A Joint Entity Relation Extraction Model Based on Relation Semantic Template Automatically Constructed

The joint entity relation extraction model which integrates the semantic information of relation is favored by relevant researchers because of its effectiveness in solving the overlapping of entities,and the method of defining the semantic template of relation manually is particularly prominent in the extraction effect because it can obtain the deep semantic information of relation.However,this method has some problems,such as relying on expert experience and poor portability.Inspired by the rule-based entity relation extraction method,this paper proposes a joint entity relation extraction model based on a relation semantic template automatically constructed,which is abbreviated as RSTAC.This model refines the extraction rules of relation semantic templates from relation corpus through dependency parsing and realizes the automatic construction of relation semantic templates.Based on the relation semantic template,the process of relation classification and triplet extraction is constrained,and finally,the entity relation triplet is obtained.The experimental results on the three major Chinese datasets of DuIE,SanWen,and FinRE showthat the RSTAC model successfully obtains rich deep semantics of relation,improves the extraction effect of entity relation triples,and the F1 scores are increased by an average of 0.96% compared with classical joint extraction models such as CasRel,TPLinker,and RFBFN.

Enhancing Relational Triple Extraction in Specific Domains:Semantic Enhancement and Synergy of Large Language Models and Small Pre-Trained Language Models

In the process of constructing domain-specific knowledge graphs,the task of relational triple extraction plays a critical role in transforming unstructured text into structured information.Existing relational triple extraction models facemultiple challenges when processing domain-specific data,including insufficient utilization of semantic interaction information between entities and relations,difficulties in handling challenging samples,and the scarcity of domain-specific datasets.To address these issues,our study introduces three innovative components:Relation semantic enhancement,data augmentation,and a voting strategy,all designed to significantly improve the model’s performance in tackling domain-specific relational triple extraction tasks.We first propose an innovative attention interaction module.This method significantly enhances the semantic interaction capabilities between entities and relations by integrating semantic information fromrelation labels.Second,we propose a voting strategy that effectively combines the strengths of large languagemodels(LLMs)and fine-tuned small pre-trained language models(SLMs)to reevaluate challenging samples,thereby improving the model’s adaptability in specific domains.Additionally,we explore the use of LLMs for data augmentation,aiming to generate domain-specific datasets to alleviate the scarcity of domain data.Experiments conducted on three domain-specific datasets demonstrate that our model outperforms existing comparative models in several aspects,with F1 scores exceeding the State of the Art models by 2%,1.6%,and 0.6%,respectively,validating the effectiveness and generalizability of our approach.

The Exchange from Relational Schemas to XML Schemas Based on Semantic Constraints

XML is the standard format for data exchange between inter-enterprise applications on the Internet. To facilitate data exchange, industry groups define public document type that specify the format of the XML data to be exchanged between their applications. In this paper, we propose a new method to solve the problem of automating the conversion of relational data into XML. During the conversion, we considers not only the structure of relational schemas, but also semantic constraints such as inclusion dependencies during the translation--it takes as input a relational schema where multiple tables are interconnected through inclusion dependencies and converts it into an X-Schema. Finally, in order to validate our proposal, we present experimental results using real schemas.

A Study on Semantic Relations of“and”Used in Chinese EFL Learners’Narrative Writing

Studies on conjunctions used by Chinese English as a Foreign Language(EFL)learners over the past ten years have focused mainly on the use of conjunctions in argumentative writing,and there is little empirical work on conjunction“and”in narrative writing.The purpose of this paper is to explore the characteristics of the semantic relations of“and”used in the narrative writing of Chinese EFL learners from the perspective of text coherence.Through analysis of narrative writing of 29 sophomores,this study investigates the characteristics of semantic relations expressed by the conjunction“and”and the differences in the use of semantic relations of“and”between high-score and low-score writing.The results show different frequencies of the use of semantic relations of“and”.ELF learners prefer to use the term“and”to build progressive relation and parallel relation more than any other relation.Both high-score and low-score writing use a sizable number of“and”to build progressive relation and parallel relation,but high-score writing obviously contains more guiding relations and fewer supplementary relations.These findings have some pedagogical implications for teaching transitions.

The Application of Semantic Relations and Denotative and Connotative Meanings in Translation Practice

Semantics,the study of meaning,is closely connected with translation,the practice of transferring meaning.The paper uses a lot of examples based on real translation practice to prove that semantics plays a very important role in translation practice.Understanding and making good use of semantic relations,including synonymy,polysemy,homonymy and antonymy,are quite important for a translator to deal with some complicated semantic problems in translation practice.The paper also discusses the concept of denotative and connotative meanings,two basic types of meaning in Semantics.Denotation means the literal meaning of a word which is given in dictionaries;and connotation,the associative and suggestive meanings of a word in its context.Be cause of cultural difference,words with the same denotations may have totally different connotations,which is why the concept of denotation and connotation plays a very important role in English/Chinese translation.In order to translate a text into another language correctly,translator must totally understand the meaning of the original word,both denotative and connotative mean ing,and be aware of the potential connotations of the word in the target language.

Mechanisms underlying syntactic and semantic processing of Chinese simple sentences Evidence from event-related brain potentials

This study sought to test the processing of three types of sentences in Chinese, as correct sentences, semantic violation sentences, and sentences containing semantic and syntactic violations, based on the following sentence pattern： ＂subject （noun） ＋ yi/gang/zheng ＋ predicate （verb）＂. Event-related potentials on the scalp were recorded using 32-channel electroencephalography. Compared with correct sentences, target words elicited an early left anterior negativity （N400） and a later positivity （P600） over frontal, central and temporal sites in sentences involving semantic violations. In addition, when sentences contained both semantic and syntactic violations, the target words elicited a greater N400 and P600 distributed in posterior brain areas. These results indicate that Chinese sentence comprehension involves covert grammar processes.

Rules-based object-relational databases ontology construction

To solve the problems of shaving and reusing information in the information system, a rules-based ontology constructing approach from object-relational databases is proposed. A 3-tuple ontology constructing model is proposed first. Then, four types of ontology constructing rules including class, property, property characteristics, and property restrictions ave formalized according to the model. Experiment results described in Web ontology language prove that our proposed approach is feasible for applying in the semantic objects project of semantic computing laboratory in UC Irvine. Our approach reduces about twenty percent constructing time compared with the ontology construction from relational databases.

Exploiting multi-context analysis in semantic image classification

As the popularity of digital images is rapidly increasing on the Internet, research on technologies for semantic image classification has become an important research topic. However, the well-known content-based image classification methods do not overcome the so-called semantic gap problem in which low-level visual features cannot represent the high-level semantic content of images. Image classification using visual and textual information often performs poorly since the extracted textual features are often too limited to accurately represent the images. In this paper, we propose a semantic image classification ap- proach using multi-context analysis. For a given image, we model the relevant textual information as its multi-modal context, and regard the related images connected by hyperlinks as its link context. Two kinds of context analysis models, i.e., cross-modal correlation analysis and link-based correlation model, are used to capture the correlation among different modals of features and the topical dependency among images induced by the link structure. We propose a new collective classification model called relational support vector classifier (RSVC) based on the well-known Support Vector Machines (SVMs) and the link-based cor- relation model. Experiments showed that the proposed approach significantly improved classification accuracy over that of SVM classifiers using visual and/or textual features.

Evaluating Relational Ranking Queries Involving both Text Attributes and Numeric Attributes

In many database applications, ranking queries may reference both text and numeric attributes, where the ranking functions are based on both semantic distances/similarities for text attributes and numeric distances for numeric attributes. In this paper, we propose a new method for evaluating such type of ranking queries over a relational database. By statistics and training, this method builds a mechanism that combines the semantic and numeric distances, and the mechanism can be used to balance the effects of text attributes and numeric attributes on matching a given query and tuples in database search. The basic idea of the method is to create an index based on WordNet to expand the tuple words semantically for text attributes and on the information of numeric attributes. The candidate results for a query are retrieved by the index and a simple SQL selection statement, and then top-N answers are obtained. The results of extensive experiments indicate that the performance of this new strategy is efficient and effective.

Semantic Features and Applications in Translation of English Words in Pairs

English words in pairs are a special form of English idioms, which have different kinds and are used widely. For English learners, words in pairs are one of the difficult points. This paper discusses their form patterns, semantic relations, grammatical functions, rhetoric features and their application in translation. Its purpose is to help learners understand and use them accurately and correctly so as to improve language expressing ability.

On Application of the “Sameness Relation” in Chinese-English Translation Practice

The theme of this article is mainly to explore the application of the"Sameness Relation"into the Chinese-English trans-lation practice.In view of the theoretical guidance of sameness relation into the practice of the Chinese-English translation,this pa-per first points out a liable mistake in Chinese-English translation due to an inadequate knowledge of the"Sense Relations",andthen defines the linguistic term"sense relations","Sameness relation""and relevant "Semantics".Next this text continues to ana-lyze how the sameness relations are applied into the translation from the five main aspects.The reference and help of the samenessrelations finally demonstrate the realistic importance of the semantics to the Chinese-English translation,attracting much wider at-tention to other linguistic theories which is great of value to Chinese-English translation.

Research community detection from multi-relation researcher network based on structure/attribute similarities

Purpose: This paper aims to provide a method to detect research communities based on research interest in researcher network, which combines the topological structure and vertex attributes in a unified manner.Design/methodology/approach: A heterogeneous researcher network has been constructed by combining multiple relations of academic researchers. Vertex attributes and their similarities were considered and calculated. An approach has been proposed and tested to detect research community in research organizations based on this multi-relation researcher network.Findings: Detection of topologically well-connected, semantically coherent and meaningful research community was achieved.Research limitations: The sample size of evaluation experiments was relatively small. In the present study, a limited number of 72 researchers were analyzed for constructing researcher network and detecting research community. Therefore, a large sample size is required to give more information and reliable results.Practical implications: The proposed multi-relation researcher network and approaches for discovering research communities of similar research interests will contribute to collective innovation behavior such as brainstorming and to promote interdisciplinary cooperation.Originality/value: Recent researches on community detection devote most efforts to singlerelation researcher networks and put the main focus on the topological structure of networks.In reality, there exist multi-relation social networks. Vertex attribute also plays an important role in community detection. The present study combined multiple single-relational researcher networks into a multi-relational network and proposed a structure-attribute clustering method for detecting research community in research organizations.

Graph reasoning over explicit semantic relation

Multi-hop reasoning over language or graphs represents a significant challenge in contemporary research,particularly with the reliance on deep neural networks.These networks are integral to text reasoning processes,yet they present challenges in extracting and representing domain or commonsense knowledge,and they often lack robust logical reasoning capabilities.To address these issues,we introduce an innovative text reasoning framework.This framework is grounded in the use of a semantic relation graph and a graph neural network,designed to enhance the model’s ability to encapsulate knowledge and facilitate complex multi-hop reasoning.Our framework operates by extracting knowledge from a broad range of texts.It constructs a semantic relationship graph based on the logical relationships inherent in the reasoning process.Beginning with the core question,the framework methodically deduces key knowledge,using it as a guide to iteratively establish a complete evidence chain,thereby determining the final answer.Leveraging the advanced reasoning capabilities of the graph neural network,this approach is adept at multi-hop logical reasoning.It demonstrates strong performance in tasks like machine reading comprehension and question answering,while also clearly delineating the path of logical reasoning.

How Some Sense Relations Affect Language Use

Language must make contact with the outside world.This contact is what we call meaning.The meaning of words forms part of human linguistic knowledge and therefore part of grammar.For foreign language teachers and learners,it is necessary to distinguish some lexical meanings in English,for it is these different sense relations that affect language use.This article analyzes the possible reasons which cause these changes in language use and aims at providing linguistic assistance for foreign language teaching and learning.

Kernel-Based Semantic Relation Detection and Classification via Enriched Parse Tree Structure

This paper proposes a tree kernel method of semantic relation detection and classification （RDC） between named entities. It resolves two critical problems in previous tree kernel methods of RDC. First, a new tree kernel is presented to better capture the inherent structural information in a parse tree by enabling the standard convolution tree kernel with context-sensitiveness and approximate matching of sub-trees. Second, an enriched parse tree structure is proposed to well derive necessary structural information, e.g., proper latent annotations, from a parse tree. Evaluation on the ACE RDC corpora shows that both the new tree kernel and the enriched parse tree structure contribute significantly to RDC and our tree kernel method much outperforms the state-of-the-art ones.

An event-related potential observation of preposition processing in Chinese: Is N280 a specific component for Chinese prepositions?

BACKGROUND： Studies have shown that closed-class words, such as prepositions and conjunctions, induce a left anterior negativity （N280）, indicating that N280 should be a specific component of the word category. OBJECTIVE： To observe if Chinese prepositions and verbs exhibit different linguistic functions, to determine whether they are processed by different neural systems, and to verify that N280 is a specific component. DESIGN, TIME AND SETTING： The observed neurolinguistics experiment was performed at Xuzhou Normal University between November and December 2006. PARTICIPANTS： Sixteen undergraduate students, comprising 8 females and 8 males, with no mental or neuropathological history, were selected. METHODS： A total of 15 verbs and prepositions were used as linguistic stimuli, and each verb and preposition was combined to produce four correct phrase collocations and four incorrect ones. MAIN OUTCOME MEASURES： Event-related potentials were recorded in the subjects while they read correct or incorrect phases flashed upon a video screen. RESULTS： Both verbs and prepositions elicited negativity at the frontal site in a 230-330 ms window, as well as at the fronto-temporal and central sites in a 350-500 ms window. Neither exhibited significant differences in peak [F（1, 15） = 0.144, P = 0.710] and latency [F（1, 15） = 0.144, P= 0.710]. Both verbs and prepositions elicited negativity at the left and right hemisphere in a 270-400 ms window. CONCLUSION： There was no significant difference between Chinese prepositions and verbs in the neural system process and N280 was not the specific component for closed-class words.

基于异构图和语义融合的实体关系抽取

关系抽取是信息抽取中的一项重要任务,其目的是从非结构化文本中抽取出所有关系三元组。然而,如何有效地处理这一问题仍然是一个挑战,特别是对于关系重叠问题。为了有效处理重叠问题,该文提出一种基于异构图和语义融合的实体关系抽取方法:使用异构图将关系信息作为先验知识融入词表示,增强词表示的表示能力,使得模型能有效地处理单词实体重叠问题;使用语义融合模块将不同层次特征融合在一起作为关系分类模型的输入,使得模型能够有效地处理实体对重叠问题。所提方法在NYT和WebNLG数据集上取得了最好的效果,详细的实验也表明所提方法可以处理复杂的场景。

基于注意力机制语义增强的文档级关系抽取

文档级关系抽取旨在从文档中抽取出多个实体对之间的关系,具有较高的复杂性。针对文档级关系抽取中的多实体、关系相关性、关系分布不平衡等问题,提出了一种基于注意力机制(Attention)语义增强的文档级关系抽取方法,能够实现实体对之间关系的推理。具体来说,首先在数据编码模块改进编码策略,引入更多实体信息,通过编码网络捕获文档的语义特征,获得实体对矩阵;然后,设计了一个基于Attention门控机制的U-Net网络,对实体对矩阵进行局部信息捕获和全局信息汇总,实现语义增强;最后,使用自适应焦点损失函数缓解关系分布不平衡的问题。在4个公开的文档级关系抽取数据集(DocRED、CDR、GDA和DWIE)上评估了Att-DocuNet模型并取得了良好的实验结果。

融合词语语义与标签依赖的隐式篇章关系识别

中文隐式篇章关系识别旨在推断出两个论元间的篇章关系类型。然而,现有的方法往往忽略了论元中词语所蕴含的关键信息,并且仅考虑单个层级内的篇章关系类型,忽略了各层级间篇章关系的依赖关联。鉴于此,提出融合词语语义和标签依赖的方法,以序列生成的方式实现篇章关系识别,先根据相似度权重将词向量嵌入到字编码表示中,应用字词对齐注意力机制强调关键字、词信息,再采用标签注意力编码从蕴含词语语义的论元表示和篇章关系表示中获取篇章关系依赖性的上下文表示,以自下而上的方式预测顶层的篇章关系类型。此外,构建面向阅读理解篇章的篇章关系数据集,并在该数据集上展开实验,结果显示隐式篇章关系识别准确率和F1值分别达到74.19%和73.81%,最终验证了该方法的有效性。