基于图神经网络的汉语依存分析和语义组合计算联合模型(Joint Learning Chinese Dependency Parsing and Semantic Composition based on Graph Neural Network)

2020-10-01 · CCL 2020 10 · Kai Wang, Mingtong Liu, Yuanmeng Chen, Yujie Zhang, Jinan Xu, Yufeng Chen

组合原则表明句子的语义由其构成成分的语义按照一定规则组合而成, 由此基于句法结构的语义组合计算一直是一个重要的探索方向,其中采用树结构的组合计算方法最具有代表性。但是该方法难以应用于大规模数据处理,主要问题是其语义组合的顺序依赖于具体树的结构,无法实现并行处理。本文提出一种基于图的依存句法分析和语义组合计算的联合框架,并借助复述识别任务训练语义组合模型和句法分析模型。一方面图模型可以在训练和预测阶段采用并行处理,极大缩短计算时间;另一方面联合句法分析的语义组合框架不必依赖外部句法分析器,同时两个任务的联合学习可使语义表示同时学习句法结构和语义的上下文信息。我们在公开汉语复述识别数据集LCQMC上进行评测,实验结果显示准确率接近树结构组合方法,达到79.54%,而预测速度提升高达30倍。

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Chinese Dependency ParsingDependency Parsing Graph Neural NetworkSemantic Composition

A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing

2019-04-09 · TACL 2020 1 · Hang Yan, Xipeng Qiu, Xuanjing Huang

Chinese word segmentation and dependency parsing are two fundamental tasks for Chinese natural language processing. The dependency parsing is defined on word-level. Therefore word segmentation is the precondition of depe…

Chinese Word Segmentation Dependency Parsing Feature Engineering Language Modeling+2

A Joint Model for Graph-based Chinese Dependency Parsing

2020-10-01 · CCL 2020 10 · Xingchen Li, Mingtong Liu, Yujie Zhang, Jinan Xu 외

In Chinese dependency parsing, the joint model of word segmentation, POS tagging and dependency parsing has become the mainstream framework because it can eliminate error propagation and share knowledge, where the transi…

Chinese Dependency Parsing Chinese Word Segmentation Dependency Parsing POS+3

Neural Joint Model for Transition-based Chinese Syntactic Analysis

2017-07-01 · ACL 2017 7 · Shuhei Kurita, Daisuke Kawahara, Sadao Kurohashi

We present neural network-based joint models for Chinese word segmentation, POS tagging and dependency parsing. Our models are the first neural approaches for fully joint Chinese analysis that is known to prevent the err…

Chinese Word Segmentation Dependency Parsing POS POS Tagging+2

A Re-ranking Model for Dependency Parser with Recursive Convolutional Neural Network

2015-05-21 · IJCNLP 2015 7 · Chenxi Zhu, Xipeng Qiu, Xinchi Chen, Xuanjing Huang

In this work, we address the problem to model all the nodes (words or phrases) in a dependency tree with the dense representations. We propose a recursive convolutional neural network (RCNN) architecture to capture synta…

Dependency Parsing Re-Ranking

Head-Driven Phrase Structure Grammar Parsing on Penn Treebank

2019-07-05 · ACL 2019 7 · Junru Zhou, Hai Zhao

Head-driven phrase structure grammar (HPSG) enjoys a uniform formalism representing rich contextual syntactic and even semantic meanings. This paper makes the first attempt to formulate a simplified HPSG by integrating c…

Constituency Parsing Decoder Dependency Parsing