语言技术平台

中文信息处理不仅需要基础数据平台的支撑,而且需要基础技术平台的支撑.该文介绍了我们历经八年研制并不断改进的语言技术平台LTP(Language Technology Platform).该平台包括中文词法分析、句法分析以及语义分析等多项中文处理技术,其中的句法语义分析技术在CoNLL 2009国际评测中获得第一名的成绩...     

汉英机器翻译源语分析中词的识别

汉英MT源语分析首先遇到的问题是词的识别。汉语中的“词”没有明确的定义,语素和词、词和词组、词组和句子,相互之间也没有清楚的界限。按照先分词、再句法分析的办法,会在分词时遇到构词问题和句法问题相互交错的困难。作者认为,可以把字作为源语句法分析的起始点,使词和词组的识别与句法分析同时进行。本文叙述了这种观点及其实现过程,并且以处理离合词为例,说明了识别的基本方法。     

一个基于GLR算法的英汉机器翻译浅层句法分析器

浅层句法分析是指短语级的自然语言句法分析。在研制MatLink英汉机器翻译系统的过程中,提出了扩充的CFG文法用于描述英语短语句法,并改进了GLR算法,设计实现了用于英汉翻译的英语浅层句法分析器。该分析器采用多出口的分析表结构,引入符号映射函数实现短语边界的自动识别,用孩子兄弟树描述短语的句法结构,并通过短语转换模式实现源语言向目标语言的短语级转换。最后,通过对一个实例句子的分析阐述了该浅层句法分析器的设计思想和工作过程。     

Parallel Parsing Algorithms and VLSI Implementations for Syntactic Pattern Recognition

Earley's algorithm has been commonly used for the parsing of general context-free languages and the error-correcting parsing in syntactic pattern recognition. The time complexity for parsing is 0(n3). This paper presents a parallel Earley's recognition algorithm in terms of an ``X*' operator. By restricting the input context-free grammar to be ?-free, the parallel algorithm can be executed on a triangular-shape VLSI array. This array system has an efficient way of moving data to the right place at the right time. Simulation results show that this system can recognize a string with length n in 2n + 1 system time. We also present a parallel parse-extraction algorithm, a complete parsing algorithm, and an error-correcting recognition algorithm. The parallel complete parsing algorithm has been simulated on a processor array which is similar to the triangular VLSI array. For an input string of length n the processor array will give the correct right-parse at system time 2n + 1 if the string is accepted. The error-correcting recognition algorithm has also been simulated on a triangular VLSI array. This array recognizes an erroneous string of length n in time 2n + 1 and gives the correct error count. These parallel algorithms are especially useful for syntactic pattern recognition.     

基于统计学习模型的句法分析方法综述

句法分析是自然语言处理领域中重要的基础研究问题之一。近年来,基于统计学习模型的句法分析方法研究受到了广泛关注,多种模型与算法先后被提出。从采用的学习模型和算法类型着手,该文系统地对各种主流和前沿方法进行了归纳与分类,着重对各类模型和算法的思想进行了分析和对比,并对中文句法分析的研究现状进行了综述;最后,对句法分析下一步的研究方向与趋势进行了展望。     

融合语义类信息的句法分析统计模型

稀疏数据严重影响句子结构分析模型的结果, 而句法结构是语义内容和句法分析形式的结合。本文在语义结构信息标注的基础上提出了一种基于语义搭配关系的词聚类模型和算法,建立基于语义类的头驱动句子结构分析统计模型。该语言模型不但比较成功地解决了数据稀疏问题, 而且句子结构分析系统性能也有了明显的提高。句子结构分析实验结果表明,基于语义类的头驱动的句子结构分析统计模型,其召回率和精确率的值相应为88.26%和88.73%,综合指标改进了8.39%。     

Parsing Turkish using the lexical functional grammar formalism

This paper describes our work on parsing Turkish using thelexical-functional grammar formalism [11]. This work represents the first effort for wide-coverage syntactic parsing of Turkish. Our implementation is based on Tomita's parser developed at Carnegie Mellon University Center for Machine Translation. The grammar covers a substantial subset of Turkish including structurally simple and complex sentences, and deals with a reasonable amount of word order freeness. The complex agglutinative morphology of Turkish lexical structures is handled using a separate two-level morphological analyzer, which has been incorporated into the syntactic parser. After a discussion of the key relevant issues regarding Turkish grammar, we discuss aspects of our system and present results from our implementation. Our initial results suggest that our system can parse about 82% of the sentences directly and almost all the remaining with very minor pre-editing.This work was done as a part of the first author's M.Sc. degree work at the Department of Computer Engineering and Information Science, Bilkent University, Ankara, 06533, Turkey.     

良构子串表在自然语言处理中的程序化应用以花园幽径句为例

自然语言处理是计算语言学研究的方向之一,通常借助计算机技术进行自然语言的分析和解读。NS 流程图具有选择算法剖析的结构性特点。良构子串表具有保存剖析过程多种结构的特性。花园幽径句是句法加工过程中能产生行进式错位且对前期模式破旧立新的特殊句式。基于NS 流程图算法的良构子串表可用于对自然语言中的特殊现象(如花园幽径句)进行程序剖析,最终使这种程序分析法在语言学中得到应用成为可能。     

引入标点处理的层次化汉语长句句法分析方法

在分析汉语标点符号用法和句法功能的基础上,本文提出了一种新的面向汉语长句的层次化句法分析方法。这种方法和传统的不考虑标点符号的一遍分析方法的主要区别在于两个方面:第一,利用部分标点符号的特殊功能将复杂长句分割成子句序列,从而把整句的句法分析分成两级来进行。这种“分而治之”的策略大大降低了在传统的一遍分析方法中同时识别子句或短语之间的句法关系以及子句和短语内部成分的句法关系的困难。第二,从大规模树库中提取包含所有标点符号的语法规则和相应概率分布信息,有利于句法分析和歧义消解。实验证明我们的方法与传统的一遍图表(chart)分析方法相比,能够大大减少时间消耗和歧义边的个数,并且提高了复杂长句分析的正确率和召回率约7%。     

Improving Syntactic Parsing of Chinese with Empty Element Recovery

This paper puts forward and explores the problem of empty element （EE） recovery in Chinese from the syntactic parsing perspective, which has been largely ignored in the literature. First, we demonstrate why EEs play a critical role in syntactic parsing of Chinese and how EEs can better benefit syntactic parsing of Chinese via re-categorization from the syntactic perspective. Then, we propose two ways to automatically recover EEs： a joint constituent parsing approach and a chunk-based dependency parsing approach. Evaluation on the Chinese TreeBank （CTB） 5.1 corpus shows that integrating EE recovery into the Charniak parser achieves a significant performance improvement of 1.29 in Fl-measure. To the best of our knowledge, this is the first close examination of EEs in syntactic parsing of Chinese, which deserves more attention in the future with regard to its specific importance.     

句法分析前沿动态综述

句法分析的目标是分析输入句子并得到其句法结构,是自然语言处理领域的经典任务之一。目前针对该任务的研究主要集中于如何通过从数据中自动学习来提升句法分析器的精度。该文对句法分析方向的前沿动态进行了调研,分别从有监督句法分析、无监督句法分析和跨领域跨语言句法分析三个子方向梳理和介绍了2018—2019年发表的新方法和新发现,并对句法分析子方向的研究前景进行了分析和展望。     

统计句法分析建模中基于信息论的特征类型分析

统计句法分析利用概率评价模型评价每棵选句法树存在的可能性,选择概率值最高的候选句法树作为最终的句法分析结果。因此,统计句法分析的核心是一个概率评价模型,而各种概率评价模型的本质区别主要在于它们分别是根据上下文中的哪些特征来赋予句法树概率的。在统计句法分析研究领域,虽然已经提出了大量的概率评价模型,然而,不同的模型用得到了不同类型的特征,如何评价这些特征类型对于句法分析的作用呢？针对以上的问题,本研究为统计句法分析提出了一种特征类型的分析模型,该模型可以从信息论的角度量化地分析不同类型的上下文特征对于句法结构的预测作用。其基本思想是利用信息论中熵与条件熵的度量来显示一个特征类型是否抓住了预测句法结构的主要信息。如果加入某个特征类型之后当前句法结构的不确定性（熵）明显下降,则认为该特征类型抓住了上下文中影响句法结构的某些主要信息。特征类型分析的信息论模型利用预测信息量、预测信息增益、预测信息关联度以及预测信息总量四种度量从不同的仙量化地分析各种特征类型及特征类型组合对于当前目标的预测作用。实验以Penn TreeBank为训练集,将上下文中不同的特征类型对于句法分析规则的预测作用进行了系统的量化分析,得出了一系列有关不同特征类型及特征类型组合对句法结构的预测作用的结论。     

基于ER模型的数据库受限汉语查询界面RChiQL的文法分析系统研究

RChiQL是一个基于受限汉语的关系数据库查询语言界面的计算模型,其中文法分析占有重要地位。本文引入了一种新的文法GWERSC(Grammar with ER Semantic Characteristics , ER语义特征文法) ,设计了分析算法,其内嵌的ER语义特征有利于排除语法分析的歧义并可简化语义分析。     

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.     

哈萨克语句法分析辅助特征提取研究

在哈萨克语句法分析中,该文用平均感知器算法训练句法分析模型,用柱搜索算法进行解码,可以快速准确地对哈萨克语句子进行短语结构句法分析。在解析句子过程中,构建了一个双向LSTM模型,利用它提取句子中每个单词之间组成结构的信息,以预测每个单词在句法树中的句法组成部分,然后将结果作为辅助前瞻特征传递给句法分析过程。实验证明,此方法与基线模型相比,在准确率和召回率上均有提高。     

A Shallow Text Processing Core Engine

In this article we present SMES–SPPC, a high–performance system for intelligent extraction of structured data from free text documents. SMES–SPPC consists of a set of domain–adaptive shallow core components that are realized by means of cascaded weighted finite–state machines and generic dynamic tries. The system has been fully implemented for German; it includes morphological and on–line compound analysis, efficient POS–filtering, high–performance named–entity recognition and chunk parsing based on a novel divide–and–conquer strategy. The whole approach proved to be very useful for processing free word order languages such as German. SMES–SPPC has a good performance (more than 6000 words per second on standard PC environments) and achieves high linguistic coverage, especially for the divide–and–conquer parsing strategy, where we obtained an f –measure of 87.14% on unseen data.     

融入句法感知表示进行句法增强的语义解析

在自然语言处理（NLP）中,句法信息是完整句子中词汇与词汇之间的句法结构关系或者依存关系,是一种重要且有效的参考信息。语义解析任务是将自然语言语句直接转化成语义完整的、计算机可执行的语言。在以往的语义解析研究中,少有采用输入源的句法信息来提高端到端语义解析效率的工作。为了进一步提高端到端语义解析模型的准确率和效率,提出一种利用输入端句法依存关系信息来提高模型效率的语义解析方法。该方法的基本思路是先对一个端到端的依存关系解析器进行预训练;然后将该解析器的中间表示作为句法感知表示,与原有的字词嵌入表示拼接到一起以产生新的输入嵌入表示,并将得到的输入嵌入表示用于端到端语义解析模型;最后采用转导融合学习方式进行模型融合。实验对比了所提模型和基准模型Transformer以及过去十年的相关工作。实验结果表明,在ATIS、GEO、JOBS数据集上,融入依存句法信息感知表示以及转导融合学习的语义解析模型分别实现了89.1%、90.7%、91.4%的最佳准确率,全面超过了Transformer,验证了引入句法依存关系信息的有效性。     

汉语组块分析研究综述

组块分析作为浅层句法分析的代表,既可以满足很多语言信息处理系统对于句法功能的需求,又可以作为子任务,在词法分析和完全句法分析以及语义分析中间架起一座桥梁,为句子进行进一步深入分析提供有力的支持,因此众多的研究将注意力集中于组块分析上。该文主要对组块的定义和分类、组块识别方法、组块的标注和评测以及组块内部关系分析等几方面的研究进展进行详细的综述。最后,探讨了组块分析存在的问题并对未来的发展方向进行了展望。     

Towards Syntax-Aware Editors for Visual Languages

Editors for visual languages should provide a user-friendly environment supporting end users in the composition of visual sentences in an effective way. Syntax-aware editors are a class of editors that prompt users into writing syntactically correct programs by exploiting information on the visual language syntax. In particular, they do not constrain users to enter only correct syntactic states in a visual sentence. They merely inform the user when visual objects are syntactically correct. This means detecting both syntax and potential semantic errors as early as possible and providing feedback on such errors in a non-intrusive way during editing. As a consequence, error handling strategies are an essential part of such editing style of visual sentences.In this work, we develop a strategy for the construction of syntax-aware visual language editors by integrating incremental subsentence parsers into free-hand editors. The parser combines the LR-based techniques for parsing visual languages with the more general incremental Generalized LR parsing techniques developed for string languages. Such approach has been profitably exploited for introducing a noncorrecting error recovery strategy, and for prompting during the editing the continuation of what the user is drawing.     

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.