一种基于小字典不对等语料的跨语言词嵌入方法

双语词嵌入通常采用从源语言空间到目标语言空间映射,通过源语言映射嵌入到目标语言空间的最小距离线性变换实现跨语言词嵌入。然而大型的平行语料难以获得,词嵌入的准确率难以提高。针对语料数量不对等、双语语料稀缺情况下的跨语言词嵌入问题,该文提出一种基于小字典不对等语料的跨语言词嵌入方法,首先对单语词向量进行归一化,对小字典词对正交最优线性变换求得梯度下降初始值,然后通过对大型源语言(英语)语料进行聚类,借助小字典找到与每一聚类簇相对应的源语言词,取聚类得到的每一簇词向量均值和源语言与目标语言对应的词向量均值,建立新的双语词向量对应关系,将新建立的双语词向量扩展到小字典中,使得小字典得以泛化和扩展。最后,利用泛化扩展后的字典对跨语言词嵌入映射模型进行梯度下降求得最优值。在英语—意大利语、德语和芬兰语上进行了实验验证,实验结果证明该文方法可以在跨语言词嵌入中减少梯度下降迭代次数,减少训练时间,同时在跨语言词嵌入上表现出较好的正确率。     

基于Hash结构词典的双向最大匹配分词法

针对当前自然语言处理中中文分词基于词典的机械分词方法,正序词典不能作为逆向最大匹配分词词典以及反序词典维护困难的问题,提出一种新的词典构造方法并设计了相应的双向最大匹配算法,同时在算法中加入了互信息歧义处理模块来处理分词中出现的交集型歧义。该算法可以在分词的过程中显著提高分词的精确度,适用于对词语切分精度要求较高的中文语言处理系统。     

A method of creating new valency entries

Information on subcategorization and selectional restrictions in a valency dictionary is important for natural language processing tasks such as monolingual parsing, accurate rule-based machine translation and automatic summarization. In this paper we present an efficient method of assigning valency information and selectional restrictions to entries in a bilingual dictionary, based on information in an existing valency dictionary. The method is based on two assumptions: words with similar meaning have similar subcategorization frames and selectional restrictions; and words with the same translations have similar meanings. Based on these assumptions, new valency entries are constructed for words in a plain bilingual dictionary, using entries with similar source-language meaning and the same target-language translations. We evaluate the effects of various measures of semantic similarity.     

基于Transfer和Triangulation融合的中介语统计机器翻译方法

为了解决在构建统计机器翻译系统过程中所面临的双语平行数据缺乏的问题,该文提出了一种新的基于中介语的翻译方法,称为Transfer-Triangulation方法。该方法可以在基于中介语的翻译过程中,结合传统的Transfer方法和Triangulation方法的优点,利用解码中介语短语的方法改进短语表。该文方法是在使用英语作为中介语的德-汉翻译任务中进行评价的。实验结果表明,相比于传统的基于中介语方法的基线系统,该方法显著提高了翻译性能。     

The Existence of a Short Sequence of Admissible Pivots to an Optimal Basis in LP and LCP

We say an LP (linear programming) is fully nondegenerate if both the primal and the dual problems are nondegenerate. In this paper, we prove the existence of a sequence of | B ∖ B | admissible pivot from any basis B (not necessarily feasible) to the unique optimal basis B , if the given LP has an optimal solution and is fully nondegenerate. Here admissible pivots are those pivots (satisfying certain sign conditions) that exist if the current LP dictionary is not terminal, i.e., neither optimal, inconsistent nor dual inconsistent. A natural extension of the result to LCPs (linear complementarity problems) with sufficient matrices is given. The existence itself does not yield a strongly polynomial pivot algorithm for LPs but provides us with a good motivation to study the class of admissible pivot methods for LPs, as opposed to the narrower class of simplex methods for which the shortest sequence of pivots is not known to be polynomially bounded.     

Topic-aware pivot language approach for statistical machine translation

The pivot language approach for statistical machine translation （SMT） is a good method to break the resource bottleneck for certain language pairs. However, in the implementation of conventional approaches, pivot- side context information is far from fully utilized, resulting in erroneous estimations of translation probabilities. In this study, we propose two topic-aware pivot language approaches to use different levels of pivot-side context. The first method takes advantage of document-level context by assuming that the bridged phrase pairs should be similar in the document-level topic distributions. The second method focuses on the effect of local context. Central to this approach are that the phrase sense can be reflected by local context in the form of probabilistic topics, and that bridged phrase pairs should be compatible in the latent sense distributions. Then, we build an interpolated model bringing the above methods together to further enhance the system performance. Experimental results on French-Spanish and French-German translations using English as the pivot language demonstrate the effectiveness of topic-based context in pivot-based SMT.     

Within-word pronunciation variation modeling for Arabic ASRs: a direct data-driven approach

Pronunciation variation is a major obstacle in improving the performance of Arabic automatic continuous speech recognition systems. This phenomenon alters the pronunciation spelling of words beyond their listed forms in the pronunciation dictionary, leading to a number of out of vocabulary word forms. This paper presents a direct data-driven approach to model within-word pronunciation variations, in which the pronunciation variants are distilled from the training speech corpus. The proposed method consists of performing phoneme recognition, followed by a sequence alignment between the observation phonemes generated by the phoneme recognizer and the reference phonemes obtained from the pronunciation dictionary. The unique collected variants are then added to dictionary as well as to the language model. We started with a Baseline Arabic speech recognition system based on Sphinx3 engine. The Baseline system is based on a 5.4 hours speech corpus of modern standard Arabic broadcast news, with a pronunciation dictionary of 14,234 canonical pronunciations. The Baseline system achieves a word error rate of 13.39%. Our results show that while the expanded dictionary alone did not add appreciable improvements, the word error rate is significantly reduced by 2.22% when the variants are represented within the language model.     

Stochastic learning of multi-instance dictionary for earth mover’s distance-based histogram comparison

Dictionary plays an important role in multi-instance data representation. It maps bags of instances to histograms. Earth mover’s distance (EMD) is the most effective histogram distance metric for the application of multi-instance retrieval. However, up to now, there is no existing multi-instance dictionary learning methods designed for EMD-based histogram comparison. To fill this gap, we develop the first EMD-optimal dictionary learning method using stochastic optimization method. In the stochastic learning framework, we have one triplet of bags, including one basic bag, one positive bag, and one negative bag. These bags are mapped to histograms using a multi-instance dictionary. We argue that the EMD between the basic histogram and the positive histogram should be smaller than that between the basic histogram and the negative histogram. Base on this condition, we design a hinge loss. By minimizing this hinge loss and some regularization terms of the dictionary, we update the dictionary instances. The experiments over multi-instance retrieval applications shows its effectiveness when compared to other dictionary learning methods over the problems of medical image retrieval and natural language relation classification.

     

一种基于词素媒介的汉蒙统计机器翻译方法

汉蒙语形态差异性及平行语料库规模小制约了汉蒙统计机器翻译性能的提升。该文将蒙古语形态信息引入汉蒙统计机器翻译中,通过将蒙古语切分成词素的形式,构造汉语词和蒙古语词素,以及蒙古语词素和蒙古语的映射关系,弥补汉蒙形态结构上的非对称性,并将词素作为中间语言,通过训练汉语—蒙古语词素以及蒙古语词素-蒙古语统计机器翻译系统,构建出新的短语翻译表和调序模型,并采用多路径解码及多特征的方式融入汉蒙统计机器翻译。实验结果表明,将基于词素媒介构建出的短语翻译表和调序模型引入现有统计机器翻译方法,使得译文在BLEU值上比基线系统有了明显提高,一定程度上消解了数据稀疏和形态差异对汉蒙统计机器翻译的影响。该方法是一种通用的方法,通过词素和短语两个层面信息的结合,实现了两种语言在形态结构上的对称,不仅适用于汉蒙统计机器翻译,还适用于形态非对称且低资源的语言对。     

运用改进的分词方法进行外国译名识别的研究

该文首先介绍了基于词典的分词算法的语言模型和一种基于词典分词算法：最大词频分词法。分析了基于词典的分词算法的语言模型,指出其无法处理未登录词的原因。针对此原因,提出了引入动态词典的方法,将最大词频分词算法和局部频率法相结合以解决未登录词中译名识别的问题。最后,给出了一个系统实现。     

一种支持混合语言的并行查询纠错方法

中文信息检索系统中的查询语句包含中文字、拼音、英文等多种形式,而有些查询语句过长,不利于纠错处理。现有的查询纠错方法不能很好的解决中文检索系统中的混合语言与中文长查询的问题。为了解决上述两个问题,该文提出了一种支持混合语言的并行纠错方法。该方法通过对混合语言统一编码,建立统一编码语言模型和异构字符词典树,并根据语言特点制定相应的编辑规则对查询词语进行统一处理,其中,针对中文长查询,提出双向并行的纠错模型。为了并行处理查询语句,我们在字符词典树和语言模型的基础上提出了逆向字符词典树和逆向语言模型的概念。模型中使用的训练语料库是从用户查询日志、网页点击日志、网页链接信息等文件中提取的高质量文本。实验表明,与单向查询纠错相比,支持混合语言的并行纠错方法在准确率上提升了9%,召回率降低了3%,在速度上提升了40%左右。     

基于半监督的汉缅双语词典构建方法

汉缅双语词典是开展机器翻译、跨语言检索等研究的重要数据资源.当前在种子词典的基础上使用迭代自学习的方法在平行语料中抽取双语词典取得了较好的效果,然而针对低资源语言汉语-缅语的双语词典抽取任务,由于双语平行资源匮乏,基于迭代自学习的方法不能得到有效的双语词向量表示,致使双语词典抽取模型准确度较低.研究表明,可比语料中相似...     

Effects of digital dictionary format on incidental acquisition of spelling knowledge and cognitive load during second language learning: Click-on vs. key-in dictionaries

Recent research has shown that students involved in computer-based second language learning prefer to use a digital dictionary in which a word can be looked up by clicking on it with a mouse (i.e., click-on dictionary) to a digital dictionary in which a word can be looked up by typing it on a keyboard (i.e., key-in dictionary). This study investigated whether digital dictionary format also differentially affects students' incidental acquisition of spelling knowledge and cognitive load during second language learning. A comparison between a click-on dictionary condition, a key-in dictionary condition, and a non-dictionary control condition for 45 Taiwanese students learning English as a foreign language revealed that learners who used a key-in dictionary invested more time investment on dictionary consultation than learners who used a click-on dictionary. However, on a subsequent unexpected spelling test the key-in group invested less time investment and performed better than the click-on group. The theoretical and practical implications of the results are discussed.     

Sparse coding of i-vector/JFA latent vector over ensemble dictionaries for language identification systems

Computing sparse representation (SR) over an exemplar dictionary is time consuming and computationally expensive for large dictionary size. This also requires huge memory requirement for saving the dictionary. In order to reduce the latency and to achieve some diversity, ensemble of exemplar dictionary based language identification (LID) system is explored. The full diversity can be obtained if each of the exemplar dictionary contains only one feature vector from each of the language class. To achieve full diversity, a large number of multiple dictionaries are required; thus needs to compute SR for a particular test utterance as many times. The other solution to reduce the latency is to use a learned dictionary. The dictionary may contain unequal number of dictionary atoms and it is not guaranteed that each language class information is present. It totally depends upon the number of data and its variations. Motivated by this, language specific dictionary is learned, and then concatenated to form a single learned dictionary. Furthermore, to overcome the problem of ensemble exemplar dictionary based LID system, we investigated the ensemble of learned-exemplar dictionary based LID system. The proposed approach achieves the same diversity and latency as that of ensemble exemplar dictionary with reduced number of learned dictionaries. The proposed techniques are applied on two spoken utterance representations: the i-vector and the JFA latent vector. The experiments are performed on 2007 NIST LRE, 2009 NIST LRE and AP17-OLR datasets in closed set condition.     

关系数据库上泛关系查询与中文查询语言的接口

本文初步探讨了实现关系数据库上泛关系查询与自然语言查询接口的一种方法, 文章对其中的若干问题如词典的组织、翻译算法等作了比较详细的讨论并通过实例进行了具体的说明。     

基于远监督的语义知识资源扩展研究

语义知识资源蕴含了深刻的语言学理论,是语言学知识和语言工程的重要接口。该文以形容词句法语义词典为研究对象,探索对语义知识资源自动扩展的方法。该文的目标是利用大规模语料库,扩展原有词典的词表及其对应的句法格式。具体方法是根据词的句法格式将词典的词分类,将待扩展的新词通过分类器映射到原有词典的词中,以此把词典扩展问题转化为多类分类问题。依据的原理是词典词和待扩展新词在大规模语料中句法结构的相似性。该文通过远监督的方法构造训练数据,避免大量的人工标注。训练过程结合了浅层机器学习方法和深度神经网络,取得了有意义的成果。实验结果显示,深度神经网络能够习得句法结构信息,有效提升匹配的准确率。     

引入语义匹配和语言评价的跨语言图像描述

目的 由于缺乏图像与目标语言域的成对数据,现有的跨语言描述方法都是基于轴(源)语言转化为目标语言,由于转化过程中的语义噪音干扰,生成的句子存在不够流畅以及与图像视觉内容关联弱等问题,为此,本文提出了一种引入语义匹配和语言评价的跨语言图像描述模型。方法 首先,选择基于编码器—解码器的图像描述基准网络框架。其次,为了兼顾图像及其轴语言所包含的语义知识,构建了一个源域语义匹配模块;为了学习目标语言域的语言习惯,还构建了一个目标语言域评价模块。基于上述两个模块,对图像描述模型进行语义匹配约束和语言指导：1)图像&轴语言域语义匹配模块通过将图像、轴语言描述以及目标语言描述映射到公共嵌入空间来衡量各自模态特征表示的语义一致性。2)目标语言域评价模块依据目标语言风格,对所生成的描述句子进行语言评分。结果 针对跨语言的英文图像描述任务,本文在MS COCO(Microsoft common objects in context)数据集上进行了测试。与性能较好的方法相比,本文方法在BLEU(bilingual evaluation understudy)-2、BLEU-3、BLEU-4和METE...     

English–Thai Structure–Based Machine Translation

We propose an alternative method of machine–aided translation: Structure–Based Machine Translation (SBMT). SBMT uses language structure matching techniques to reduce complicated grammar rules and provide efficient and feasible translation results. SBMT comprises the following four features: (1) source language input sentence analysis; (2) source language sentence transformation into target language structure; (3) dictionary lookup; and (4) semantic disambiguation or word sense disambiguation (WSD) for correct output selection. SBMT has been designed and a prototype system has been implemented that generates satisfactory translations.     

中波广播发射台的一种扩充故障树诊断方法

针对某中波广播发射机台,利用故障树和故障字典方法相结合的新型故障诊断方法--扩充的故障树诊断技术实现了发射机的实时故障诊断功能,并建立了广播发射机故障树的拓扑结构,给出了故障字典的建立方法和故障诊断的具体实现过程,同时将该方法在Windows系统环境下采用Borland C 进行了编程实现.     

Word reordering on multiple pivots for the Japanese and Indonesian language pair

Machine Translation - We investigated multiple pivot approaches for the Japanese and Indonesian (Ja–Id) language pair in phrase-based statistical machine translation (SMT). We used four...