基于中心/修饰依存重排序模型的短语SMT ?

为了提高基于短语的机器翻译系统的重排序能力,提出了一个基于源语言端的中心-修饰依存结构的重排序模型,并将该重排序模型以软约束的方式加入到机器翻译系统中。该排序模型提出了一种在机器翻译中应用句法树资源的方法,将句法树结构,通过将句法树映射成中心-修饰词的依存关系集合。该重排序模型在基于短语系统的默认参数设置下,显著地提升了系统的翻译质量。在系统原有的词汇化的重排序模型基础上,该重排序模型在翻译模型中融入了句法信息。实验结果显示,该模型可以明显地改善机器翻译系统的局部调序。     

面向机器翻译的藏语短语句法研究

针对现代藏语句法,在参照宾大中文树库的基础上,构建藏语短语句法树库,并建立了树库编辑工具,为藏汉机器翻译服务。在短语句法树库的基础上,提出一种融合藏语句法特征的藏汉机器翻译方法。实验分析结果表明,该方法可以很好地应用于藏汉机器翻译系统。     

基于同步树序列替换文法的统计机器翻译模型

基于短语的模型是目前发展相对成熟的一种统计机器翻译(Statistical machine translation, SMT)模型. 但基于短语的模型不包含任何结构信息, 因而缺乏有效的全局调序能力, 同时不能对非连续短语进行建模. 基于句法的模型因具有结构信息而具有解决以上问题的潜力, 因而越来越受到研究者们的重视. 然而现有的大多数基于句法的模型都因严格的句法限制而制约了模型的描述能力. 为突破这种限制并将 基于短语的模型的优点融入到句法模型中, 本文提出一种基于同步树序列替换文法(Synchronous tree sequence substitution grammar, STSSG)的统计机器翻译模型. 在此模型中, 树序列被用作为基本的翻译单元. 在这种框架下, 不满足句法限制的翻译等价对和满足句法限制的翻译等价对都可以融入句法信息并被翻译模型所使用. 从而, 两种模型的优点均得到充分利用. 在2005年度美国国家标准与技术研究所(NIST)举办的机器翻译评比的中文翻译任务语料上的实验表明, 本文提出的模型显著地超过了两个基准系统: 基于短语的翻译系统Moses和一个基于严格树结构的句法翻译模型.     

基于最大熵短语重排序模型的特征抽取算法改进

该文针对统计机器翻译中基于最大熵短语重排序模型特征抽取算法,提出一种改进算法。该算法能够抽取出更多准确的短语重排序信息,特别是逆序短语的特征信息,解决了原算法中最大熵训练时特征数据不平衡的问题,提高了翻译中短语重排序的准确率。以NIST MT 05 作为汉语到英语翻译的测试集,实验结果表明改进后的系统BLEU值比原系统提高0.65%。     

统计机器翻译中翻译规则抽取

对齐短语是决定统计机器翻译系统质量的核心模块。提出基于短语结构树的层次短语模型,这是利用串-树模型的思想对层次短语模型的扩展。基于短语结构树的层次短语模型是在双语对齐短语的基础之上结合英语短语结构树抽取翻译规则,并利用启发式策略获得翻译规则的扩展句法标记。采用翻译规则的统计机器翻译系统在不同数据集上具有稳定的翻译结果,在训练集和测试集的平均BlEU评分高于短语模型和层次短语模型的BLEU评分。     

基于有效句型的英汉双语短语对齐

双语短语对齐的输入是源语言 (英语 )、目标语言 (汉语 )候选句法分析树集 由于翻译异常现象的大量存在 ,源语言句法树和目标语言句法树间往往不存在简单的对应关系 如何在翻译异常的情况下 ,从源语言、目标语言候选句法树集中排除歧义 ,选出正确的句法树 ,并揭示其短语层次上的对应关系 ,是双语短语对齐的主要困难 提出的基于“有效句型”概念和“翻译中相对不变准则”的短语对齐模型基本解决了上述问题 双语短语对齐本身是一个复杂度较高的处理过程 ,提出的有关定理和算法使系统在保证对齐正确率的前提下 ,保证了时间效率     

基于藏语语义分析的机器翻译技术研究

藏汉机器翻译技术跟汉英机器翻译技术有所不同,其中,很重要的一个方面,藏语更依赖于格助词等虚词在句子中的作用,格助词种类繁多,用法差异很大。针对藏语格助词进行分析,在藏语短语句法树库的基础上,加入了藏语本体特征的语义信息,形成融合藏语语义信息的藏汉机器翻译方法。通过对比基于短语和句法的实验分析,该方法可以很好地应用于藏汉机器翻译系统。     

融入双语最大名词短语的机器翻译模型

在统计机器翻译中融入有价值的句法层面的语言学知识,对于推动统计机器翻译的发展,具有重要的理论意义和应用价值。提出了三种由简到繁的把双语最大名词短语融入到统计翻译模型的策略,整体翻译性能逐步上升。Method-III采用“分而治之”的策略,以“硬约束”的方式在统计机器翻译中融入最大名词短语,并在双语最大名词短语层面上,融合了短语翻译模型和层次短语模型,对翻译系统的改善最显著。所述策略显著提高了短语翻译模型的质量,在复杂长句翻译中,Method-III的BLEU值比基于短语的基线翻译模型提高了3.03%。     

基于有效包型的英汉双语短语对齐

双语短语对齐的输入是源语言（英语）、目标语言（汉语）候选句法分析树集。由于翻译异常现象的大量存在，源语言句法树和目标语言句法树间往往不存在简单的对应关系。如何在翻译异常的情况下，从源语言、目标语言候选句法树集中排除歧义，选出正确的句法树，并揭示其短语层次上的对应关系，是双语短语对齐的主要困难。提出的基于“有效句型”概念和“翻译中相对不变准则”的短语对齐模型基本解决了上述问题。双语短语对齐本身是一个复杂度较高的处理过程，提出的有关定量和算法使系统在保证对齐正确率的前提下，保证了时间效率。     

统计机器翻译和翻译记忆的动态融合方法研究

在融合翻译记忆和统计机器翻译的整合式模型的基础上,该文提出在解码过程中进一步地动态加入翻译记忆中新发现的短语对。它在机器翻译解码过程中,动态地加入翻译记忆片段作为候选,并利用翻译记忆的相关信息,指导基于短语的翻译模型进行解码。实验结果表明该方法显著提高了翻译质量: 与翻译记忆系统相比,该方法提高了21.15个BLEU值,降低了21.47个TER值;与基于短语的翻译系统相比,该方法提高了5.16个BLEU值,降低了4.05个TER值。     

A unified approach for effectively integrating source-side syntactic reordering rules into phrase-based translation

Phrase-based translation models, with sequences of words (phrases) as translation units, achieve state-of-the-art translation performance. However, phrase reordering is a major challenge for this model. Recently, researchers have focused on utilizing syntax to improve phrase reordering. In adding syntactic knowledge into phrase reordering model, using handcrafted or probabilistic syntactic rules to reorder the source-language approximating the target-language word order has been successful in improving translation quality. However, it suffers from propagating the pre-ordering errors to the later translation step (e.g. decoding). In this paper, we propose a novel framework to uniformly represent the handcrafted and probabilistic syntactic rules and integrate them more effectively into phrase-based translation. In the translation phase, for a source sentence to be translated, handcrafted or probabilistic syntactic rules are first acquired from the source parse tree prior to translation, and then instead of reordering the source sentence directly, we input these rules into the decoder and design a new algorithm to apply these rules during decoding. In order to attach more importance to the syntactic rules and distinguish reordering between syntactic and non-syntactic unit reordering, we propose to design respectively a syntactic reordering model and a non-syntactic reordering model. The syntactic rules will guide phrase reordering in decoding within the syntactic reordering model. Extensive experiments on Chinese-to-English translation show that our approach, whether incorporating handcrafted or probabilistic syntactic rules, significantly outperforms the previous methods.     

Dependency treelet translation: the convergence of statistical and example-based machine-translation?

We describe a novel approach to MT that combines the strengths of the two leading corpus-based approaches: Phrasal SMT and EBMT. We use a syntactically informed decoder and reordering model based on the source dependency tree, in combination with conventional SMT models to incorporate the power of phrasal SMT with the linguistic generality available in a parser. We show that this approach significantly outperforms a leading string-based Phrasal SMT decoder and an EBMT system. We present results from two radically different language pairs, and investigate the sensitivity of this approach to parse quality by using two distinct parsers and oracle experiments. We also validate our automated bleu scores with a small human evaluation.     

句法调序的统计机器翻译方法研究

为解决基于短语统计机器翻译存在的调序能力不足的问题,尝试利用句法分析器对基于短语统计机器翻译的输入汉语句子进行句法分析,然后利用转换器进行调序操作,并对部分类型短语进行预先翻译,然后再利用基于短语统计机器翻译的解码器进行翻译。重点测试了汉语中“的”字引导的复杂定语调序、介词短语、特定搭配短语、方位词短语的调序及预翻译产生的效果。实验结果表明,这些调序及预翻译操作可以显著地提高基于短语的统计机器翻译的英文译文结果的BLEU值。     

融合句法解析树的汉-越卷积神经机器翻译

神经机器翻译是目前应用最广泛的机器翻译方法,在语料资源丰富的语种上取得了良好的效果.但是在汉语-越南语这类缺乏双语数据的语种上表现不佳.考虑汉语和越南语在语法结构上的差异性,提出一种融合源语言句法解析树的汉越神经机器翻译方法,利用深度优先遍历得到源语言的句法解析树的向量化表示,将句法向量与源语言词嵌入相加作为输入,训练翻译模型.在汉-越语言对上进行了实验,相较于基准系统,获得了0.6个BLUE值的提高.实验结果表明,融合句法解析树可以有效提高在资源稀缺情况下机器翻译模型的性能.     

Language modeling with probabilistic left corner parsing

We present a novel language model, suitable for large-vocabulary continuous speech recognition, based on parsing with a probabilistic left corner grammar (PLCG). The PLCG probabilities are conditioned on local and non-local features of the partial parse tree, and some of these features are lexical. They are not derived from another stochastic grammar, but directly induced from a treebank, a corpus of text sentences, annotated with parse trees. A context-enriched constituent represents all partial parse trees that are equivalent with respect to the probability of the next parse move. For computational efficiency the parsing problem is represented as a traversal through a compact stochastic network of constituents connected by PLCG moves. The efficiency of the algorithm is due to the fact that the network consists of recursively nested, shared subnetworks. The PLCG-based language model results from accumulating the probabilities of all (partial) paths through this network. Next word probabilities can be computed synchronously with the probabilistic left corner parsing algorithm in one single pass from left to right. They are guaranteed to be normalized, even when pruning less likely paths. Finally, it is shown experimentally that the PLCG-based language model is a competitive alternative to other syntax-based language models, both in efficiency and accuracy.     

Linear algorithm for lexicographic enumeration of CFG parse trees

We study CFG parse tree enumeration in this paper. By dividing the set of all parse trees into infinite hierarchies according to height of parse tree, the hierarchical lexicographic order on the set of parse trees is established. Then grammar-based algorithms for counting and enumerating CFG parse trees in this order are presented. To generate a parse tree of height n, the time complexity is O(n). If τ is a lowest parse tree for its yield, then O(n) =O(∥ gt ∥+ 1), where ∥τ ∥ is the length of the sentence (yield) generated by τ. The sentence can be obtained as a by-product of the parse tree. To compute sentence from its parse tree (needn’t be lowest one), the time complexity is O(node)+O(∥τ ∥ + 1), where node is the number of non-leaf nodes of parse tree τ. To generate both a complete lowest parse tree and its yield at the same time, the time complexity is O(∥τ ∥ + 1). Supported by the National Natural Science Foundation of China (Grant Nos. 60273023, 60721061)     

An application for plagiarized source code detection based on a parse tree kernel

Program plagiarism detection is a task of detecting plagiarized code pairs among a set of source codes. In this paper, we propose a code plagiarism detection system that uses a parse tree kernel. Our parse tree kernel calculates a similarity value between two source codes in terms of their parse tree similarity. Since parse trees contain the essential syntactic structure of source codes, the system effectively handles structural information. The contributions of this paper are two-fold. First, we propose a parse tree kernel that is optimized for program source code. The evaluation shows that our system based on this kernel outperforms well-known baseline systems. Second, we collected a large number of real-world Java source codes from a university programming class. This test set was manually analyzed and tagged by two independent human annotators to mark plagiarized codes. It can be used to evaluate the performance of various detection systems in real-world environments. The experiments with the test set show that the performance of our plagiarism detection system reaches to 93% level of human annotators.     

A syntactically informed reordering model for statistical machine translation

Word reordering is one of the challengeable problems of machine translation. It is an important factor of quality and efficiency of machine translation systems. In this paper, we introduce a novel reordering model based on an innovative structure, named, phrasal dependency tree. The phrasal dependency tree is a modern syntactic structure which is based on dependency relationships between contiguous non-syntactic phrases. The proposed model integrates syntactical and statistical information in the context of log-linear model aimed at dealing with the reordering problems. It benefits from phrase dependencies, translation directions (orientations) and translation discontinuity between translated phrases. In comparison with well-known and popular reordering models such as distortion, lexicalised and hierarchical models, the experimental study demonstrates the superiority of our model in terms of translation quality. Performance is evaluated for Persian → English and English → German translation tasks using Tehran parallel corpus and WMT07 benchmarks, respectively. The results report 1.54/1.7 and 1.98/3.01 point improvements over the baseline in terms of BLEU/TER metrics on Persian → English and German → English translation tasks, respectively. On average our model retrieved a significant impact on precision with comparable recall value with respect to the lexicalised and distortion models.     

基于多目标人工鱼群算法的符号回归

针对现有符号回归方法仅关注拟合误差而忽略模型简化的问题,提出了一种基于多目标的人工鱼群算法,将拟合误差与模型复杂度同时作为目标函数进行优化.以二叉堆对语法树编码,优良分支得以稳定地遗传和继承,也更易解码.在引入蒙版、邻域、小生境、拥挤度等概念的基础上,设计和定义了适用于二叉堆编码的随机游动、觅食、追尾、逃脱等人工鱼行为算子.详尽的实验表明,提出算法在符号回归过程中能获取高质量的Pareto解.此外,对从Pareto前沿上选取折衷解及降低算法内存开销的方法也进行了讨论.     

Semantic Role Labeling of Chinese Nominal Predicates with Dependency-Driven Constituent Parse Tree Structure

This paper explores a tree kernel based method for semantic role labeling （SRL） of Chinese nominal predicates via a convolution tree kernel. In particular, a new parse tree representation structure, called dependency-driven constituent parse tree （D-CPT）, is proposed to combine the advantages of both constituent and dependence parse trees. This is achieved by directly representing various kinds of dependency relations in a CPT-style structure, which employs dependency relation types instead of phrase labels in CPT （Constituent Parse Tree）. In this way, D-CPT not only keeps the dependency relationship information in the dependency parse tree （DPT） structure but also retains the basic hierarchical structure of CPT style. Moreover, several schemes are designed to extract various kinds of necessary information, such as the shortest path between the nominal predicate and the argument candidate, the support verb of the nominal predicate and the head argument modified by the argument candidate, from D-CPT. This largely reduces the noisy information inherent in D-CPT. Finally, a convolution tree kernel is employed to compute the similarity between two parse trees. Besides, we also implement a feature-based method based on D-CPT. Evaluation on Chinese NomBank corpus shows that our tree kernel based method on D-CPT performs significantly better than other tree kernel-based ones and achieves comparable performance with the state-of-the-art feature-based ones. This indicates the effectiveness of the novel D-CPT structure in representing various kinds of dependency relations in a CPT-style structure and our tree kernel based method in exploring the novel D-CPT structure. This also illustrates that the kernel-based methods are competitive and they are complementary with the feature- based methods on SRL.