Low-Resource Semantic Role Labeling

Gormley, Matthew R.; Durme, Benjamin Van; Dredze, Mark

doi:10.3115/v1/p14-1111

Cited by 14 publications

(13 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…present a model (which we call RL-SPINN) that is identical to SPINN at test time, but uses the REINFORCE algorithm (Williams, 1992) at training time to compute gradients for the transition classification function, which produces discrete decisions and does not otherwise receive gradients through backpropagation. Surprisingly, and in contrast to Gormley et al (2014), they find that a small 100D instance of this RL-SPINN model performs somewhat better on several text classification tasks than an otherwise-identical model which is explicitly trained to parse.…”

Section: Introductionmentioning

confidence: 69%

Do latent tree learning models identify meaningful structure in sentences?

Williams

Drozdov

Bowman

2018

TACL

124

View full text Add to dashboard Cite

Recent work on the problem of latent tree learning has made it possible to train neural networks that learn to both parse a sentence and use the resulting parse to interpret the sentence, all without exposure to groundtruth parse trees at training time. Surprisingly, these models often perform better at sentence understanding tasks than models that use parse trees from conventional parsers. This paper aims to investigate what these latent tree learning models learn. We replicate two such models in a shared codebase and find that (i) only one of these models outperforms conventional tree-structured models on sentence classification, (ii) its parsing strategies are not especially consistent across random restarts, (iii) the parses it produces tend to be shallower than standard Penn Treebank (PTB) parses, and (iv) they do not resemble those of PTB or any other semantic or syntactic formalism that the authors are aware of.

show abstract

Section: Introductionmentioning

confidence: 69%

Do latent tree learning models identify meaningful structure in sentences?

Williams

Drozdov

Bowman

2018

TACL

124

View full text Add to dashboard Cite

show abstract

“…An important observation is that as by-products we get, the semantic-compatible trees are taskspecific, and may not be in line with any expertdesigned grammar (Marcus et al, 1993). However, once we directly examine our model on grammar induction task (Klein and Manning, 2004;Gormley et al, 2014), we find surprisingly promising results. More discussions can be found in Appendix B.…”

Section: Recovery From Dependency Treesmentioning

confidence: 86%

Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments

Xia¹,

Zhou²,

Jiang

et al. 2021

Preprint

View full text Add to dashboard Cite

Semantic role labeling is a fundamental yet challenging task in the NLP community. Recent works of SRL mainly fall into two lines:1) BIO-based and 2) span-based. Despite effectiveness, they share some intrinsic drawbacks of not explicitly considering internal argument structures, which may potentially hinder the model's expressiveness. To remedy this, we propose to reduce SRL to a dependency parsing task and regard the flat argument spans as latent subtrees. In particular, we equip our formulation with a novel span-constrained TreeCRF model to make tree structures spanaware, and further extend it to the secondorder case. Experiments on CoNLL05 and CoNLL12 benchmarks reveal that the results of our methods outperform all previous works and achieve the state-of-the-art.

show abstract

“…Creating SRL datasets requires expert annotation, which is expensive. While there are some efforts on semi-automatic annotation targeting low-resource languages (e.g., Akbik et al, 2016), achieving high neural network performance with small or unlabeled datasets remains a challenge (e.g., Lapata, 2009, 2012;Titov and Klementiev, 2012;Gormley et al, 2014;Abend et al, 2009).…”

Section: Scenario 1: Low Training Datamentioning

confidence: 99%

Structured Tuning for Semantic Role Labeling

Li¹,

Jawale²,

Palmer³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Recent neural network-driven semantic role labeling (SRL) systems have shown impressive improvements in F1 scores. These improvements are due to expressive input representations, which, at least at the surface, are orthogonal to knowledge-rich constrained decoding mechanisms that helped linear SRL models. Introducing the benefits of structure to inform neural models presents a methodological challenge. In this paper, we present a structured tuning framework to improve models using softened constraints only at training time. Our framework leverages the expressiveness of neural networks and provides supervision with structured loss components. We start with a strong baseline (RoBERTa) to validate the impact of our approach, and show that our framework outperforms the baseline by learning to comply with declarative constraints. Additionally, our experiments with smaller training sizes show that we can achieve consistent improvements under low-resource scenarios. BERT CoNLL-2012 (100%) +U,F,O 0.5 1 0.1Table 10: Values of hyperparameter λ's.

show abstract

Low-Resource Semantic Role Labeling

Cited by 14 publications

References 21 publications

Do latent tree learning models identify meaningful structure in sentences?

Do latent tree learning models identify meaningful structure in sentences?

Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments

Structured Tuning for Semantic Role Labeling

Contact Info

Product

Resources

About