Automating visual language generation

A system to generate and interpret customized visual languages in given application areas is presented. The generation is highly automated. The user presents a set of sample visual sentences to the generator. The generator uses inference grammar techniques to produce a grammar that generalizes the initial set of sample sentences, and exploits general semantic information about the application area to determine the meaning of the visual sentences in the inferred language. The interpreter is modeled on an attribute grammar. A knowledge base, constructed during the generation of the system, is then consulted to construct the meaning of the visual sentence. The architecture of the system and its use in the application environment of visual text editing (inspired by the Heidelberg icon set) enhanced with file management features are reported     

基于用法的现代汉语连词结构短语识别研究

连词能够连接词语、短语、小句、句子乃至句群,连词结构短语是连词所连接对象的一种,不同的连词形成不同长度、不同关系的连词结构短语。该文根据虚词用法知识库中的连词用法,构建了连词结构短语识别规则,实现了基于规则的连词结构短语识别,并将连词用法作为特征采用条件随机场模型实现了基于统计的连词结构短语识别。实验结果表明,统计的识别效果高于规则的识别效果,连词用法能够较好地用于连词结构短语的识别中。     

A computational grammar for Persian based on GPSG

In this paper, we present our attempts to design and implement a large-coverage computational grammar for the Persian language based on the Generalized Phrase Structured Grammar (GPSG) model. This grammatical model was developed for continuous speech recognition (CSR) applications, but is suitable for other applications that need the syntactic analysis of Persian. In this work, we investigate various syntactic structures relevant to the modern Persian language, and then describe these structures according to a phrase structure model. Noun (N), Verb (V), Adjective (ADJ), Adverb (ADV), and Preposition (P) are considered basic syntactic categories, and X-bar theory is used to define Noun phrases, Verb phrases, Adjective phrases, Adverbial phrases, and Prepositional phrases. However, we have to extend Noun phrase levels in X-bar theory to four levels due to certain complexities in the structure of Noun phrases in the Persian language. A set of 120 grammatical rules for describing different phrase structures of Persian is extracted, and a few instances of the rules are presented in this paper. These rules cover the major syntactic structures of the modern Persian language. For evaluation, the obtained grammatical model is utilized in a bottom-up chart parser for parsing 100 Persian sentences. Our grammatical model can take 89 sentences into account. Incorporating this grammar in a Persian CSR system leads to a 31% reduction in word error rate.     

基于语义模式分解的英语介词语义分析和汉译

在研究英语介词相关短语和句式的基础上,给出了语义模式的概念,构建了介词相关短语语义模式库、相关句式语义模式库、主虚量库和固定搭配知识库。根据介词相关短语语义模式特点,提出了一种基于语义模式分解的介词语义分析和汉译算法,结合相关句式语义模式库和固定搭配知识库,对英语介词进行语义分析和汉译。实验表明,利用该文方法能有效解决英语介词汉译的问题。     

基于短语替换的汉越伪平行句对生成

神经机器翻译在语料丰富的语种上取得了良好的翻译效果,但是在汉语-越南语这类双语资源稀缺的语种上性能不佳,通过对现有小规模双语语料进行词级替换生成伪平行句对可以较好地缓解此类问题。考虑到汉越词级替换中易存在一词多译问题,该文对基于更大粒度的替换进行了研究,提出了一种基于短语替换的汉越伪平行句对生成方法。利用小规模双语语料进行短语抽取构建短语对齐表,并通过在维基百科中抽取的实体词组对其进行扩充,在对双语数据的汉语和越南语分别进行短语识别后,利用短语对齐表中与识别出的短语相似性较高的短语对进行替换,以此实现短语级的数据增强,并将生成的伪平行句对与原始数据一起训练最终的神经机器翻译模型。在汉-越翻译任务上的实验结果表明,通过短语替换生成的伪平行句对可以有效提高汉-越神经机器翻译的性能。     

基于汉语自然语言信息查询的计算机理解实现

文中根据汉语的二层语义分析结构。深层语义结构-语意指向，表层语义结构-语义指向：针对四种汉语疑问句型进行具体分析其在计算机理解实现中的理论方法和规则；在进行正确的汉语词汇切分之后；根据语意指向与语义指向建立起各词汇的本体言语和本体行为标注，进行组合词汇生成符合语意的短语，再进行本体行为转化为本体言语的研究，归结为专业数据库的语义；最后通过实验系统得以验证。     

基于用户兴趣的文本摘要方法研究

提出的摘要方法,以句子为基本抽取单位,以兴趣主题词为句子的加权特征。对句子基于潜语义聚类,提出语义结构,这种结构对摘要质量的提高有重要作用,并且提出了较为客观和有效的摘要评价方法。实验表明,本文方法是行之有效的。     

The potential of Swetra — A multilanguage MT system

One may indicate the potentials of an MT system by stating what text genres it can process, e.g., weather reports and technical manuals. This approach is practical, but misleading, unless domain knowledge is highly integrated in the system. Another way to indicate which fragments of language the system can process is to state its grammatical potentials, or more formally, which languages the grammars of the system can generate. This approach is more technical and less understandable to the layman (customer), but it is less misleading, since it stresses the point that the fragments which can be translated by the grammars of a system need not necessarily coincide exactly with any particular genre. Generally, the syntactic and lexical rules of an MT system allow it to translate many sentences other than those belonging to a certain genre. On the other hand it probably cannot translate all the sentences of a particular genre. Swetra is a multilanguage MT system defined by the potentials of a formal grammar (standard referent grammar) and not by reference to a genre. Successful translation of sentences can be guaranteed if they are within a specified syntactic format based on a specified lexicon. The paper discusses the consequences of this approach (Grammatically Restricted Machine Translation, GRMT) and describes the limits set by a standard choice of grammatical rules for sentences and clauses, noun phrases, verb phrases, sentence adverbials, etc. Such rules have been set up for English, Swedish and Russian, mainly on the basis of familiarity (frequency) and computer efficiency, but restricting the grammar and making it suitable for several languages poses many problems for optimization. Sample texts — newspaper reports — illustrate the type of text that can be translated with reasonable success among Russian, English and Swedish.     

Sentence entailment in compositional distributional semantics

Distributional semantic models provide vector representations for words by gathering co-occurrence frequencies from corpora of text. Compositional distributional models extend these from words to phrases and sentences. In categorical compositional distributional semantics, phrase and sentence representations are functions of their grammatical structure and representations of the words therein. In this setting, grammatical structures are formalised by morphisms of a compact closed category and meanings of words are formalised by objects of the same category. These can be instantiated in the form of vectors or density matrices. This paper concerns the applications of this model to phrase and sentence level entailment. We argue that entropy-based distances of vectors and density matrices provide a good candidate to measure word-level entailment, show the advantage of density matrices over vectors for word level entailments, and prove that these distances extend compositionally from words to phrases and sentences. We exemplify our theoretical constructions on real data and a toy entailment dataset and provide preliminary experimental evidence.     

The potential of swetra—A multilanguage MT system

One may indicate the potentials of an MT system by stating what text genres it can process, e.g., weather reports and technical manuals. This approach is practical, but misleading, unless domain knowledge is highly integrated in the system. Another way to indicate which fragments of language the system can process is to state its grammatical potentials, or more formally, which languages the grammars of the system can generate. This approach is more technical and less understandable to the layman (customer), but it is less misleading, since it stresses the point that the fragments which can be translated by the grammars of a system need not necessarily coincide exactly with any particular genre. Generally, the syntactic and lexical rules of an MT system allow it to translate many sentences other than those belonging to a certain genre. On the other hand it probably cannot translate all the sentences of a particular genre. Swetra is a multilanguage MT system defined by the potentials of a formal grammar (standard referent grammar) and not by reference to a genre. Successful translation of sentences can be guaranteed if they are within a specified syntactic format based on a specified lexicon. The paper discusses the consequences of this approach (Grammatically Restricted Machine Translation, GRMT) and describes the limits set by a standard choice of grammatical rules for sentences and clauses, noun phrases, verb phrases, sentence adverbials, etc. Such rules have been set up for English, Swedish and Russian, mainly on the basis of familiarity (frequency) and computer efficiency, but restricting the grammar and making it suitable for several languages poses many problems for optimization. Sample texts—newspaper reports—illustrate the type of text that can be translated with reasonable success among Russian, English and Swedish.     

基于统计特征的Quality Phrase挖掘方法

Quality Phrase挖掘是从文本语料库中提取有意义短语的过程,是文档摘要、信息检索等任务的基础。然而现有的无监督短语挖掘方法存在候选短语质量不高、Quality Phrase的特征权重平均分配的问题。本文提出基于统计特征的Quality Phrase挖掘方法,将频繁N-Gram挖掘、多词短语组合性约束及单词短语拼写检查相结合,保证了候选短语的质量;引入公共知识库对候选短语添加类别标签,实现了Quality Phrase特征权重的分配,并考虑特征之间相互影响设置惩罚因子调整权重比例;按照候选短语的特征加权函数得分排序,提取Quality Phrase。实验结果表明,基于统计特征的Quality Phrase挖掘方法明显提高了短语挖掘的精度,与最优的无监督短语挖掘方法相比,精确率、召回率及F1-Score分别提升了5.97%,1.77%和4.02%。     

英语人体隐喻的识别与汉译

词语隐喻意义的机器识别和正确翻译是机译的难点。提出了语义语法模式的概念、提取方法以及一种基于语义语法模式集、固定搭配集和变量表示库的英语隐喻识别与汉译的合一算法。语义语法模式集包括语法隐喻模式集、词汇隐喻模式集、字面意义模式集、短语模式集、构句模式集等子集。以人体词为研究对象,构建了英语人体词的语义语法模式集、固定搭配集和变量表示库。实验表明,该方法能有效解决英语人体隐喻的识别与汉译问题。     

SyMSS: A syntax-based measure for short-text semantic similarity

Sentence and short-text semantic similarity measures are becoming an important part of many natural language processing tasks, such as text summarization and conversational agents. This paper presents SyMSS, a new method for computing short-text and sentence semantic similarity. The method is based on the notion that the meaning of a sentence is made up of not only the meanings of its individual words, but also the structural way the words are combined. Thus, SyMSS captures and combines syntactic and semantic information to compute the semantic similarity of two sentences. Semantic information is obtained from a lexical database. Syntactic information is obtained through a deep parsing process that finds the phrases in each sentence. With this information, the proposed method measures the semantic similarity between concepts that play the same syntactic role. Psychological plausibility is added to the method by using previous findings about how humans weight different syntactic roles when computing semantic similarity. The results show that SyMSS outperforms state-of-the-art methods in terms of rank correlation with human intuition, thus proving the importance of syntactic information in sentence semantic similarity computation.     

语法和语义相结合的中文对话系统问题理解研究

针对中文口语问句的表达多样性对对话系统问题理解带来的挑战,该文采用“在语法结构之上获取语义知识”的设计理念,提出了一种语法和语义相结合的口语对话系统问题理解方法。首先人工编制了独立于领域和应用方向的语法知识库,进而通过句子压缩模块简化复杂句子,取得结构信息,再进行问题类型模式识别,得到唯一确定问题的语义组织方法、查询策略和应答方式的句型模式。另一方面,根据领域语义知识库,从源句子中提取相应的语义信息,并根据识别到的句型模式所对应的知识组织方法进行语义知识组织,完成对问句的理解。该文的方法被应用到开发的中文手机导购对话系统。测试结果表明,该方法能有效地完成对话流程中的用户问题理解。     

基于隐马尔可夫模型的主观句识别

文本情感倾向分析是意见挖掘和情感文摘中的一个重要环节,而在情感倾向分析中涉及到的是主观性文本,这就需要进行主客观文本分类。当前的主客观文本分类方法主要是基于特征词典的概率统计方法,并没有考虑特征之间的语法与语义关系。针对该问题,该文提出一种基于隐马尔可夫模型(HMM)的主观句识别方法。该方法首先从训练语料中抽取具有明显分类效果的七类主客观特征,然后每个句子应用HMM进行特征角色类别标注,并依据标注的结果计算句子的权重,最终识别主观句。该方法在第六届中文倾向性分析评测任务中能够有效地识别主观句。     

支持背景知识的多维端到端短语识别算法研究

目前,实体识别与依存关系分析,采用的主要是基于监督学习的深度端到端方法.这种方法存在两个问题:不能引入背景知识;不能识别出自然语言的多粒度、嵌套特征.为了解决以上问题,提出了基于短语窗口的依存句法标注规则,并标注了中文短语窗口数据集(CPWD),同时设计了配套的多维端到端短语识别模型(MDM模型).该标注规则以短语为最...     

The suffix-signature method for searching for phrases in text

We present a new algorithm to find all occurrences of a given phrase based on the data structure known as a suffix array and using a corresponding array of signatures. With this algorithm, matches to phrases of moderate length can be found with expected search time of one disk access to the text and one disk access to its index. To achieve this performance for phrases of up to five words in length requires an index having total size of approximately 120% of the size of the text. The algorithm guarantees a worst case search performance of two disk accesses to the text per phrase search. Experiments with actual data ranging in size from 6Mb to 550Mb and with actual query patterns derived from logs of searches on the World Wide Web show that the approach is applicable in practice to a variety of texts and realistic phrase searches.     

Semantic separator learning and its applications in unsupervised Chinese text parsing

Grammar learning has been a bottleneck problem for a long time. In this paper, we propose a method of semantic separator learning, a special case of grammar learning. The method is based on the hypothesis that some classes of words, called semantic separators, split a sentence into several constituents. The semantic separators are represented by words together with their part-of-speech tags and other information so that rich semantic information can be involved. In the method, we first identify the semantic separators with the help of noun phrase boundaries, called subseparators. Next, the argument classes of the separators are learned from corpus by generalizing argument instances in a hypernym space. Finally, in order to evaluate the learned semantic separators, we use them in unsupervised Chinese text parsing. The experiments on a manually labeled test set show that the proposed method outperforms previous methods of unsupervised text parsing.     

基于小句复合体的句子边界自动识别研究

自然语言文本的语法结构层次包括语素、词语、短语、小句、小句复合体、语篇等.其中,语素、词、短语等相关处理技术已经相对成熟,而句子的概念至今未有公认的、适用于语言信息处理的界定.该文重新审视了语言学中句子的定义和自然语言处理中句子的切分问题,提出了中文句子切分的任务;基于小句复合体理论将句子定义为最小的话头自足的标点句序...     

基于多粒度特征的文本生成评价方法

近年来,基于预训练语言模型的文本生成评价方法得到了广泛关注,其通过计算两个句子间子词粒度的相似度来评价生成文本的质量.但是对于越南语、泰语等存在大量黏着语素的语言,单个音节或子词不能独立成词表达语义,仅基于子词粒度匹配的方法并不能够完整表征两个句子间的语义相似关系.基于此,该文提出一种基于子词、音节、词组等多粒度特征的...