基于动作建模的中文依存句法分析

决策式依存句法分析,也就是基于分析动作的句法分析方法,常常被认为是一种高效的分析算法,但是它的性能稍低于一些更复杂的句法分析模型。本文将决策式句法分析同产生式、判别式句法分析这些复杂模型做了比较,试验数据采用宾州中文树库。结果显示,对于中文依存句法分析,决策式句法分析在性能上好于产生式和判别式句法分析。更进一步,我们观察到决策式句法分析是一种贪婪的算法,它在每个分析步骤只挑选最有可能的分析动作而丢失了对整句话依存分析的全局视角。基于此,我们提出了两种模型用来对句法分析动作进行建模以避免原决策式依存分析方法的贪婪性。试验结果显示,基于动作建模的依存分析模型在性能上好于原决策式依存分析方法,同时保持了较低的时间复杂度。     

最大生成树算法和决策式算法相结合的中文依存关系解析

基于最大生成树解析算法和决策式解析算法的互补关系,提出了最大生成树解析算法和决策式解析算法相结合的中文依存关系解析方法。结合方法利用Nivre模型的依存关系解析结果和依存度修正最大生成树模型有向边的权重,再搜索最大生成树作为依存树。使用宾州中文树库中的4 500句语料作十折交叉测试,结合模型的依存关系正确率达到了86.49%。结果表明该文提出的结合方法有效地提高了的中文依存关系解析性能。     

基于多特征融合编码的神经网络依存句法分析模型

在基于神经网络的依存句法分析中,对分析栈和决策层信息的表示和利用依然有值得深入研究的空间。针对分析栈的表示,已有工作并没有对单棵依存子树独立编码的表示,导致无法利用各个依存子树的局部特征;也没有对生成的依存弧序列进行编码,导致无法利用依存弧的全局信息。针对决策层的表示,已有工作利用MLP预测转移动作,该结构无法利用历史决策动作的信息。对此,该文提出基于多特征融合编码的神经网络依存句法分析模型,基于依存子树和历史生成的依存弧表示分析栈,利用TreeLSTM网络编码依存子树信息,利用LSTM网络编码历史生成的依存弧序列,以更好地表示分析栈的局部信息和全局信息。进一步提出基于LSTM网络的结构预测转移动作序列,引入历史决策动作信息作为特征辅助当前决策。该文以汉语为具体研究对象,在CTB5汉语依存分析数据上验证所提出的多特征融合编码的神经网络模型。实验结果显示,汉语依存句法分析性能得到改进,在目前公布的基于转移的分析系统中取得最好成绩,在UAS和LAS评价指标上分别达到87.8%和86.8%的精度,表明所提出的对依存子树局部特征及历史依存弧信息和历史决策动作信息的编码方法,在改进依存分析模型性能方面的有效性。     

基于高阶词汇依存的短语结构树重排序模型

在句法分析中,已有研究工作表明,词汇依存信息对短语结构句法分析是有帮助的,但是已有的研究工作都仅局限于使用一阶的词汇依存信息.提出了一种使用高阶词汇依存信息对短语结构树进行重排序的模型,该模型首先为输入句子生成有约束的搜索空间(例如,N-best句法分析树列表或者句法分析森林),然后在约束空间内获取高阶词汇依存特征,并利用这些特征对短语结构候选树进行重排序,最终选择出最优短语结构分析树.在宾州中文树库上的实验结果表明,该模型的最高F1值达到了85.74%,超过了目前在宾州中文树库上的最好结果.另外,在短语结构分析树的基础上生成的依存结构树的准确率也有了大幅提升.     

基于序列标注模型的分层式依存句法分析方法

该文提出了一种全新的分层式依存句法分析方法。该方法以依存深度不大于1的依存层作为分析单位,自底向上构建句子的依存结构。在层内,通过穷尽搜索得到层最优子结构;在层与层之间,分析状态确定性地转移。依存层的引入,使该模型具有比典型的基于图的方法更低的算法复杂度,与基于转换的方法相比,又一定程度上缓解了确定性过程的贪婪性。此外,该方法使用典型序列标注模型进行层依存子结构搜索,证明了序列标注技术完全可以胜任句法分析等层次结构分析任务。实验结果显示,该文提出的分层式依存分析方法具有与主流方法可比的分析精度和非常高的分析效率,在宾州树库上可以达到每秒2 500个英语单词。     

短语结构树库向依存结构树库转化研究

汉语依存树库的建设相对其他语言如英语,在规模和质量上还有一些差距。树库标注需要付出很大的人力物力,并且保证树库质量也比较困难。该文尝试通过规则和统计相结合的方法,将宾州汉语短语树库Penn Chinese Treebank转化为哈工大依存树库HIT-IR-CDT的体系结构,从而增大现有依存树库的规模。将转化后的树库加入HIT-IR-CDT,训练和测试依存句法分析器的性能。实验表明,加入少量经转化后的树库后,依存句法分析器的性能有所提高;但加入大量树库后,性能反而下降。经过细致分析,作为一种利用多种树库提高依存句法分析器性能的方法,短语转依存还存在很多需要深入研究的方面。     

Neural Parse Combination

Analyzing the syntactic structure of natural languages by parsing is an important task in artificial intelligence. Due to the complexity of natural languages, individual parsers tend to make different yet complementary errors. We propose a neural network based approach to combine parses from different parsers to yield a more accurate parse than individual ones. Unlike conventional approaches, our method directly transforms linearized candidate parses into the ground-truth parse. Experiments on the Penn English Treebank show that the proposed method improves over a state-of-the-art parser combination approach significantly.     

向上学习方法改进移进归约中文句法分析

基于移进归约的句法分析系统具有线性的时间复杂度,因此在大规模句法分析任务中具有特别实际的意义。然而目前移进归约句法分析系统的性能远低于领域内最好的句法分析器,例如,伯克利句法分析器。该文研究如何利用向上学习和无标注数据改进移进归约句法分析系统,使之尽可能接近伯克利句法分析器的性能。我们首先应用伯克利句法分析器对大规模的无标注数据进行自动分析,然后利用得到的自动标注数据作为额外的训练数据改进词性标注系统和移进归约句法分析器。实验结果表明,向上学习方法和无标注数据使移进归约句法分析的性能提高了2.3%,达到82.4%。这个性能与伯克利句法分析器的性能可比。与此同时,该文最终得到的句法分析系统拥有明显的速度优势(7倍速度于伯克利句法分析器)。     

Undirected Dependency Parsing

Dependency parsers, which are widely used in natural language processing tasks, employ a representation of syntax in which the structure of sentences is expressed in the form of directed links (dependencies) between their words. In this article, we introduce a new approach to transition‐based dependency parsing in which the parsing algorithm does not directly construct dependencies, but rather undirected links, which are then assigned a direction in a postprocessing step. We show that this alleviates error propagation, because undirected parsers do not need to observe the single‐head constraint, resulting in better accuracy. Undirected parsers can be obtained by transforming existing directed transition‐based parsers as long as they satisfy certain conditions. We apply this approach to obtain undirected variants of three different parsers (the Planar, 2‐Planar, and Covington algorithms) and perform experiments on several data sets from the CoNLL‐X shared tasks and on the Wall Street Journal portion of the Penn Treebank, showing that our approach is successful in reducing error propagation and produces improvements in parsing accuracy in most of the cases and achieving results competitive with state‐of‐the‐art transition‐based parsers.     

采用Stack-Tree LSTM的汉语一体化依存分析模型

在汉语一体化依存分析中,如何利用分词、词性标注和句法分析的中间结果作为分析特征成为核心问题,也是三个任务相互制约协调、共同提高性能的关键所在。目前无论基于特征工程的方法还是基于深度学习的方法尚无法充分利用分析过程中依存子树的完整信息,而依存子树作为中间结果的主要成分对三个任务的后续分析具有重要的指导意义。该文在基于转移的依存分析框架下,提出Stack-Tree LSTM依存子树编码方法,通过对分析栈中所有依存子树的有效建模,获取任意时刻的依存子树的完整信息作为特征参与转移动作决策。利用该编码方式提出词性特征使用方法,融合N-gram特征构建汉语一体化依存分析神经网络模型。最后在宾州汉语树库上进行了验证实验,并与已有方法进行了比较。实验结果显示: 该文提出的模型在分词、词性标注和依存分析任务上的性能非常接近特征工程最好的结果,并且均超过已有的一体化依存分析神经网络模型。     

面向移进—归约句法分析器的单模型系统整合算法

该文提出了一种面向移进—归约句法分析器的单模型系统整合算法。在训练阶段,该方法通过调整训练数据的分布,来构建用于整合的多个移进—归约句法分析器。在解码阶段,该方法首先使用各个移进—归约句法分析器对待分析的句子进行句法分析,然后利用一个线性模型对各句法分析器输出的句法树进行评分,从中选出得分最高的句法树作为最终结果。该文中的实验是在宾州英文树库上进行的。实验结果表明,该文中的方法能够显著改善基准系统的性能。     

借助汉-越双语词对齐语料构建越南语依存树库

由于对越南语的研究工作相对较少,因此还没有建立规模相对较大的依存树库。相对于已经拥有了形态丰富、语料成熟的汉语,越南语的依存句法分析要困难得多,所以该文提出了一种借助汉-越双语词对齐语料构建越南语依存树库的方法。首先对汉语-越南语句子对进行词对齐处理,然后对汉语句子进行依存句法分析。最后结合越南语本身的语言特点和有关的语法规则将汉语的依存关系通过汉-越双语词对齐关系映射到越南语句子中,从而生成越南语的依存树库。实验表明,该方法简化了人工收集和标注越南语依存树库的过程,节省了人力和构建树库的时间。实验结果表明,该方法相比采用机器学习的方法准确率明显提高。     

基于主动学习的中文依存句法分析

目前依存句法分析仍主要采用有指导的机器学习方法,即需要大规模高质量的树库作为训练语料,而现阶段中文依存树库资源相对较少,树库标注又是一件费时费力的工作。面对大量未标注语料,该文将主动学习应用到中文依存句法分析,优先选择句法模型预测不准的实例交由人工标注。该文提出并比较了多种衡量依存句法模型预测可信度的准则。实验表明,一方面,与随机选择标注实例相比,当使用相同数目训练实例时,主动学习使中文依存分析性能最高提升0.8%;另一方面,主动学习使依存分析达到相同准确率时只需标注更少量实例,人工标注量最多可减少30%。     

LTAG-spinal and the Treebank

We introduce LTAG-spinal, a novel variant of traditional Lexicalized Tree Adjoining Grammar (LTAG) with desirable linguistic, computational and statistical properties. Unlike in traditional LTAG, subcategorization frames and the argument–adjunct distinction are left underspecified in LTAG-spinal. LTAG-spinal with adjunction constraints is weakly equivalent to LTAG. The LTAG-spinal formalism is used to extract an LTAG-spinal Treebank from the Penn Treebank with Propbank annotation. Based on Propbank annotation, predicate coordination and LTAG adjunction structures are successfully extracted. The LTAG-spinal Treebank makes explicit semantic relations that are implicit or absent from the original PTB. LTAG-spinal provides a very desirable resource for statistical LTAG parsing, incremental parsing, dependency parsing, and semantic parsing. This treebank has been successfully used to train an incremental LTAG-spinal parser and a bidirectional LTAG dependency parser.

Improving Shift‐Reduce Phrase‐Structure Parsing with Constituent Boundary Information

Shift‐reduce parsing enjoys the property of efficiency because of the use of efficient parsing algorithms like greedy/deterministic search and beam search. In addition, shift‐reduce parsing is much simpler and easy to implement compared with other parsing algorithms. In this article, we explore constituent boundary information to improve the performance of shift‐reduce phrase‐structure parsing. In previous work, constituent boundary information has been used to speed up chart parsers successfully. However, whether it is useful for improving parsing accuracy has not been investigated. We propose two different models to capture constituent boundary information, based on which two sets of novel features are designed for a shift‐reduce parser. The first model is a boundary prediction model that uses a classifier to predict the boundaries of constituents. We use automatically parsed data to train the classifier. The second one is a Tree Likelihood Model that measures the validity of a constituent by its likelihood which is calculated on automatically parsed data. Experimental results show that our proposed method outperforms a strong baseline by 0.8% and 1.6% in F‐score on English and Chinese data, respectively, achieving the competitive parsing accuracies on Chinese (84.8%) and English (90.8%). To our knowledge, this is the first time for shift‐reduce phrase‐structure parsing to advance the state‐of‐the‐art with constituent boundary information.     

STOCHASTIC PARSING AND EVOLUTIONARY ALGORITHMS

This article aims to show the effectiveness of evolutionary algorithms in automatically parsing sentences of real texts. Parsing methods based on complete search techniques are limited by the exponential increase of the size of the search space with the size of the grammar and the length of the sentences to be parsed. Approximated methods, such as evolutionary algorithms, can provide approximate results, adequate to deal with the indeterminism that ambiguity introduces in natural language processing. This work investigates different alternatives to implement an evolutionary bottom-up parser. Different genetic operators have been considered and evaluated. We focus on statistical parsing models to establish preferences among different parses. It is not our aim to propose a new statistical model for parsing but a new algorithm to perform the parsing once the model has been defined. The training data are extracted from syntactically annotated corpora (treebanks) which provide sets of lexical and syntactic tags as well as the grammar in which the parsing is based. We have tested the system with two corpora: Susanne and Penn Treebank, obtaining very encouraging results.     

单语句法分析指导的双语结构对齐

提出了一种单语句法分析指导的双语语料库结构对齐方法．该方法以统计的双语模型——反向转换文法为基础,通过把英语句法分析知识融入到双语模型中,实现英汉双语的结构对齐．与现有方法相比,只需要一种语言的句法分析结果,避开了汉语句法分析的难题,同时保证了双语结构对齐的语法合理性．实验结果表明,这种方法充分利用现有的句法分析知识,有效地提高了结构对齐的正确率．利用该方法获得的结构对齐双语料库对于翻译知识的自动获取研究具有重要意义．     

基于序列标注的中文依存句法分析方法

提出了一种基于序列标注模型的中文依存句法分析方法.该方法将依存句法分析转化成序列标注问题,利用条件随机场CRF(Conditional Random Field)建立序列标注模型.在宾州中文树库的测试中,达得了76.59%的依存关系准确率,句子准确率也达到了23.5%.同时我们改进了Viterbi算法,使得依存关系的准确率提高了近2个百分点,句子准确率提高了近3.5个百分点.     

Towards Incremental Parsing of Natural Language Using Recursive Neural Networks

In this paper we develop novel algorithmic ideas for building a natural language parser grounded upon the hypothesis of incrementality. Although widely accepted and experimentally supported under a cognitive perspective as a model of the human parser, the incrementality assumption has never been exploited for building automatic parsers of unconstrained real texts. The essentials of the hypothesis are that words are processed in a left-to-right fashion, and the syntactic structure is kept totally connected at each step.Our proposal relies on a machine learning technique for predicting the correctness of partial syntactic structures that are built during the parsing process. A recursive neural network architecture is employed for computing predictions after a training phase on examples drawn from a corpus of parsed sentences, the Penn Treebank. Our results indicate the viability of the approach and lay out the premises for a novel generation of algorithms for natural language processing which more closely model human parsing. These algorithms may prove very useful in the development of efficient parsers.     

基于LSTM的层次化篇章依存分析方法

在长距离依赖场景,篇章依存分析的效果欠佳,传统分析方法通常设计大量特征模板来缓解这一瓶颈问题.该文提出一种层次化篇章依存分析方法,减少了篇章分析器所需一次性处理的篇章分析单元的数量,从而缩短了分析器所处理的依存对之间的距离;并通过长短时记忆模型直接处理篇章分析单元中的序列信息,避免了特征提取.在RS T语料库上进行实验...