资源分类
》 资源 》论文》Rewarding Smatch: Transition-Based AMR Parsingwith Reinforcement Learning

Rewarding Smatch: Transition-Based AMR Parsingwith Reinforcement Learning

2019-09-18 | |  93 |   44 |   0 0 0
Abstract Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs. In addition, we also combined several AMR-to-text alignments with an attention mechanism and we supplemented the parser with pre-processed concept identification, named entities and contextualized embeddings. We achieve a highly competitive performance that is comparable to the best published results. We show an indepth study ablating each of the new components of the parser.

上一篇：Representing Schema Structure with Graph Neural Networks forText-to-SQL Parsing

下一篇：Second-Order Semantic Dependency Parsing with End-to-End NeuralNetworks

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...