• Corpus ID: 252355564

Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing

  title={Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing},
  author={Shilin Zhou and Qingrong Xia and Zhenghua Li and Yu Zhang and Yu Hong and Min Zhang},
  booktitle={International Conference on Computational Linguistics},
This paper proposes to cast end-to-end span-based SRL as a word-based graph parsing task. The major challenge is how to represent spans at the word level. Borrowing ideas from research on Chinese word segmentation and named entity recognition, we propose and compare four different schemata of graph representation, i.e., BES, BE, BIES, and BII, among which we find that the BES schema performs the best. We further gain interesting insights through detailed analysis. Moreover, we propose a simple… 

Transition-based Semantic Role Labeling with Pointer Networks

This article proposes 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.



Dependency or Span, End-to-End Uniform Semantic Role Labeling

This paper presents an end-to-end model for both dependency and span SRL with a unified argument representation to deal with two different types of argument annotations in a uniform fashion and jointly predict all predicates and arguments.

Generating Senses and RoLes: An End-to-End Model for Dependency- and Span-based Semantic Role Labeling

Evaluated on standard gold benchmarks, GSRL achieves state-of-the-art results in both dependency- and span-based English SRL, proving empirically that the simple generation-based model can learn to produce complex predicate-argument structures.

A Full End-to-End Semantic Role Labeler, Syntactic-agnostic Over Syntactic-aware?

This paper introduces an end-to-end neural model which unifiedly tackles the predicate disambiguation and the argument labeling in one shot, and is the first syntax-agnostic SRL model that surpasses all known syntax-aware models.

Deep Semantic Role Labeling with Self-Attention

This paper presents a simple and effective architecture for SRL which is based on self-attention which can directly capture the relationships between two tokens regardless of their distance and is computationally efficient.

End-to-end learning of semantic role labeling using recurrent neural networks

This work proposes to use deep bi-directional recurrent network as an end-to-end system for SRL, which takes only original text information as input feature, without using any syntactic knowledge.

Syntax-Aware Neural Semantic Role Labeling

Experiments on the benchmark CoNLL-2005 dataset show that syntax-aware SRL approaches can effectively improve performance over a strong baseline with external word representations from ELMo, and investigate several previous approaches for encoding syntactic trees to make a thorough study on whether extrantax-aware representations are beneficial for neural SRL models.

Simpler but More Accurate Semantic Dependency Parsing

The LSTM-based syntactic parser of Dozat and Manning (2017) is extended to train on and generate graph structures that aim to capture between-word relationships that are more closely related to the meaning of a sentence, using graph-structured representations.

Comparing Span Extraction Methods for Semantic Role Labeling

With extensive experiments on PropBank SRL datasets, it is found that more structured decoding methods outperform BIO-tagging when using static (word type) embeddings across all experimental settings, but when used in conjunction with pre-trained contextualized word representations, the benefits are diminished.

Efficient Second-Order TreeCRF for Neural Dependency Parsing

This paper presents a second-order TreeCRF extension to the biaffine parser, and proposes an effective way to batchify the inside and Viterbi algorithms for direct large matrix operation on GPUs, and to avoid the complex outside algorithm via efficient back-propagation.

Second-Order Semantic Dependency Parsing with End-to-End Neural Networks

This paper proposes a second-order semantic dependency parser, which takes into consideration not only individual dependency edges but also interactions between pairs of edges, and shows that second- order parsing can be approximated using mean field variational inference or loopy belief propagation.