Improving phrase-based statistical machine translation with morphosyntactic transformation

We present a phrase-based statistical machine translation approach which uses linguistic analysis in the preprocessing phase. The linguistic analysis includes morphological transformation and syntactic transformation. Since the word-order problem is solved using syntactic transformation, there is no reordering in the decoding phase. For morphological transformation, we use hand-crafted transformational rules. For syntactic transformation, we propose a transformational model based on a probabilistic context-free grammar. This model is trained using a bilingual corpus and a broad-coverage parser of the source language. This approach is applicable to language pairs in which the target language is poor in resources. We considered translation from English to Vietnamese and from English to French. Our experiments showed significant BLEU-score improvements in comparison with Pharaoh, a state-of-the-art phrase-based SMT system.     

有限语料汉蒙统计机器翻译调序方法研究

自统计机器翻译技术出现以来,调序一直是语序差异显著的语言对互译系统中的关键问题,基于大规模语料训练的调序方法得到了广泛研究。目前汉蒙双语语料资源十分有限,使得现有的依赖于大规模语料和语言学知识的调序方法难以取得良好效果。该文对已有的相关研究进行了分析,提出了在有限语料条件下的汉蒙统计机器翻译调序方法。该方法依据语言学知识获取对译文语序影响显著的短语类型,研究这些短语类型的调序方案,并融入已有的调序模型实现调序的优化。实验表明该方法在有限语料条件下的效果提升显著。     

Enriching the ER model based on discovered association rules

The entity-relationship (ER) model, a powerful means for business and data modeling, needs to be enriched with new semantics as the real world changes and its understanding improves. This paper attempts at enriching the ER model based on association rules (AR) discovered from large databases by introducing specializations and sub-types into the ER model. The proposed framework is extended to deal with more general, flexible and linguistic knowledge in fuzzy association rules. Moreover, transforming an AR-enriched-ER (AR-EER) schema to a relational database (RDB) schema is also investigated.     

基于LSTM的蒙汉机器翻译的研究

由于内蒙古地区蒙汉机器翻译水平落后、平行双语语料规模较小,利用传统的统计机器翻译方法会出现数据稀疏以及训练过拟合等问题,导致翻译质量不高。针对这种情况,提出基于LSTM的蒙汉神经机器翻译方法,通过利用长短时记忆模型构建端到端的神经网络框架并对蒙汉机器翻译系统进行建模。为了更有效地理解蒙古语语义信息,根据蒙古语的特点将蒙古文单词分割成词素形式,导入模型,并在模型中引入局部注意力机制计算与目标词有关联的源语词素的权重,获得蒙古语和汉语词汇间的对齐概率,从而提升翻译质量。实验结果表明,该方法相比传统蒙汉翻译系统提高了翻译质量。     

The UPF learner translation corpus as a resource for translator training

The learner translation corpus developed at the School of Translation and Interpreting of Pompeu Fabra University in Barcelona is a web-searchable resource created for pedagogical and research purposes. It comprises a multiple translation corpus (English–Catalan) featuring automatic linguistic annotation and manual error annotation, complemented with an interface for monolingual or bilingual querying of the data. The corpus can be used to identify common errors in the students’ work and to analyse their patterns of language use. It provides easy access to error samples and to multiple versions of the same source text sequence to be used as learning materials in various courses in the translator-training university curriculum.     

A rule triggering system for automatic text-to-sign translation

The topic of this paper is machine translation (MT) from French text into French sign language (LSF). After arguing in favour of a rule-based method, it presents the architecture of an original MT system, built on two distinct efforts: formalising LSF production rules and triggering them with text processing. The former is made without any concern for text or translation and involves corpus analysis to link LSF form features to linguistic functions. It produces a set of production rules which may constitute a full LSF production grammar. The latter is an information extraction task from text, broken down in as many subtasks as there are rules in the grammar. After discussing this architecture, comparing it to the traditional methods and presenting the methodology for each task, the paper present the set of production rules found to govern event precedence and duration in LSF and gives a progress report on the implementation of the rule triggering system. With this proposal, it is also hoped to show how MT can benefit today from sign language processing.     

层次短语翻译模型的介词短语调序

在不同的语言中,句法成分的相对位置往往不同,介词短语表现尤为明显,因此正确的对介词短语进行调序对提高翻译质量至关重要。层次短语模型借助于形式语法规则,具有较强的处理长距离调序的能力,但是其并不对短语的句法成分进行区分,这会导致规则的使用不当,从而引起翻译错误。该文在层次短语模型的基础上,针对介词短语进行处理。首先利用条件随机场模型识别出介词短语,然后抽取出带有介词短语的规则,构建一个新的同步上下文无关文法。解码的时候,在这个同步上下文无关文法定义的空间里搜索找到最优的译文。相对于层次短语模型,该方法在我们内部的英汉数据集上调高了0.8个BLEU百分点,在NIST 2008 英汉翻译数据集上提高了0.5个BLEU百分点。     

自纠正词对齐

词对齐是统计机器翻译系统的重要一环,但词对齐的获得往往基于序列模型的计算,而没有考虑语言的结构化信息及语言特征,从而造成词对齐中出现一些不符合语言特征的结果。文中提出一种词对齐的自纠正机制,以纠正词对齐中的错误部分。该机制使用一些语言学上的先验知识,对词对齐结果进行由粗颗粒度到细颗粒度的纠正。首先采用基于标点的方法对句对进行粗粒度化纠正,然后采用基于统计特征的方法对子句对进行细粒度化纠正。该自纠正过程不需要借助任何其他词对齐工具和新语料。实验结果显示,自纠正词对齐显著提高了词对齐的准确率,并提高了机器翻译的质量,其中粗粒度的纠正方法对翻译质量的提高最为显著,细粒度的纠正方法也提升了翻译质量,最终通过结合粗颗粒度和细颗粒度的纠正方法,使翻译结果相对基准系统取得了显著的提高。     

Conceptual Data Modeling for Spatiotemporal Applications

Many exciting potential application areas for database technology manage time-varying, spatial information. In contrast, existing database techniques, languages, and associated tools provide little built-in support for the management of such information. The focus of this paper is on enhancing existing conceptual data models with new constructs, improving their ability to conveniently model spatiotemporal aspects of information. The goal is to speed up the data modeling process and to make diagrams easier to comprehend and maintain. Based on explicitly formulated ontological foundations, the paper presents a small set of new, generic modeling constructs that may be introduced into different conceptual data models. The ER model is used as the concrete context for presenting the constructs. The semantics of the resulting spatiotemporal ER model, STER, is given in terms of the underlying ER model. STER is accompanied by a textual counterpart, and a CASE tool based on STER is currently being implemented, using the textual counterpart as its internal representation.     

基于变分信息瓶颈的半监督神经机器翻译

变分方法是机器翻译领域的有效方法, 其性能较依赖于数据量规模. 然而在低资源环境下, 平行语料资源匮乏, 不能满足变分方法对数据量的需求, 因此导致基于变分的模型翻译效果并不理想. 针对该问题, 本文提出基于变分信息瓶颈的半监督神经机器翻译方法, 所提方法的具体思路为: 首先在小规模平行语料的基础上, 通过引入跨层注意力机制充分利用神经网络各层特征信息, 训练得到基础翻译模型; 随后, 利用基础翻译模型, 使用回译方法从单语语料生成含噪声的大规模伪平行语料, 对两种平行语料进行合并形成组合语料, 使其在规模上能够满足变分方法对数据量的需求; 最后, 为了减少组合语料中的噪声, 利用变分信息瓶颈方法在源与目标之间添加中间表征, 通过训练使该表征具有放行重要信息、阻止非重要信息流过的能力, 从而达到去除噪声的效果. 多个数据集上的实验结果表明, 本文所提方法能够显著地提高译文质量, 是一种适用于低资源场景的半监督神经机器翻译方法.     

MARS: A Statistical Semantic Parsing and Generation-Based Multilingual Automatic tRanslation System

We present MARS (Multilingual Automatic tRanslation System), a research prototype speech-to-speech translation system. MARS is aimed at two-way conversational spoken language translation between English and Mandarin Chinese for limited domains, such as air travel reservations. In MARS, machine translation is embedded within a complex speech processing task, and the translation performance is highly effected by the performance of other components, such as the recognizer and semantic parser, etc. All components in the proposed system are statistically trained using an appropriate training corpus. The speech signal is first recognized by an automatic speech recognizer (ASR). Next, the ASR-transcribed text is analyzed by a semantic parser, which uses a statistical decision-tree model that does not require hand-crafted grammars or rules. Furthermore, the parser provides semantic information that helps further re-scoring of the speech recognition hypotheses. The semantic content extracted by the parser is formatted into a language-independent tree structure, which is used for an interlingua based translation. A Maximum Entropy based sentence-level natural language generation (NLG) approach is used to generate sentences in the target language from the semantic tree representations. Finally, the generated target sentence is synthesized into speech by a speech synthesizer.Many new features and innovations have been incorporated into MARS: the translation is based on understanding the meaning of the sentence; the semantic parser uses a statistical model and is trained from a semantically annotated corpus; the output of the semantic parser is used to select a more specific language model to refine the speech recognition performance; the NLG component uses a statistical model and is also trained from the same annotated corpus. These features give MARS the advantages of robustness to speech disfluencies and recognition errors, tighter integration of semantic information into speech recognition, and portability to new languages and domains. These advantages are verified by our experimental results.     

基于强制对齐的层次短语模型过滤和优化

该文提出一种层次短语模型过滤和优化方法。该方法在采用传统方法训练得到层次短语规则的基础上,通过强制对齐同时构建源语言和目标语言的解析树,从中过滤并抽取对齐的层次短语规则,最后利用这些规则重新估计翻译模型的翻译概率。该方法不需要引入任何语言学知识,适合大规模语料训练模型。在大规模中英翻译评测任务中,采用该方法训练的模型与传统层次短语模型相比,不仅能够过滤50%左右规则,同时获得0.8～1.2 BLEU值的提高。     

Constructing <Emphasis Type="Italic">n</Emphasis>-gram rules for natural language models through exploring the limitation of the Zipf–Mandelbrot law

The Zipf–Mandelbrot law is widely used to model a power-law distribution on ranked data. One of the best known applications of the Zipf–Mandelbrot law is in the area of linguistic analysis of the distribution of words ranked by their frequency in a text corpus. By exploring known limitations of the Zipf–Mandelbrot law in modeling the actual linguistic data from different domains in both printed media and online content, a new algorithm is developed to effectively construct n-gram rules for building natural language (NL) models required for a human-to-computer interface. The construction of statistically-oriented n-gram rules is based on a new computing algorithm that identifies the area of divergence between Zipf–Mandelbrot curve and the actual frequency distribution of the ranked n-gram text tokens extracted from a large text corpus derived from the online electronic programming guide (EPG) for television shows and movies. Two empirical experiments were carried out to evaluate the EPG-specific language models created using the new algorithm in the context of NL-based information retrieval systems. The experimental results show the effectiveness of the algorithm for developing low-complexity concept models with high coverage for the user’s language models associated with both typed and spoken queries when interacting with a NL-based EPG search interface.     

融合单语语言模型的汉越伪平行语料生成

神经机器翻译在资源丰富的语种上取得了良好的翻译效果,但是由于数据稀缺问题在汉语-越南语这类低资源语言对上的性能不佳。目前缓解该问题最有效的方法之一是利用现有资源生成伪平行数据。考虑到单语数据的可利用性,在回译方法的基础上,首先将利用大量单语数据训练的语言模型与神经机器翻译模型进行融合,然后在回译过程中通过语言模型融入语言特性,以此生成更规范质量更优的伪平行数据,最后将生成的语料添加到原始小规模语料中训练最终翻译模型。在汉越翻译任务上的实验结果表明,与普通的回译方法相比,通过融合语言模型生成的伪平行数据使汉越神经机器翻译的BLEU值提升了1.41个百分点。     

基于成分共享的英汉小句对齐语料库标注体系研究

英汉小句对齐语料库服务于英语和汉语小句的语法结构对应关系研究和应用,对于语言理论和语言翻译(包括人的翻译和机器翻译)有重要意义。前人的语法理论和相关语料库的工作对于小句复合体和小句的界定缺乏充分研究,在理论上有缺陷,难以支持自然语言处理的应用。该文首先为英汉小句对齐语料库的建设做理论准备。从近年提出的汉语小句复合体的理论出发,该文界定了成分共享的概念,基于话头共享和引语共享来界定英语的小句和小句复合体,使小句和小句复合体具有功能的完整性和单一性。在此基础上,该文设计了英汉小句对齐的标注体系,包括英语NT小句标注和汉语译文生成及组合。语料库的标注表明,在小句复合体层面上英汉翻译涉及到的结构变换,其部件可以限制为英语小句和话头、话体,无须涉及话头和话体内部的结构。基于这些工作的英汉小句对齐语料库为语言本体研究和英汉语言对比、英汉机器翻译等应用提供了结构化的标注样本。     

Improving Structural Statistical Machine Translation for Sign Language With Small Corpus Using Thematic Role Templates as Translation Memory

This paper presents a structural statistical machine translation (SSMT) model to deal with the data sparseness problem that occurs as a result of the necessarily small corpus to translate Chinese into Taiwanese Sign Language (TSL). A parallel bilingual corpus was developed, and linguistic information from the Sinica Treebank is adopted for Chinese sentence analysis. The synchronous context free grammar (SCFG) was adopted to convert a Chinese structure to the corresponding TSL structure and then extract a translation memory which comprises the thematic relations between the grammar rules of both structures. In structural translation, the statistical MT (SMT) approach was used to align the thematic roles in the grammar rules and the translation memory provides the reference templates for TSL structure translation. Finally, the agreement information for TSL verbs was labeled for enriching the expressiveness of the translated TSL sequence. Several experiments were conducted to evaluate the translation performance and the communication effectiveness for the deaf. The evaluation results demonstrate that the proposed approach outperforms a baseline statistical MT system using the same small corpus, especially for the translation of long sentences.