paper-with-me

Papers

Approximate Dynamic Oracle for Dependency Parsing with Reinforcement Learning

2018-11-01 · WS 2018 11 · Xiang Yu, Ngoc Thang Vu, Jonas Kuhn

We present a general approach with reinforcement learning (RL) to approximate dynamic oracles for transition systems where exact dynamic oracles are difficult to derive. We treat oracle parsing as a reinforcement learning problem, design the reward function inspired by the classical dynamic oracle, and use Deep Q-Learning (DQN) techniques to train the oracle with gold trees as features. The combination of a priori knowledge and data-driven methods enables an efficient dynamic oracle, which improves the parser performance over static oracles in several transition systems.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Dependency ParsingImitation LearningQ-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Structured Prediction

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Similar Papers 제목 키워드 기반

Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles

2016-12-20 · EMNLP 2016 11 · James Cross, Liang Huang

Parsing accuracy using efficient greedy transition systems has improved dramatically in recent years thanks to neural networks. Despite striking results in dependency parsing, however, neural models have not surpassed st…

Constituency ParsingDependency ParsingRerankingSentence

Bidirectional Transition-Based Dependency Parsing

2019-07-17 · AAAI 2019 7 · Yunzhe Yuan, Yong Jiang, Kewei Tu

Transition-based dependency parsing is a fast and effective approach for dependency parsing. Traditionally, a transitionbased dependency parser processes an input sentence and predicts a sequence of parsing actions in a …

Dependency ParsingSentenceTransition-Based Dependency Parsing

A Tabular Method for Dynamic Oracles in Transition-Based Parsing

2014-01-01 · TACL 2014 1 · Yoav Goldberg, Francesco Sartorio, Giorgio Satta

We develop parsing oracles for two transition-based dependency parsers, including the arc-standard parser, solving a problem that was left open in (Goldberg and Nivre, 2013). We experimentally show that using these oracl…

ARC

A Dynamic Oracle for Arc-Eager Dependency Parsing

2012-12-01 · COLING 2012 12 · Yoav Goldberg, Joakim Nivre
ARCDependency Parsing

Transition-based Dependency DAG Parsing Using Dynamic Oracles

2015-07-01 · IJCNLP 2015 7 · Alper Tokg{\"o}z, G{\"u}l{\c{s}}en Eryi{\v{g}}it
Dependency ParsingFeature EngineeringMachine TranslationNatural Language Inference+1