An automatic speech recognition system for spontaneous Punjabi speech corpus

Automatic speech recognition is the central part of the wheel towards the natural person-to-machine interaction technique. Due to the high disparity of speaking styles, speech recognition surely demands composite methods to constitute this irregularity. A speech recognition method can work in numerous distinct states such as speaker dependent/independent speech, isolated/continuous/spontaneous speech recognition, for less to very large vocabulary. The Punjabi language is being spoken by concerning 104 million peoples in India, Pakistan and other countries with Punjabi migrants. The Punjabi language is written in Gurmukhi writing in Indian Punjab, while in Shahmukhi writing in Pakistani Punjab. In the paper, the objective is to build the speaker independent automatic spontaneous speech recognition system for the Punjabi language. The system is also capable to recognize the spontaneous Punjabi live speech. So far, no work has to be achieved in the area of spontaneous speech recognition system for the Punjabi language. The user interfaces for Punjabi live speech system is created by using the java programming. Till now, automatic speech system is trained with 6012 Punjabi words and 1433 Punjabi sentences. The performance measured in terms of recognition accuracy which is 93.79% for Punjabi words and 90.8% for Punjabi sentences.     

英汉《小王子》抽象语义图结构的对比分析

AMR(抽象语义表示)是国际上一种新的句子语义表示方法,有着接近于中间语言的表示能力,其研发者已经建立了英文《小王子》等AMR语料库。AMR与以往的句法语义表示方法的最大不同在于两个方面,首先采用图结构来表示句子的语义;其次允许添加原句之外的概念节点来表示隐含的语义。该文针对汉语特点,在制定中文AMR标注规范的基础上,标注完成了中文版《小王子》的AMR语料库,标注一致性的Smatch值为0.83。统计结果显示,英汉双语含图结构句子具有很高的相关性,且含有图的句子比例高达40%左右,额外添加的概念节点则存在较大差异。最后讨论了AMR在汉语句子语义表示以及跨语言对比方面的优势。     

语义及句法特征多注意力交互的医疗自动问答

针对中文医疗自动问答任务,为了捕捉问答句中重要的句法信息和语义信息,提出引入图卷积神经网络捕捉句法信息,并添加多注意力池化模块实现问答句的语序特征和句法特征联合学习的方法。在BERT模型学习问答句的高阶语义特征基础上,利用双向门控循环单元描述句子的全局语义特征,以及引入图卷积神经网络编码句子的语法结构信息,以与双向门控循环单元所获取的序列特征呈现互补关系;通过多注意力池化模块对问答对的不同语义空间上的编码向量进行两两交互,并着重突出问答对的共现特征;通过衡量问答对的匹配分数,找出最佳答案。实验结果表明,在cMedQA v1.0和cMedQA v2.0数据集上,相比于主流的深度学习方法,所提方法的ACC@1有所提高。实验证明引入图卷积神经网络和多注意力池化模块的集成算法能有效提升自动问答模型的性能。     

基于语义依存图库的兼语句句模研究

句子语义分析是语言研究深入发展的客观要求,也是当前制约语言信息处理技术深度应用的主要因素。在探索深层语义分析方法的基础上,该文根据汉语的特点,提出了一整套语义依存图的构建方法,并建立了一个包含30 000个句子的语义依存图库。以兼语句为重点研究对象,该文研究了语料库中所有纯粹的兼语句所对应的句模情况,进而试图构建基于语义依存图的句模系统,总结句型和句模的映射规则,从而为更好的建立语义自动分析模型提供相应的知识库。
     

Building a Language‐Independent Discourse Parser using Universal Networking Language

Discourse parsing has become an inevitable task to process information in the natural language processing arena. Parsing complex discourse structures beyond the sentence level is a significant challenge. This article proposes a discourse parser that constructs rhetorical structure (RS) trees to identify such complex discourse structures. Unlike previous parsers that construct RS trees using lexical features, syntactic features and cue phrases, the proposed discourse parser constructs RS trees using high‐level semantic features inherited from the Universal Networking Language (UNL). The UNL also adds a language‐independent quality to the parser, because the UNL represents texts in a language‐independent manner. The parser uses a naive Bayes probabilistic classifier to label discourse relations. It has been tested using 500 Tamil‐language documents and the Rhetorical Structure Theory Discourse Treebank, which comprises 21 English‐language documents. The performance of the naive Bayes classifier has been compared with that of the support vector machine (SVM) classifier, which has been used in the earlier approaches to build a discourse parser. It is seen that the naive Bayes probabilistic classifier is better suited for discourse relation labeling when compared with the SVM classifier, in terms of training time, testing time, and accuracy.     

用自然语言处理改进问答系统的研究和实现

问答系统是当前人工智能应用的一个重要领域，而传统的基于模式匹配方法的问答系统具有很大的局限性。该文研究了基于HMM模型、图句法分析、词典和规则的自然语言处理算法。将这些算法应用到问答系统中，扩展了对话管理模块，对用户的自然语言进行语义分析，从而实现对话的语义块识别、主题识别和对话信息提取，提高了系统对复杂用户输入的处理能力，克服了传统方法的不足，并使用Java实现了一个实验系统。     

Parsing Arabic using induced probabilistic context free grammar

The importance of the parsing task for NLP applications is well understood. However developing parsers remains difficult because of the complexity of the Arabic language. Most parsers are based on syntactic grammars that describe the syntactic structures of a language. The development of these grammars is laborious and time consuming. In this paper we present our method for building an Arabic parser based on an induced grammar, PCFG grammar. We first induce the PCFG grammar from an Arabic Treebank. Then, we implement the parser that assigns syntactic structure to each input sentence. The parser is tested on sentences extracted from the treebank (1650 sentences).We calculate the precision, recall and f-measure. Our experimental results showed the efficiency of the proposed parser for parsing modern standard Arabic sentences (Precision: 83.59 %, Recall: 82.98 % and F-measure: 83.23 %).     

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.     

基于源语言句法增强解码的神经机器翻译方法

当前性能最优的机器翻译模型之一Transformer基于标准的端到端结构,仅依赖于平行句对,默认模型能够自动学习语料中的知识;但这种建模方式缺乏显式的引导,不能有效挖掘深层语言知识,特别是在语料规模和质量受限的低资源环境下,句子解码缺乏先验约束,从而造成译文质量下降。为了缓解上述问题,提出了基于源语言句法增强解码的神经机器翻译（SSED）方法,显式地引入源语句句法信息指导解码。所提方法首先利用源语句句法信息构造句法感知的遮挡机制,引导编码自注意力生成一个额外的句法相关表征;然后将句法相关表征作为原句表征的补充,通过注意力机制融入解码,共同指导目标语言的生成,实现对模型的先验句法增强。在多个IWSLT及WMT标准机器翻译评测任务测试集上的实验结果显示,与Transformer基线模型相比,所提方法的BLEU值提高了0.84~3.41,达到了句法相关研究的最先进水平。句法信息与自注意力机制融合是有效的,利用源语言句法可指导神经机器翻译系统的解码过程,显著提高译文质量。     

Formalisation method for the text expressed knowledge

This paper describes a method of knowledge representation as a set of text expressed statements. The method is based on the identification of word-categories/phrases and their semantic relationships within the observed statement. Furthermore, the identification of semantic relationships between words/phrases using wh-questions that clarify the role of the word/phrase in the relationship is described. A conceptual model of the computer system based on the formalization method of text-expressed knowledge is proposed. The subsystem text formalization is described in detail, especially its parts: syntactic analysis of the sentence, sentence formalization, phrase structure grammar and lexicon. The phrase structure grammar is formed by induction and it is used to generate the language of the formalized notation of a sentence. The derivation of grammar is based on the simple phrase structure grammar which was used for the syntactical analysis of informal language notation. In its base, the suggested method translates sentences of the informal language into formal language sentences which are generated by the derivated phrase structure grammar. Current limitations of the method that also set the path of its further development are shown. Next concrete steps in the development of the method are also described.     

Learning the “Whys”: Discovering design rationale using text mining — An algorithm perspective

Collecting design rationale (DR) and making it available in a well-organized manner will better support product design, innovation and decision-making. Many DR systems have been developed to capture DR since the 1970s. However, the DR capture process is heavily human involved. In addition, with the increasing amount of DR available in archived design documents, it has become an acute problem to research a new computational approach that is able to capture DR from free textual contents effectively. In our previous study, we have proposed an ISAL (issue, solution and artifact layer) model for DR representation. In this paper, we focus on algorithm design to discover DR from design documents according to the ISAL modeling. For the issue layer of the ISAL model, we define a semantic sentence graph to model sentence relationships through language patterns. Based on this graph, we improve the manifold-ranking algorithm to extract issue-bearing sentences. To discover solution–reason bearing sentences for the solution layer, we propose building up two sentence graphs based on candidate solution-bearing sentences and reason-bearing sentences respectively, and propagating information between them. For artifact information extraction, we propose two term relations, i.e. positional term relation and mutual term relation. Using these relations, we extend our document profile model to score the candidate terms. The performance and scalability of the algorithms proposed are tested using patents as research data joined with an example of prior art search to illustrate its application prospects.     

基于图卷积网络融合依存信息的事件检测方法

句子级别细粒度的事件检测任务旨在对触发词进行识别与分类。针对现有事件检测方法中存在的过度平滑及缺乏依存类型信息的问题,提出了一种基于图卷积网络融合依存信息的事件检测方法。该模型首先使用双向长短期记忆网络对句子进行编码,同时根据依存分析构建多阶句法图和依存句法图;然后利用图卷积网络融合句子的依存信息,从而有效地利用多跳信息和依存标签信息。在自动文本抽取数据集上进行实验,在触发词识别和分类这两个子任务中分别取得了81.7%和78.6%的F1值。结果显示,提出的方法能更加有效地捕获句子中的事件信息,提升了事件检测的效果。     

一种基于情感句模的文本情感分类方法

考虑到同类型的情感句往往具有相同或者相似的句法和语义表达模式,该文提出了一种基于情感句模的文本情感自动分类方法。首先,将情感表达相关句模人工分为3大类105个二级分类;然后,设计了一种利用依存特征、句法特征和同义词特征的句模获取方法,从标注情感句中半自动地获取情感句模。最后,通过对输入句进行情感句模分类实现文本情感分类。在NLP&CC2013中文微博情绪分类评测语料及RenCECps博客语料的实验结果显示,该文提出的分类方法准确率显著高于基于词特征支持向量机分类器。     

REPRESENTATION AND CONTROL STRATEGIES FOR LARGE KNOWLEDGE DOMAINS: An Application to NLP

The design issues encountered during the development of a natural language processor (NLP) for the Italian language are described. The focus is on strategic aspects, namely representation and control, and their implementation with first-order logic. The complexity and the size of the knowledge domain (press agency releases on finance and economics) do not present severe restrictions in the sentence structure; hence a considerable design effort for data structures and control algorithms was required. Logic proved to be an important tool for implementing in a modular and efficient way the knowledge sources along with the programs that derive the morphologic, syntactic, and semantic features of sentences. As for the data structures, we found a considerable advantage in separating linguistic knowledge in three sources: morphologic, syntactic, and semantic. This resulted in a clear and systematic representation scheme and reduced the complexity of the parsing system.     

基于N-gram超核的中文倾向性句子识别

倾向性句子识别是文本倾向性分析的重要组成部分,其目的是识别文档中具有情感倾向的主观性句子。中文句子的倾向性不仅与倾向词有关,而且还跟句法、语义等因素有关,这使得倾向性句子识别不能简单地从词语的倾向性来统计得到。该文提出了一种基于N-gram超核的中文倾向性句子识别分类算法。该算法基于句子的句法、语义等特征构造N-gram超核函数,并采用基于该超核函数的支持向量机分类器识别中文倾向性句子。实验结果表明,与多项式核、N-gram核等单核函数相比,基于N-gram超核的中文倾向性句子识别算法在一定程度上能有效识别倾向性句子。     

面向特定方面情感分析的图卷积过度注意(ASGCN-AOA)模型

针对注意力机制与卷积神经网络模型在方面级情感分析研究中,无法发掘句中长距离单词与相关句法约束间依存关系,而将与语法无关的上下文单词作为方面情感判断线索的问题,该文提出了一种结合图卷积网络(GCN)和注意-过度注意(AOA)神经网络的方面级情感分类模型(ASGCN-AOA).首先,采用双向长短时记忆网络来对上下文词之间特...     

校园导航系统Easy Nav的设计与实现

本文介绍了校园导航口语对话系统EasyNav的设计与实现。在分析了口语对话系统的特点和要求之后,我们提出了适合于对话系统的基于规则的语言理解流程。在这一流程中,句法分析使用GLR分析器处理上下文无关文法(CFG),获取句子结构特征以便为语义分析服务,句法规则照顾到覆盖率和准确率间的平衡。语义分析使用考虑句法约束条件的模板匹配方法,以获取话者意图为目标,并消除句法分析引入的歧义。这一设计的优点是系统容易搭建,也容易扩展。     

OntoMap: an ontology-based architecture to perform the semantic mapping between an interlingua and software components

This paper is about the use of natural language to communicate with computers. Most researches that have pursued this goal consider only requests expressed in English. A way to facilitate the use of several languages in natural language systems is by using an interlingua. An interlingua is an intermediary representation for natural language information that can be processed by machines. We propose to convert natural language requests into an interlingua [universal networking language (UNL)] and to execute these requests using software components. In order to achieve this goal, we propose OntoMap, an ontology-based architecture to perform the semantic mapping between UNL sentences and software components. OntoMap also performs component search and retrieval based on semantic information formalized in ontologies and rules.     

Event Pattern Analysis and Prediction at Sentence Level using Neuro-Fuzzy Model for Crime Event Detection

Classifying the sentences that describe Events is an important task for many applications. In this paper, Event patterns are identified and extracted at sentence level using term features. The terms that trigger Events along with the sentences are extracted from web documents. The sentence structures are analyzed using POS tags. A hierarchal sentence classification model is proposed by considering specific term features of the sentence and the rules are derived. The rules fail to define a clear boundary between the patterns and create ambiguity and impreciseness. To overcome this, suitable fuzzy rules are derived which gives importance to all term features of the sentence. The fuzzy rules are constructed with more variables and generate sixteen patterns. Artificial Neuro-Fuzzy Inference System (ANFIS) model is proposed for training and classifying the sentence patterns for capturing the knowledge present in sentences. The obtained patterns are assigned linguistic grades based on previous classification knowledge. These grades represent the type and quality of information in the patterns. The membership function is used to evaluate the fuzzy rules. The patterns share the membership values between [0–1] which determines the weights for each pattern. Later, higher weighted patterns are considered to build Event Corpus, which helps in retrieving useful and interested information of Event Instances. The performance of the proposed approach classification is evaluated for ‘Crime’ Event by crawling documents from WWW and also evaluated for benchmark dataset for ‘Die’ Event. It is found that the performance of the proposed approach is encouraging when compared with recently proposed similar approaches.     

用于关系抽取的注意力图长短时记忆神经网络

关系抽取是信息获取中一项关键技术.句子结构树能够捕获单词之间的长距离依赖关系,已被广泛用于关系抽取任务中.但是,现有方法存在过度依赖句子结构树本身信息而忽略外部信息的不足.本文提出一种新型的图神经网络模型,即注意力图长短时记忆神经网络(attention graph long short term memory neu...