Frame-Semantic Role Labeling with Heterogeneous Annotations

Kshirsagar, Meghana; Thomson, Sam; Schneider, Nathan; Carbonell, Jaime R.; Smith, Noah A.; Dyer, Chris

doi:10.3115/v1/p15-2036

Cited by 57 publications

(51 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our baselines include SEMAFOR 9 , a widely used frame-semantic parser for English, and SEMAFOR (BEST), an improved SEMAFOR system that is trained with heterogeneous resources (Kshirsagar et al, 2015).…”

Section: Framenet Resultsmentioning

confidence: 99%

A Joint Sequential and Relational Model for Frame-Semantic Parsing

Yang¹,

Mitchell²

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

We introduce a new method for framesemantic parsing that significantly improves the prior state of the art. Our model leverages the advantages of a deep bidirectional LSTM network which predicts semantic role labels word by word and a relational network which predicts semantic roles for individual text expressions in relation to a predicate. The two networks are integrated into a single model via knowledge distillation, and a unified graphical model is employed to jointly decode frames and semantic roles during inference. Experiments on the standard FrameNet data show that our model significantly outperforms existing neural and non-neural approaches, achieving a 5.7 F1 gain over the current state of the art, for full frame structure extraction.

show abstract

Section: Framenet Resultsmentioning

confidence: 99%

A Joint Sequential and Relational Model for Frame-Semantic Parsing

Yang¹,

Mitchell²

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…Most earlier work had in common that it assumed jointly labeled data (same corpus annotated with multiple labels). In contrast, in this paper we evaluate multitask training from distinct sources to address data paucity, like done recently (Kshirsagar et al, 2015;Braud et al, 2016;Plank, 2016). Sutton et al (2007) demonstrate improvements for POS tagging by training a joint CRF model for both POS tagging and noun-phrase chunking.…”

Section: Related Workmentioning

confidence: 99%

When is multitask learning effective? Semantic sequence prediction under varying data conditions

Alonso¹,

Plank²

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

View full text Add to dashboard Cite

Multitask learning has been applied successfully to a range of tasks, mostly morphosyntactic. However, little is known on when MTL works and whether there are data characteristics that help to determine its success. In this paper we evaluate a range of semantic sequence labeling tasks in a MTL setup. We examine different auxiliary tasks, amongst which a novel setup, and correlate their impact to datadependent conditions. Our results show that MTL is not always effective, significant improvements are obtained only for 1 out of 5 tasks. When successful, auxiliary tasks with compact and more uniform label distributions are preferable.

show abstract

“…For FrameNet-style SRL, Kshirsagar et al (2015) recently proposed the use of PropBankbased features, but their system performance falls short of the state of the art. Roth and Lapata (2015) proposed another approach exploring linguistically motivated features tuned towards the FrameNet lexicon, but their performance metrics are significantly worse than our best results.…”

Section: Related Workmentioning

confidence: 99%

Semantic Role Labeling with Neural Network Factors

FitzGerald¹,

Täckström²,

Ganchev³

et al. 2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

112

107

View full text Add to dashboard Cite

We present a new method for semantic role labeling in which arguments and semantic roles are jointly embedded in a shared vector space for a given predicate. These embeddings belong to a neural network, whose output represents the potential functions of a graphical model designed for the SRL task. We consider both local and structured learning methods and obtain strong results on standard PropBank and FrameNet corpora with a straightforward product-of-experts model. We further show how the model can learn jointly from PropBank and FrameNet annotations to obtain additional improvements on the smaller FrameNet dataset.

show abstract

Frame-Semantic Role Labeling with Heterogeneous Annotations

Cited by 57 publications

References 21 publications

A Joint Sequential and Relational Model for Frame-Semantic Parsing

A Joint Sequential and Relational Model for Frame-Semantic Parsing

When is multitask learning effective? Semantic sequence prediction under varying data conditions

Semantic Role Labeling with Neural Network Factors

Contact Info

Product

Resources

About