A Natural Language Generation Algorithm for Greek by Using Hole Semantics and a Systemic Grammatical Formalism

This work is about the progress of previous related work based on an experiment to improve the intelligence of robotic systems,with the aim of achieving more linguistic communication capabilities between humans and robots.In this paper,the authors attempt an algorithmic approach to natural language generation through hole semantics and by applying the OMAS-III computational model as a grammatical formalism.In the original work,a technical language is used,while in the later works,this has been replaced by a limited Greek natural language dictionary.This particular effort was made to give the evolving system the ability to ask questions,as well as the authors developed an initial dialogue system using these techniques.The results show that the use of these techniques the authors apply can give us a more sophisticated dialogue system in the future.

Recommender System for Information Retrieval Using Natural Language Querying Interface Based in Bibliographic Research for Naïve Users

With the increasing of data on the internet, data analysis has become inescapable to gain time and efficiency, especially in bibliographic information retrieval systems. We can estimate the number of actual scientific journals points to around 40,000 with about four million articles published each year. Machine learning and deep learning applied to recommender systems had become unavoidable whether in industry or in research. In this current, we propose an optimized interface for bibliographic information retrieval as a running example, which allows different kind of researchers to find their needs following some relevant criteria through natural language understanding. Papers indexed in Web of Science and Scopus are in high demand. Natural language including text and linguistic-based techniques, such as tokenization, named entity recognition, syntactic and semantic analysis, are used to express natural language queries. Our Interface uses association rules to find more related papers for recommendation. Spanning trees are challenged to optimize the search process of the system.

Classification of Conversational Sentences Using an Ensemble Pre-Trained Language Model with the Fine-Tuned Parameter

Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.

The research and realization about automatic abstracting based on text clustering and natural language understanding

A method of realization of automatic abstracting based on text clustering and natural language understanding is explored, aimed at overcoming shortages of some current methods. The method makes use of text clustering and can realize automatic abstracting of multi-documents. The algo- rithm of twice word segmentation based on the title and first sentences in paragraphs is investigated. Its precision and recall is above 95 %. For a specific domain on plastics, an automatic abstracting system named TCAAS is implemented. The precision and recall of multi-document’s automatic ab- stracting is above 75 %. Also, the experiments prove that it is feasible to use the method to develop a domain automatic abstracting system, which is valuable for further in-depth study.

Intuitionistic Logic as the Implement of Incremental Model Construction for Natural Language

The process of understanding natural language can be viewed as the process of model construction. This paper? employing Kripke frame for intuitionistic logic semantics as the implement of model construction for natural language, introduces a method of incremental model construction.

Chinese spoken language understanding in SHTQS

Spoken dialogue systems are an active research field with wide applications. But the differences in the Chinese spoken dialogue system are not as distinct as that of English. In Chinese spoken dialogues, there are many language phenomena. Firstly, most utterances are ill-formed. Secondly, ellipsis, anaphora and negation are also widely used in Chinese spoken dialogue. Determining how to extract semantic information from incomplete sentences and resolve negation, anaphora and ellipsis is crucial. SHTQS (Shanghai Transportation Query System) is an intelligent telephone-based spoken dialogue system providing information about the best route between any two sites in Shanghai. After a brief description of the system, the natural language processing is emphasized. Speech recognition sentences unavoidably contain errors. In language sequence processing procedures, these errors can be easily passed to the later parts and take on a ripple effect. To detect and recover these from errors as early as possible, language-processing strategies are specially considered. For errors resulting from divided words in speech recognition, segmentation and POS Tagging approaches that can rectify these errors are designed. Since most of the inquiry utterances are ill-formed and negation, anaphora and ellipsis are common language phenomena, the language understanding must be adequately adaptive. So, a partial syntactic parsing scheme is adopted and a chart algorithm is used. The parser is based on unification grammar. The semantic frame that extracts from the best arc set of the chart is used to represent the meaning of sentences. The negation, anaphora and ellipsis are also analyzed and corresponding processing approaches are presented. The accuracy of the language processing part is 88.39% and the testing result shows that the language processing strategies are rational and effective.

A Hierarchical Combination Method for Computer Understanding of Chinese Language

On the basis of the characteristics of Chinese language such.as simple and uniform structure, distinct hierarchy and construction by word order and function words, and in the view of the human cognitive mechanism, a hierarchical combination method for computer understanding of Chinese language is put forward in this paper. By this method, the whole information of a sentence is hierarchically combined from the partial information of the basic units of it, with the unification operation under attribute description frames. This method is perfect in combining syntax analysis with semantic analysis, easy to implement, and very suitable for the computer understanding system for processing Chinese language.

诠释学视域下GPT语言模型的本质及特征

GPT语言模型的设计思路具有自然语言理解的诠释学思维特征,但本质上该模型并不具备诠释学语言理解的属人性基础;GPT语言模型将智能视为一种本体论层面以语言作为媒介的整体性系统“涌现”结果,缺乏诠释的“本体论—主体性”地位和“本体论—整体性”结构;GPT语言模型采用的生成式和预训练的设计思路凸显了诠释学理解和解释的“历史性”特征,而数据训练的强化和“思维链”的对话机制使该模型具有“效果历史”和“视域融合”的语言理解特征;GPT语言模型在模拟人类“偏见性”认知方面取得进步,但与人类的“偏见—个性化”和“偏见—创造性”能力相比存在根本差异;GPT语言模型形成了“诠释学循环”的语言对话机制,但其并不具有自身独立的“诠释学循环”实践基础,因此,难以达成诠释学意义上的语言理解共识。

基于HNC的中文文本校对系统模型的研究

针对中文文本在语法错误和语义错误校对方面存在的问题,基于HNC理论构建了一个中文文本校对系统模型,该模型利用传统查错系统和HNC句类分析系统相结合的方法,并对日常报刊杂志100篇文章进行了实验,与word2003查错系统相比,在解决语法层次和语义层次上的错误,该方法有明显优势.

基于文本知识增强的问题生成模型

预训练语言模型在大规模训练数据和超大规模算力的基础上,能够从非结构化的文本数据中学到大量的知识。针对三元组包含信息有限的问题,提出利用预训练语言模型丰富知识的问题生成方法。首先,利用预训练语言模型中丰富的知识增强三元组信息,设计文本知识生成器,将三元组中的信息转化为子图描述,丰富三元组的语义;然后,使用问题类型预测器预测疑问词,准确定位答案所在的领域,从而生成语义正确的问题,更好地控制问题生成的效果;最后,设计一种受控生成框架对关键实体和疑问词进行约束,保证关键实体和疑问词同时出现在问题中,使生成的问题更加准确。在公开数据集WebQuestion和PathQuestion中验证所提模型的性能。实验结果表明,与现有模型LFKQG相比,所提模型的BLUE-4、METEOR、ROUGE-L指标在WebQuestion数据集上分别提升0.28、0.16、0.22个百分点,在PathQuestion数据集上分别提升0.8、0.39、0.46个百分点。

基于HNC理论的语义相关度计算方法

语义相关度计算对于语句的语义结构的分析有重要作用,同时也可以用于自动文本分类和信息检索的语义处理。该文以HNC理论的概念基元树表和词语的HNC符号映射方法为依据,提出并实现了语义相关度计算的方法。论文分析了这种方法的优势,并验证了它在语句语义结构分析中的作用。

基于提示学习的生成式医疗对话理解方法

任务型对话系统中的对话理解模块的目标是将用户输入的自然语言转换成结构化的形式,但在面向诊断的医疗对话系统中,现有方法存在如下问题:1)无法支持精准医疗所需的信息粒度,如给出某一症状的严重程度;2)难以同时满足医疗领域中多样化的槽值表示形式,如“症状”等可能含有非连续与嵌套实体的抽取型槽以及“否定”等分类型槽。文中提出了一种基于提示学习的多层次生成式医疗对话理解方法。针对问题1),用多层次槽结构替代当前对话理解任务中单层的槽结构,以表示更细粒度的信息,之后采用一种基于对话风格提示的生成式方法,利用提示字符模拟医患对话,从多轮交互中获得多层次信息。针对问题2),提出在推理过程中使用一种受限的解码策略,使模型能够以统一的方式处理意图识别与分类型和抽取型的槽填充任务,避免复杂的建模。此外,针对医疗领域缺少标注数据的问题,提出了一种两阶段训练策略,以充分利用大规模的无标注医疗对话语料来提升性能。针对含有多层次槽结构的医疗对话理解任务标注并发布了一个数据集,包含4722条对话,涉及17种意图与74种槽。实验结果表明,所提方法能够有效解析医疗对话中的各种复杂实体,相比已有的生成方法,其性能高出2.18%,而在小样本的场景下两阶段训练最高能提高模型5.23%的性能。

基于BERT的双特征融合注意力的方面情感分析模型

方面情感分析旨在预测句子或文档中一个特定方面的情感极性,现阶段大部分的研究都是使用注意力机制对上下文进行建模。然而,目前情感分类模型在使用BERT模型计算表征之间的依赖关系抽取特征时,大多未根据不同的语境背景考虑上下文信息,导致建模后的特征缺乏上下文的语境信息。同时,方面词的重要性未能得到充分的重视而影响模型整体分类的性能。针对上述问题,提出双特征融合注意力方面情感分析模型(DFLGA-BERT),分别设计了局部与全局的特征抽取模块,充分捕捉方面词和上下文的语义关联。并将一种改进的“准”注意力添加到DFLGA-BERT的全局特征抽取器中,使模型学习在注意力的融合中使用减性注意力以削弱噪声产生的负面影响。基于条件层规泛化(CLN)设计了局部特征和全局特征的特征融合结构来更好地融合局部和全局特征。在SentiHood和SemEval 2014 Task 4数据集上进行了实验,实验结果表明,与基线模型相比该模型在融入了上下文语境特征后取得了较明显的性能提升。

基于HNC的现代汉语词语知识库建设

基于HNC的汉语词语知识库是HNC知识库系统的重要组成部分,它以句类知识为核心,从概念、语句和语境三个层面提供汉语理解处理所需的知识。经过10多年的建设,该库已达到80,000多词的规模,成为中文信息处理、汉语教学和汉语本体研究的宝贵资源。

自然语言理解新思路─HNC

ＨＮＣ是 Ｈｉｅｒａｒｃｈｉａｌ Ｎｅｔｗｏｒｋ ｏｆ Ｃｏｎｃｅｐｔｓ概念层次网络）的简称，是关于自然语言理解处理的一个理论体系．这个理论体系的基本思路与传统计算语言理论有本质的不同．它展示了自然语言理解的突破性进展，其三大理论要点集中体现了ＨＮＣ理论在自然语言表述和处理模式上的突破，本文描述笔者对 ＨＮＣ理论这种“突破”的认识。

基于HNC概念框架的检索模型

针对目前搜索引擎难以按用户个性需求给出精确答案的现状,把概念层次网络理论的语义分析技术应用到搜索引擎中,在概念层次网络理论的基础上将自然语言的词、句和句群映射为概念符号、句类和概念框架,通过比较用户输入与网页文本的概念符号和概念框架,给出与用户输入语义上相同或相近的搜索结果,可以使搜索结果更加准确、更加符合用户意图,这有助于推动和促进下一代搜索引擎的个性化和智能化研究。

旅游领域意图识别和槽位填充联合建模方法研究

构建了基于BERT的双向连接模式BERT-based Bi-directional Association Model(BBAM)以实现在意图识别和槽位填充之间建立双向关系的目标,来实现意图识别与槽位填充的双向关联,融合两个任务的上下文信息,对意图识别与槽位填充两个任务之间的联系进行深度挖掘,从而优化问句理解的整体性能.为了验证模型在旅游领域中的实用性和有效性,通过远程监督和人工校验构建了旅游领域问句数据集TFQD(Tourism Field Question Dataset),BBAM模型在此数据集上的槽填充任务F 1值得分为95.21%,意图分类准确率(A)为96.71%,整体识别准确率(A_(sentence))高达89.62%,显著优于多种基准模型.所提出的模型在ATIS和Snips两个公开数据集上与主流联合模型进行对比实验后,结果表明其具备一定的泛化能力.

面向医疗领域的意图识别方法研究

针对意图标签数量过多带来的识别挑战,提出一种拆分策略,旨在降低训练的复杂度,并在解码层采用双头MLP(多层感知机)结合CRF(条件随机场)的机制,精准预测意图标签。实验结果表明,该方法的F_(1)值相较于基准模型提升至78%。此外,为验证大语言模型在意图识别任务上的表现,提出了一种面向医疗领域的大语言模型意图识别方法,其在处理多样化信息的数据时,能够深入探索并提炼出丰富的知识,将其与提出的深度学习方法进行对比,并深入分析二者在数据集上表现存在差异的原因,可为医疗领域意图识别的后续研究提供重要参考依据。

基于HNC句类体系的句子语义研究

HNC(概念层次网络)理论的句类体系建立了句子的语义表述模式,本文从七个方面讨论了运用这一体系来开展句子语义研究的基本内容。