Tree-Stack LSTM in Transition Based Dependency Parsing

Tree-Stack LSTM in Transition Based Dependency Parsing
复制标题

基于转换的依存解析中的 Tree-Stack LSTM

DOI:
10.18653/v1/k18-2012
复制
发表时间:
2018
期刊:
Knowl. Based Syst.
影响因子:
--
通讯作者:
Deniz Yuret
Deniz Yuret
中科院分区:
--
文献类型:
--
作者:
Ömer Kirnap;Erenay Dayanik;Deniz Yuret

文献摘要

参考文献

被引文献

相似文献

我们引入树栈LSTM来用递归神经网络对基于转换的解析器的状态进行建模。树栈LSTM不使用任何基于解析树或手工制作的功能,但比具有这些功能的模型表现更好。我们还从原始特征中开发了一组新的嵌入,以提高性能。该模型有4个主要组成部分:堆栈的σ-LSTM,缓冲区的β-LSTM,动作的LSTM和树-RNN。所有LSTM都使用连续密集特征向量(嵌入)作为输入。Tree-RNN基于转换更新这些嵌入。我们表明,我们的模型与其前辈相比,提高了低资源语言的性能。我们作为“KParse”团队参加了CoNLL 2018 UD共享任务,在LAS中排名第16位,在BLAS和BLEX指标中排名第15位,共有27名参与者解析了来自57种语言的82个测试集。
We introduce tree-stack LSTM to model state of a transition based parser with recurrent neural networks. Tree-stack LSTM does not use any parse tree based or hand-crafted features, yet performs better than models with these features. We also develop new set of embeddings from raw features to enhance the performance. There are 4 main components of this model: stack’s σ-LSTM, buffer’s β-LSTM, actions’ LSTM and tree-RNN. All LSTMs use continuous dense feature vectors (embeddings) as an input. Tree-RNN updates these embeddings based on transitions. We show that our model improves performance with low resource languages compared with its predecessors. We participate in CoNLL 2018 UD Shared Task as the “KParse” team and ranked 16th in LAS, 15th in BLAS and BLEX metrics, of 27 participants parsing 82 test sets from 57 languages.
DOI: 10.3115/v1/p15-1033
发表时间: 2015-05
期刊: ArXiv
影响因子: --
作者:
Chris Dyer;Miguel Ballesteros;Wang Ling;Austin Matthews;Noah A. Smith
通讯作者: Chris Dyer;Miguel Ballesteros;Wang Ling;Austin Matthews;Noah A. Smith