Fast and Accurate Span-based Semantic Role Labeling as Graph Parsing
Currently, BIO-based and Tuple-based approaches perform quite well on the span-based semantic role labeling (SRL) task. However, the BIO-based approach usually needs to encode a sentence once for each predicate when predicting its arguments, and the Tuple-based approach has to deal with a huge search space of $O(n^3)$, greatly reducing the training and inference efficiency. Moreover, both BIO-based and Tuple-based approaches usually consider only local structural information when making predictions.This paper proposes to cast end-to-end span-based SRL as a graph parsing task. Based on a novel graph representation schema, we present a fast and accurate SRL parser on the shoulder of recent works on high-order semantic dependency graph parsing (SDGP). Moreover, we propose a constrained Viterbi procedure to ensure the legality of the output graph. Experiments on CoNLL05, CoNLL12, and Chinese Proposition Bank 1.0 (CPB1.0) datasets show that our model achieves new state-of-the-art results and can parse over 600 sentences per second.
Code (0)
등록된 구현이 없습니다.
Tasks
Semantic Role LabelingSentenceSimilar Papers 제목 키워드 기반
A Span Selection Model for Semantic Role Labeling
We present a simple and accurate span-based model for semantic role labeling (SRL). Our model directly takes into account all possible argument spans and scores them for each label. At decoding time, we greedily select h…
modelSemantic Role LabelingSemantic Role Labeling as Syntactic Dependency Parsing
We reduce the task of (span-based) PropBank-style semantic role labeling (SRL) to syntactic dependency parsing. Our approach is motivated by our empirical analysis that shows three common syntactic patterns account for o…
Dependency ParsingSemantic Role LabelingIterative Span Selection: Self-Emergence of Resolving Orders in Semantic Role Labeling
Semantic Role Labeling (SRL) is the task of labeling semantic arguments for marked semantic predicates. Semantic arguments and their predicates are related in various distinct manners, of which certain semantic arguments…
Semantic Role LabelingA Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling
We introduce a simple and accurate neural model for dependency-based semantic role labeling. Our model predicts predicate-argument dependencies relying on states of a bidirectional LSTM encoder. The semantic role labeler…
Semantic Role LabelingDependency and Span, Cross-Style Semantic Role Labeling on PropBank and NomBank
The latest developments in neural semantic role labeling (SRL) have shown great performance improvements with both the dependency and span formalisms/styles. Although the two styles share many similarities in linguistic …
Semantic Role Labeling