Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing
원문 초록
Dynamic oracles provide strong supervision for training constituency parsers with exploration, but must be custom defined for a given parser's transition system. We explore using a policy gradient method as a parser-agnostic alternative. In addition to directly optimizing for a tree-level metric such as F1, policy gradient has the potential to reduce exposure bias by allowing exploration during training; moreover, it does not require a dynamic oracle for supervision. On four constituency parsers in three languages, the method substantially outperforms static oracle likelihood training in almost all settings. For parsers where a dynamic oracle is available (including a novel oracle which we define for the transition system of Dyer et al. 2016), policy gradient typically recaptures a substantial fraction of the performance gain afforded by the dynamic oracle.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Automatic Extraction of Clausal Embedding Based on Large-Scale English Text Data
Improving Unsupervised Constituency Parsing via Maximizing Semantic Information
Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction
To be Continuous, or to be Discrete, Those are Bits of Questions
Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing
Structured Tree Alignment for Evaluation of (Speech) Constituency Parsing
토론
이 논문과 연결된 포럼 글이 아직 없습니다.