tensorflow: Large-scale machine learning on heterogeneous systems, 2015. Software available from tensorflow.org. [find](https://scholar.google.com/scholar?q=Mart%C4%B1n+Abadi%2C+Ashish+Agarwal%2C+Paul+Barham%2C+Eugene+Brevdo%2C+Zhifeng+Chen%2C+Craig+Citro%2C+Greg+S+Corrado%2C+Andy+Davis%2C+Jeffrey+Dean%2C+Matthieu+Devin%2C+et+al%2E+2015%2E+Tensorflow%3A+Large%2Dscale+machine+learning+on+)
2. Héctor Martı́nez Alonso and Barbara Plank. 2017. When is multitask learning effective? semantic sequence prediction under varying data conditions. In EACL. [↗](https://doi.org/10.48550/arxiv.1612.02251)
3. Miguel Ballesteros, Yoav Goldberg, Chris Dyer, and Noah A. Smith. 2016. Training with exploration improves a greedy stack lstm parser. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2005–2010. [↗](https://doi.org/10.48550/arxiv.1603.03793)
4. Marzieh Bazrafshan and Daniel Gildea. 2013. Semantic roles for string to tree machine translation. In ACL. [find](https://scholar.google.com/scholar?q=Marzieh+Bazrafshan+and+Daniel+Gildea%2E+2013%2E+Semantic+roles+for+string+to+tree+machine+translation%2E+In+ACL%2E)
5. Samy Bengio, Oriol Vinyals, Navdeep Jaitly, and Noam Shazeer. 2015. Scheduled sampling for sequence prediction with recurrent neural networks. In NIPS. [↗](https://doi.org/10.48550/arxiv.1506.03099)
6. Yoshua Bengio, Patrice Simard, and Paolo Frasconi. 1994. Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2):157–166. [↗](https://doi.org/10.1109/72.279181)
7. Jonathan Berant, Vivek Srikumar, Pei-Chun Chen, Brad Huang, Christopher D. Manning, Abby Vander Linden, Brittany Harding, and Peter Clark. 2014. [Modeling biological processes for reading comprehension](https://md.research.elamur.ai/free/en/papers/berant-2014-modeling-biological-processes-reading-comprehension/). In EMNLP.
8. Joachim Bingel and Anders Søgaard. 2017. [Identifying beneficial task relations for multi-task learning in deep neural networks](https://md.research.elamur.ai/free/en/papers/bingel-2017-identifying-beneficial-task-relations-multi/). In EACL.
9. Xavier Carreras and Lluı́s Màrquez. 2005. [Introduction to the conll-2005 shared task: Semantic role labeling](https://md.research.elamur.ai/free/en/papers/carreras-2005-introduction-conll-2005-shared-task/). In CoNLL.
10. Rich Caruana. 1993. Multitask learning: a knowledge-based source of inductive bias. In ICML. [↗](https://doi.org/10.1016/b978-1-55860-307-3.50012-5)
11. Kai-Wei Chang, Akshay Krishnamurthy, Alekh Agarwal, Hal Daumé III, and John Langford. 2015. Learning to search better than your teacher. In ICML. [↗](https://doi.org/10.48550/arxiv.1502.02206)
12. Yun-Nung Chen, William Yang Wang, and Alexander I Rudnicky. 2013. Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame-semantic parsing. In Proc. of ASRU-IEEE. [find](https://scholar.google.com/scholar?q=Yun%2DNung+Chen%2C+William+Yang+Wang%2C+and+Alexander+I+Rudnicky%2E+2013%2E+Unsupervised+induction+and+filling+of+semantic+slots+for+spoken+dialogue+systems+using+frame%2Dsemantic+parsing%2E+In+Proc%2E+of+ASRU%2DIEEE%2E)
13. Jinho D. Choi and Martha Palmer. 2011. Getting the most out of transition-based dependency parsing. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: short papers, pages 687–692. [find](https://scholar.google.com/scholar?q=Jinho+D%2E+Choi+and+Martha+Palmer%2E+2011%2E+Getting+the+most+out+of+transition%2Dbased+dependency+parsing%2E+In+Proceedings+of+the+49th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%3A+short+pa)
14. Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. [Natural language processing (almost) from scratch](https://md.research.elamur.ai/free/en/papers/collobert-2011-natural-language-processing-almost-scratch/). Journal of Machine Learning Research, 12(Aug):2493–2537.
15. Hal Daumé III, John Langford, and Daniel Marcu. 2009. Search-based structured prediction. Machine Learning, 75(3):297–325. [↗](https://doi.org/10.1007/s10994-009-5106-x)
16. Timothy Dozat. 2016. Incorporating nesterov momentum into adam. In ICLR Workshop track. [find](https://scholar.google.com/scholar?q=Timothy+Dozat%2E+2016%2E+Incorporating+nesterov+momentum+into+adam%2E+In+ICLR+Workshop+track%2E)
17. Timothy Dozat and Christopher D. Manning. 2017. [Deep biaffine attention for neural dependency parsing](https://md.research.elamur.ai/free/en/papers/dozat-2016-deep-biaffine-attention-neural-dependency/). In ICLR.
18. Nicholas FitzGerald, Oscar Täckström, Kuzman Ganchev, and Dipanjan Das. 2015. Semantic role labeling with neural network factors. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 960–970. [find](https://scholar.google.com/scholar?q=Nicholas+FitzGerald%2C+Oscar+Ta%CC%88ckstro%CC%88m%2C+Kuzman+Ganchev%2C+and+Dipanjan+Das%2E+2015%2E+Semantic+role+labeling+with+neural+network+factors%2E+In+Proceedings+of+the+2015+Conference+on+Empirical+Methods+in+Natura)
19. W. N. Francis and H. Kučera. 1964. Manual of information to accompany a standard corpus of present-day edited american english, for use with digital computers. Technical report, Department of Linguistics, Brown University, Providence, Rhode Island. [find](https://scholar.google.com/scholar?q=W%2E+N%2E+Francis+and+H%2E+Kuc%CC%8Cera%2E+1964%2E+Manual+of+information+to+accompany+a+standard+corpus+of+present%2Dday+edited+american+english%2C+for+use+with+digital+computers%2E+Technical+report%2C+Department+of+Linguis)
20. Yoav Goldberg and Joakim Nivre. 2012. A dynamic oracle for arc-eager dependency parsing. In Proceedings of COLING 2012: Technical Papers, pages 959–976. [find](https://scholar.google.com/scholar?q=Yoav+Goldberg+and+Joakim+Nivre%2E+2012%2E+A+dynamic+oracle+for+arc%2Deager+dependency+parsing%2E+In+Proceedings+of+COLING+2012%3A+Technical+Papers%2C+pages+959%E2%80%93976%2E)
21. Kazuma Hashimoto, Caiming Xiong, Yoshimasa Tsuruoka, and Richard Socher. 2017. [A joint many-task model: Growing a neural network for multiple nlp tasks](https://md.research.elamur.ai/free/en/papers/hashimoto-2016-joint-many-task-model-growing/). In Conference on Empirical Methods in Natural Language Processing.
22. Luheng He, Kenton Lee, Omer Levy, and Luke Zettlemoyer. 2018. [Jointly predicting predicates and arguments in neural semantic role labeling](https://md.research.elamur.ai/free/en/papers/he-2018-jointly-predicting-predicates-arguments-neural/). In ACL.
23. Luheng He, Kenton Lee, Mike Lewis, and Luke Zettlemoyer. 2017. [Deep semantic role labeling: What works and whats next](https://md.research.elamur.ai/free/en/papers/he-2017-deep-semantic-role-labeling-what/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.
24. Richard Johansson and Pierre Nugues. 2008. [Dependency-based semantic role labeling of propbank](https://md.research.elamur.ai/free/en/papers/johansson-2008-dependency-based-semantic-role-labeling/). In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 69–78.
25. Diederik Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference for Learning Representations (ICLR), San Diego, California, USA. [↗](https://doi.org/10.48550/arxiv.1412.6980)
26. Eliyahu Kiperwasser and Yoav Goldberg. 2016. [Simple and accurate dependency parsing using bidirectional LSTM feature representations](https://md.research.elamur.ai/free/en/papers/kiperwasser-2016-simple-accurate-dependency-parsing-bidirectional/). Transactions of the Association for Computational Linguistics, 4:313–327. [↗](https://doi.org/10.1162/tacl_a_00101)
27. Thomas N. Kipf and Max Welling. 2017. Semisupervised classification with graph convolutional networks. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Thomas+N%2E+Kipf+and+Max+Welling%2E+2017%2E+Semisupervised+classification+with+graph+convolutional+networks%2E+In+International+Conference+on+Learning+Representations%2E)
28. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017. [End-to-end neural coreference resolution](https://md.research.elamur.ai/free/en/papers/lee-2017-end-end-neural-coreference-resolution/). In EMNLP. [↗](https://doi.org/10.18653/v1/d17-1018)
29. Beth Levin. 1993. English verb classes and alternations: A preliminary investigation. University of Chicago press. [find](https://scholar.google.com/scholar?q=Beth+Levin%2E+1993%2E+English+verb+classes+and+alternations%3A+A+preliminary+investigation%2E+University+of+Chicago+press%2E)
30. Mike Lewis, Luheng He, and Luke Zettlemoyer. 2015. Joint A* CCG Parsing and Semantic Role Labeling. In EMNLP. [find](https://scholar.google.com/scholar?q=Mike+Lewis%2C+Luheng+He%2C+and+Luke+Zettlemoyer%2E+2015%2E+Joint+A%2A+CCG+Parsing+and+Semantic+Role+Labeling%2E+In+EMNLP%2E)
31. Ding Liu and Daniel Gildea. 2010. Semantic role features for machine translation. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING). [find](https://scholar.google.com/scholar?q=Ding+Liu+and+Daniel+Gildea%2E+2010%2E+Semantic+role+features+for+machine+translation%2E+In+Proceedings+of+the+23rd+International+Conference+on+Computational+Linguistics+%28COLING%29%2E)
32. Yang Liu and Mirella Lapata. 2018. [Learning structured text representations](https://md.research.elamur.ai/free/en/papers/liu-2018-learning-structured-text-representations/). Transactions of the Association for Computational Linguistics, 6:63–75. [↗](https://doi.org/10.1162/tacl_a_00005)
33. Andrew L. Maas, Awni Y. Hannun, and Andrew Y. Ng. 2013. Rectifier nonlinearities improve neural network acoustic models. In ICML, volume 30. [find](https://scholar.google.com/scholar?q=Andrew+L%2E+Maas%2C+Awni+Y%2E+Hannun%2C+and+Andrew+Y%2E+Ng%2E+2013%2E+Rectifier+nonlinearities+improve+neural+network+acoustic+models%2E+In+ICML%2C+volume+30%2E)
34. Diego Marcheggiani, Anton Frolov, and Ivan Titov. 2017. [A simple and accurate syntax-agnostic neural model for dependency-based semantic role labeling](https://md.research.elamur.ai/free/en/papers/marcheggiani-2017-simple-accurate-syntax-agnostic-neural/). In CoNLL.
35. Diego Marcheggiani and Ivan Titov. 2017. [Encoding sentences with graph convolutional networks for semantic role labeling](https://md.research.elamur.ai/free/en/papers/marcheggiani-2017-encoding-sentences-graph-convolutional-networks/). In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP).
36. Mitchell P. Marcus, Mary Ann Marcinkiewicz, and Beatrice Santorini. 1993. [Building a large annotated corpus of English: The Penn TreeBank](https://md.research.elamur.ai/free/en/papers/marcus-1993-building-large-annotated-corpus-english/). Computational Linguistics – Special issue on using large corpora: II, 19(2):313–330. [↗](https://doi.org/10.21236/ada273556)
37. Marie-Catherine de Marneffe and Christopher D. Manning. 2008. [The stanford typed dependencies representation](https://md.research.elamur.ai/free/en/papers/marneffe-2008-stanford-typed-dependencies-representation/). In COLING 2008 Workshop on Cross-framework and Cross-domain Parser Evaluation.
38. Yurii Nesterov. 1983. A method of solving a convex programming problem with convergence rate o(1/k 2 ). volume 27, pages 372–376. [find](https://scholar.google.com/scholar?q=Yurii+Nesterov%2E+1983%2E+A+method+of+solving+a+convex+programming+problem+with+convergence+rate+o%281%2Fk+2+%29%2E+volume+27%2C+pages+372%E2%80%93376%2E)
39. Martha Palmer, Daniel Gildea, and Paul Kingsbury. 2005. [The proposition bank: An annotated corpus of semantic roles](https://md.research.elamur.ai/free/en/papers/palmer-2005-proposition-bank-annotated-corpus-semantic/). Computational Linguistics, 31(1). [↗](https://doi.org/10.1162/0891201053630264)
40. Razvan Pascanu, Tomas Mikolov, and Yoshua Bengio. 2013. On the difficulty of training recurrent neural networks. In Proceedings of the 30 th International Conference on Machine Learning. [↗](https://doi.org/10.48550/arxiv.1211.5063)
41. Hao Peng, Sam Thomson, and Noah A. Smith. 2017. [Deep multitask learning for semantic dependency parsing](https://md.research.elamur.ai/free/en/papers/peng-2017-deep-multitask-learning-semantic-dependency/). In ACL.
42. Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. [Glove: Global vectors for word representation](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/). In EMNLP.
43. Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. [Deep contextualized word representations](https://md.research.elamur.ai/free/en/papers/peters-2018-deep-contextualized-word-representations/). In NAACL.
44. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Hwee Tou Ng, Anders Björkelund, Olga Uryupina, Yuchen Zhang, and Zhi Zhong. 2013. Towards robust linguistic analysis using OntoNotes. In Proceedings of the Seventeenth Conference on Computational Natural Language Learning, pages 143– 152. [find](https://scholar.google.com/scholar?q=Sameer+Pradhan%2C+Alessandro+Moschitti%2C+Nianwen+Xue%2C+Hwee+Tou+Ng%2C+Anders+Bjo%CC%88rkelund%2C+Olga+Uryupina%2C+Yuchen+Zhang%2C+and+Zhi+Zhong%2E+2013%2E+Towards+robust+linguistic+analysis+using+OntoNotes%2E+In+Proceedings)
45. Sameer Pradhan, Wayne Ward, Kadri Hacioglu, James Martin, and Dan Jurafsky. 2005. Semantic role labeling using different syntactic views. In Proceedings of the Association for Computational Linguistics 43rd annual meeting (ACL). [find](https://scholar.google.com/scholar?q=Sameer+Pradhan%2C+Wayne+Ward%2C+Kadri+Hacioglu%2C+James+Martin%2C+and+Dan+Jurafsky%2E+2005%2E+Semantic+role+labeling+using+different+syntactic+views%2E+In+Proceedings+of+the+Association+for+Computational+Linguistic)
46. Vasin Punyakanok, Dan Roth, and Wen-Tau Yih. 2008. [The importance of syntactic parsing and inference in semantic role labeling](https://md.research.elamur.ai/free/en/papers/punyakanok-2008-importance-syntactic-parsing-inference-semantic/). Computational Linguistics, 34(2):257–287. [↗](https://doi.org/10.1162/coli.2008.34.2.257)
47. Stéphane Ross, Geoffrey J. Gordon, and J. Andrew Bagnell. 2011. A reduction of imitation learning and structured prediction to no-regret online learning. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS). [↗](https://doi.org/10.1184/r1/6550949)
48. Michael Roth and Mirella Lapata. 2016. [Neural semantic role labeling with dependency path embeddings](https://md.research.elamur.ai/free/en/papers/roth-2016-neural-semantic-role-labeling-dependency/). In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL), pages 1192–1202. [↗](https://doi.org/10.48550/arxiv.1605.07515)
49. Anders Søgaard and Yoav Goldberg. 2016. [Deep multi-task learning with low level tasks supervised at lower layers](https://md.research.elamur.ai/free/en/papers/sogaard-2016-deep-multi-task-learning-low/). In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 231–235.
50. Nitish Srivastava, Geoffrey E Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. Journal of machine learning research, 15(1):1929–1958. [find](https://scholar.google.com/scholar?q=Nitish+Srivastava%2C+Geoffrey+E+Hinton%2C+Alex+Krizhevsky%2C+Ilya+Sutskever%2C+and+Ruslan+Salakhutdinov%2E+2014%2E+Dropout%3A+a+simple+way+to+prevent+neural+networks+from+overfitting%2E+Journal+of+machine+learning+re)
51. Mihai Surdeanu, Lluı́s Màrquez, Xavier Carreras, and Pere R. Comas. 2007. Combination strategies for semantic role labeling. Journal of Artificial Intelligence Research, 29:105–151. [↗](https://doi.org/10.1613/jair.2088)
52. Charles Sutton and Andrew McCallum. 2005. Joint parsing and semantic role labeling. In CoNLL. [↗](https://doi.org/10.21236/ada439390)
53. Swabha Swayamdipta, Sam Thomson, Chris Dyer, and Noah A. Smith. 2017. [Frame-semantic parsing with softmax-margin segmental rnns and a syntactic scaffold](https://md.research.elamur.ai/free/en/papers/swayamdipta-2017-frame-semantic-parsing-softmax-margin/). In arXiv:1706.09528. [↗](https://arxiv.org/abs/1706.09528)
54. Oscar Täckström, Kuzman Ganchev, and Dipanjan Das. 2015. [Efficient inference and structured learning for semantic role labeling](https://md.research.elamur.ai/free/en/papers/tackstrom-2015-efficient-inference-structured-learning-semantic/). TACL, 3:29–41. [↗](https://doi.org/10.1162/tacl_a_00120)
55. Zhixing Tan, Mingxuan Wang, Jun Xie, Yidong Chen, and Xiaodong Shi. 2018. [Deep semantic role labeling with self-attention](https://md.research.elamur.ai/free/en/papers/tan-2017-deep-semantic-role-labeling-self/). In AAAI.
56. Kristina Toutanova, Aria Haghighi, and Christopher D. Manning. 2008. [A global joint model for semantic role labeling](https://md.research.elamur.ai/free/en/papers/toutanova-2008-global-joint-model-semantic-role/). Computational Linguistics, 34(2):161–191. [↗](https://doi.org/10.1162/coli.2008.34.2.161)
57. Kristina Toutanova, Dan Klein, Christopher D Manning, and Yoram Singer. 2003. [Feature-rich part-of-speech tagging with a cyclic dependency network](https://md.research.elamur.ai/free/en/papers/toutanova-2003-feature-rich-part-speech-tagging/). In Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology-Volume 1, pages 173–180. Association for Computational Linguistics.
58. Gokhan Tur, Dilek Hakkani-Tür, and Ananlada Chotimongkol. 2005. Semi-supervised learning for spoken language understanding using semantic role labeling. In ASRU. [find](https://scholar.google.com/scholar?q=Gokhan+Tur%2C+Dilek+Hakkani%2DTu%CC%88r%2C+and+Ananlada+Chotimongkol%2E+2005%2E+Semi%2Dsupervised+learning+for+spoken+language+understanding+using+semantic+role+labeling%2E+In+ASRU%2E)
59. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In 31st Conference on Neural Information Processing Systems (NIPS).
60. Hai Wang, Mohit Bansal, Kevin Gimpel, and David McAllester. 2015. Machine comprehension with syntax, frames, and semantics. In ACL. [find](https://scholar.google.com/scholar?q=Hai+Wang%2C+Mohit+Bansal%2C+Kevin+Gimpel%2C+and+David+McAllester%2E+2015%2E+Machine+comprehension+with+syntax%2C+frames%2C+and+semantics%2E+In+ACL%2E)
61. R. J. Williams and D. Zipser. 1989. A learning algorithm for continually running fully recurrent neural networks. Neural computation, 1(2):270–280. [↗](https://doi.org/10.1162/neco.1989.1.2.270)
62. Daniel Zeman, Martin Popel, Milan Straka, Jan Hajic, Joakim Nivre, Filip Ginter, Juhani Luotolahti, Sampo Pyysalo, Slav Petrov, Martin Potthast, et al. 2017. [Conll 2017 shared task: Multilingual parsing from raw text to universal dependencies](https://md.research.elamur.ai/free/en/papers/zeman-2017-conll-2017-shared-task-multilingual/). In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 1–19, Vancouver, Canada. Association for Computational Linguistics.
63. Yuan Zhang and David Weiss. 2016. Stack-propagation: Improved representation learning for syntax. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1557–1566. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yuan+Zhang+and+David+Weiss%2E+2016%2E+Stack%2Dpropagation%3A+Improved+representation+learning+for+syntax%2E+In+Proceedings+of+the+54th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+)
64. Jie Zhou and Wei Xu. 2015. [End-to-end learning of semantic role labeling using recurrent neural networks](https://md.research.elamur.ai/free/en/papers/zhou-2015-end-end-learning-semantic-role/). In Proc. of the Annual Meeting of the Association for Computational Linguistics (ACL). Greedy F1 81.99 83.37 86.57 Viterbi F1 82.24 83.58 86.81 ∆ F1 +0.25 +0.21 +0.24
65. CoNLL-2005 LISA +D&M +Gold CoNLL-2012 LISA +D&M +Gold Greedy F1 80.11 81.55 85.94 Viterbi F1 80.70 82.05 86.43 ∆ F1 +0.59 +0.50 +0.49 Table 7 : Comparison of development F1 scores with and without Viterbi decoding at test time. F1 LISA +D&M +Gold 0-10 11-20 21-30 31-40 Sentence length (tokens) Figure 5 : F1 score as a function of sentence length. [find](https://scholar.google.com/scholar?q=CoNLL%2D2005+LISA+%2BD%26M+%2BGold+CoNLL%2D2012+LISA+%2BD%26M+%2BGold+Greedy+F1+80%2E11+81%2E55+85%2E94+Viterbi+F1+80%2E70+82%2E05+86%2E43+%E2%88%86+F1+%2B0%2E59+%2B0%2E50+%2B0%2E49+Table+7+%3A+Comparison+of+development+F1+scores+with+and+without+Vit)

*Updated 24 October 2026*