Semantic Role Labeling with Iterative Structure Refinement

Lyu, Chunchuan; Cohen, Shay B.; Titov, Ivan

doi:10.18653/v1/d19-1099

Cited by 19 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The relation identification component is however weaker than, e.g., (Cai and Lam, 2020). This may not be surprising, as we, following Lyu and Titov (2018), score edges independently, whereas (Cai and Lam, 2020) perform iterative refinement which is known to boost performance on relations (Lyu et al, 2019). Also, we use BiLSTM encoders, which -while cheaper to train and easier to tune -is likely weaker than Transformer encoders used by Astudillo et al; Lee et al While these modifications, along with using extra pre-training techniques and data augmentation, may further boost performance of our model, we believe that our model is strong enough for our purposes, i.e.…”

Section: Resultsmentioning

confidence: 94%

A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing

Lyu¹,

Cohen²,

Titov³

2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

Meaning Representations (AMR) are a broad-coverage semantic formalism which represents sentence meaning as a directed acyclic graph. To train most AMR parsers, one needs to segment the graph into subgraphs and align each such subgraph to a word in a sentence; this is normally done at preprocessing, relying on hand-crafted rules. In contrast, we treat both alignment and segmentation as latent variables in our model and induce them as part of end-to-end training. As marginalizing over the structured latent variables is infeasible, we use the variational autoencoding framework. To ensure end-to-end differentiable optimization, we introduce a differentiable relaxation of the segmentation and alignment problems. We observe that inducing segmentation yields substantial gains over using a 'greedy' segmentation heuristic. The performance of our method also approaches that of a model that relies on the segmentation rules of Lyu and Titov (2018), which were hand-crafted to handle individual AMR constructions.

show abstract

Section: Resultsmentioning

confidence: 94%

A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing

Lyu¹,

Cohen²,

Titov³

2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Intuitively speaking, the refinement mechanism provides the models with additional chances to revise previous decisions. In existing work, this method was successfully applied to various tasks, e.g., text classification , sequential labeling (Cui and Zhang, 2019;Lyu et al, 2019), machine translation , and question answering (Nema et al, 2019). Our work is not the first attempt of introducing refinement mechanism to sequential labeling tasks.…”

Section: Discussionmentioning

confidence: 99%

Structured Refinement for Sequential Labeling

Wang¹,

Shindo

Matsumoto

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

Filtering target-irrelevant information through hierarchically refining hidden states has been demonstrated to be effective for obtaining informative representations. However, previous work simply relies on locally normalized attention without considering possible labels at other time steps, the capacity for modeling long-term dependency relations is thus limited. In this paper, we propose to extend previous work with globally normalized attention, e.g., structured attention, to leverage structural information for more effective representation refinement. We also propose two implementation tricks to accelerate CRF computation and an initialization trick for Chinese character embeddings to further improve performance. We provide extensive experimental results on various datasets to show the effectiveness and efficiency of our proposed method.

show abstract

“…We can also find recent syntax-agnostic approaches that do not perform full SRL and follow a predicate-centered strategy for decoding and word representation (based on gold predicates provided by CoNLL-2009 corpora): (Chen, Lyu and Titov, 2019) and (Lyu, Cohen and Titov, 2019), which additionally implement different iterative refinement procedures, and (Conia and Navigli, 2020), which employs an additional specific encoder for contextualizing each gold predicate in the sentence.…”

Section: Related Workmentioning

confidence: 99%

Transition-based Semantic Role Labeling with Pointer Networks

Fernández-González¹

2022

Preprint

View full text Add to dashboard Cite

Semantic role labeling (SRL) focuses on recognizing the predicate-argument structure of a sentence and plays a critical role in many natural language processing tasks such as machine translation and question answering. Practically all available methods do not perform full SRL, since they rely on pre-identified predicates, and most of them follow a pipeline strategy, using specific models for undertaking one or several SRL subtasks. In addition, previous approaches have a strong dependence on syntactic information to achieve state-of-the-art performance, despite being syntactic trees equally hard to produce. These simplifications and requirements make the majority of SRL systems impractical for real-world applications. In this article, we propose the first transition-based SRL approach that is capable of completely processing an input sentence in a single left-to-right pass, with neither leveraging syntactic information nor resorting to additional modules. Thanks to our implementation based on Pointer Networks, full SRL can be accurately and efficiently done in ( 2 ), achieving the best performance to date on the majority of languages from the CoNLL-2009 shared task.

show abstract

Semantic Role Labeling with Iterative Structure Refinement

Cited by 19 publications

References 30 publications

A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing

A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing

Structured Refinement for Sequential Labeling

Transition-based Semantic Role Labeling with Pointer Networks

Contact Info

Product

Resources

About