A Knowledge-Enriched and Span-Based Network for Joint Entity and Relation Extraction

The joint extraction of entities and their relations from certain texts plays a significant role in most natural language processes.For entity and relation extraction in a specific domain,we propose a hybrid neural framework consisting of two parts:a span-based model and a graph-based model.The span-based model can tackle overlapping problems compared with BILOU methods,whereas the graph-based model treats relation prediction as graph classification.Our main contribution is to incorporate external lexical and syntactic knowledge of a specific domain,such as domain dictionaries and dependency structures from texts,into end-to-end neural models.We conducted extensive experiments on a Chinese military entity and relation extraction corpus.The results show that the proposed framework outperforms the baselines with better performance in terms of entity and relation prediction.The proposed method provides insight into problems with the joint extraction of entities and their relations.

A Two-Phase Paradigm for Joint Entity-Relation Extraction

An exhaustive study has been conducted to investigate span-based models for the joint entity and relation extraction task.However,these models sample a large number of negative entities and negative relations during the model training,which are essential but result in grossly imbalanced data distributions and in turn cause suboptimal model performance.In order to address the above issues,we propose a two-phase paradigm for the span-based joint entity and relation extraction,which involves classifying the entities and relations in the first phase,and predicting the types of these entities and relations in the second phase.The two-phase paradigm enables our model to significantly reduce the data distribution gap,including the gap between negative entities and other entities,aswell as the gap between negative relations and other relations.In addition,we make the first attempt at combining entity type and entity distance as global features,which has proven effective,especially for the relation extraction.Experimental results on several datasets demonstrate that the span-based joint extraction model augmented with the two-phase paradigm and the global features consistently outperforms previous state-ofthe-art span-based models for the joint extraction task,establishing a new standard benchmark.Qualitative and quantitative analyses further validate the effectiveness the proposed paradigm and the global features.

Chunk Parsing and Entity Relation Extracting to Chinese Text by Using Conditional Random Fields Model

Currently, large amounts of information exist in Web sites and various digital media. Most of them are in natural lan-guage. They are easy to be browsed, but difficult to be understood by computer. Chunk parsing and entity relation extracting is important work to understanding information semantic in natural language processing. Chunk analysis is a shallow parsing method, and entity relation extraction is used in establishing relationship between entities. Because full syntax parsing is complexity in Chinese text understanding, many researchers is more interesting in chunk analysis and relation extraction. Conditional random fields (CRFs) model is the valid probabilistic model to segment and label sequence data. This paper models chunk and entity relation problems in Chinese text. By transforming them into label solution we can use CRFs to realize the chunk analysis and entities relation extraction.

Relation-Aware Entity Matching Using Sentence-BERT

A key aspect of Knowledge fusion is Entity Matching.The objective of this study was to investigate how to identify heterogeneous expressions of the same real-world entity.In recent years,some representative works have used deep learning methods for entity matching,and these methods have achieved good results.However,the common limitation of these methods is that they assume that different attribute columns of the same entity are independent,and inputting the model in the form of paired entity records will cause repeated calculations.In fact,there are often potential relations between different attribute columns of different entities.These relations can help us improve the effect of entity matching,and can perform feature extraction on a single entity record to avoid repeated calculations.To use attribute relations to assist entity matching,this paper proposes the Relation-aware Entity Matching method,which embeds attribute relations into the original entity description to form sentences,so that entity matching is transformed into a sentence-level similarity determination task,based on Sentence-BERT completes sentence similarity calculation.We have conducted experiments on structured,dirty,and textual data,and compared them with baselines in recent years.Experimental results show that the use of relational embedding is helpful for entity matching on structured and dirty data.Our method has good results on most data sets for entity matching and reduces repeated calculations.

The Profound Revelation of Human Social Relations and the Profound Realization of Information Right of Citizens——The social significance of network technique advancement in the perspective of “Entity Cube”

The R＆D group of relationship searching in Microsoft Asia Research Institute explains ＂Entity Cube＂ launched in 2008 as follows：

A multi-attention RNN-based relation linking approach for question answering over knowledge base

Aiming at the relation linking task for question answering over knowledge base,especially the multi relation linking task for complex questions,a relation linking approach based on the multi-attention recurrent neural network(RNN)model is proposed,which works for both simple and complex questions.First,the vector representations of questions are learned by the bidirectional long short-term memory(Bi-LSTM)model at the word and character levels,and named entities in questions are labeled by the conditional random field(CRF)model.Candidate entities are generated based on a dictionary,the disambiguation of candidate entities is realized based on predefined rules,and named entities mentioned in questions are linked to entities in knowledge base.Next,questions are classified into simple or complex questions by the machine learning method.Starting from the identified entities,for simple questions,one-hop relations are collected in the knowledge base as candidate relations;for complex questions,two-hop relations are collected as candidates.Finally,the multi-attention Bi-LSTM model is used to encode questions and candidate relations,compare their similarity,and return the candidate relation with the highest similarity as the result of relation linking.It is worth noting that the Bi-LSTM model with one attentions is adopted for simple questions,and the Bi-LSTM model with two attentions is adopted for complex questions.The experimental results show that,based on the effective entity linking method,the Bi-LSTM model with the attention mechanism improves the relation linking effectiveness of both simple and complex questions,which outperforms the existing relation linking methods based on graph algorithm or linguistics understanding.

Qualia Role-Based Quantity Relation Extraction for Solving Algebra Story Problems

A qualia role-based entity-dependency graph(EDG)is proposed to represent and extract quantity relations for solving algebra story problems stated in Chinese.Traditional neural solvers use end-to-end models to translate problem texts into math expressions,which lack quantity relation acquisition in sophisticated scenarios.To address the problem,the proposed method leverages EDG to represent quantity relations hidden in qualia roles of math objects.Algorithms were designed for EDG generation and quantity relation extraction for solving algebra story problems.Experimental result shows that the proposedmethod achieved an average accuracy of 82.2%on quantity relation extraction compared to 74.5%of baseline method.Another prompt learning result shows a 5%increase obtained in problem solving by injecting the extracted quantity relations into the baseline neural solvers.

A U-Shaped Network-Based Grid Tagging Model for Chinese Named Entity Recognition

Chinese named entity recognition(CNER)has received widespread attention as an important task of Chinese information extraction.Most previous research has focused on individually studying flat CNER,overlapped CNER,or discontinuous CNER.However,a unified CNER is often needed in real-world scenarios.Recent studies have shown that grid tagging-based methods based on character-pair relationship classification hold great potential for achieving unified NER.Nevertheless,how to enrich Chinese character-pair grid representations and capture deeper dependencies between character pairs to improve entity recognition performance remains an unresolved challenge.In this study,we enhance the character-pair grid representation by incorporating both local and global information.Significantly,we introduce a new approach by considering the character-pair grid representation matrix as a specialized image,converting the classification of character-pair relationships into a pixel-level semantic segmentation task.We devise a U-shaped network to extract multi-scale and deeper semantic information from the grid image,allowing for a more comprehensive understanding of associative features between character pairs.This approach leads to improved accuracy in predicting their relationships,ultimately enhancing entity recognition performance.We conducted experiments on two public CNER datasets in the biomedical domain,namely CMeEE-V2 and Diakg.The results demonstrate the effectiveness of our approach,which achieves F1-score improvements of 7.29 percentage points and 1.64 percentage points compared to the current state-of-the-art(SOTA)models,respectively.

基于自适应上下文匹配网络的小样本知识图谱补全

知识图谱在构建过程中需要面对繁杂的现实世界信息,无法建模所有知识,因此需要补全。真实的知识图谱中很多类型的关系通常只有少量的训练实体样本对。因此,如何进行小样本知识图谱补全是一个十分有价值的问题。目前基于嵌入的方法一般通过注意力机制等方法聚合实体上下文信息,通过学习关系嵌入的方式来补全知识图谱,仅考虑关系层面的匹配程度,虽然能够预测未知关系,但往往准确度不高。针对小样本知识图谱补全问题,提出了一个自适应上下文匹配网络(Adaptive Context Matching Network,ACMN)。首先提出一个共性邻居感知编码器,聚合参考集实体上下文,即一跳邻居实体,获得共性邻居感知编码;接着提出一个任务相关实体编码器,挖掘任务实体上下文与共性上下文的相似度信息,区分一跳邻居对当前任务的贡献,增强实体表征;然后提出一个上下文关系编码器获得动态关系表征;最后通过加权求和综合考虑实体上下文和关系的匹配程度,完成补全。ACMN从实体上下文相似度和关系匹配程度两个方面综合评价查询三元组是否成立,能够在小样本的背景下有效提高预测准确性。在两个公共数据集上和其他8个广泛使用的算法进行比较,ACMN在不同规模的小样本情况下,取得了目前最好的补全结果。

基于深度学习的医学实体和关系联合抽取研究综述

命名实体识别与关系抽取作为医学领域信息抽取的核心任务,能够从非结构化或半结构化的文本中自动识别实体边界、实体类型以及实体之间的关系。不仅能够促进知识的发现与整合,应用于临床决策,加强药物的发现和再利用,还可以助力公共卫生监测和疾病预防。回顾了实体识别和关系抽取的发展历程,介绍了常用评价指标和医学领域实体关系联合抽取数据集,指出目前联合抽取领域存在医学文本结构比较复杂、实体关系重叠句子抽取率低等问题。根据这些问题,进一步探讨了基于深度学习的实体关系联合抽取方法在医学领域上的应用。这些方法根据模型解码的方式主要分为基于共享参数的联合抽取模型和基于联合解码的联合抽取模型,从问题解决角度对不同的模型的优缺点进行探讨分析和总结。讨论了医学领域实体关系抽取面临的挑战和未来的研究方向。

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。

基于深度字词融合的小麦种质信息实体关系联合抽取

为获得结构化的小麦品种表型和遗传描述,针对非结构化小麦种质数据中存在的实体边界模糊以及关系重叠问题,提出一种基于深度字词融合的小麦种质信息实体关系联合抽取模型WGIE-DCWF(wheat germplasm information extraction model based on deep character and word fusion)。模型编码层通过深度字词融合和上下文语义特征融合,提高密集实体特征识别能力;模型三元组抽取层建立层叠指针网络,提高重叠关系的提取能力。在小麦种质数据集和公开数据集上的一系列对比实验结果表明,WGIE-DCWF模型能够有效提高小麦种质数据实体关系联合抽取效果,同时拥有较好的泛化性,可以为小麦种质信息知识库构建提供技术支撑。

融合限定关系和交互信息的实体关系联合抽取模型

实体关系抽取作为信息抽取领域的核心任务,旨在从非结构化文本中自动抽取所有的关系三元组。现有研究较难处理句子中关系重叠的情况,存在识别冗余和语义依赖不足的问题。鉴于此,该文提出一种融合限定关系和交互信息的实体关系联合抽取模型。该模型首先对句子进行关系预测,构成限定关系集。其次,利用限定关系分别地预测可能存在关系的头实体和尾实体,解决关系重叠问题,同时缓解冗余识别。为了加强句子中实体与关系的交互,利用注意力机制强化句子中关系有关信息,通过双仿射和卷积操作来构建评分矩阵。最后,通过评分矩阵对候选三元组进行校正,确定最终的关系三元组。实验结果表明,该模型在NYT和WebNLG数据集上F1值分别达到92.0%和88.7%,相比于所对比的基线模型F1值分别提高了2.8%和1.0%,验证了模型的有效性。

基于MacBERT-BiLSTM-CRF模型的继电保护装置缺陷知识图谱构建方法

电网发展至今积累了大量继电保护装置缺陷文本数据,尚未被有效挖掘利用。此外,继电保护装置的缺陷排除工作过度依赖运行人员的专业能力,现场运维工作难度大。针对上述问题,提出基于MacBERT-BiLSTM-CRF模型的继电保护装置缺陷知识图谱构建方法。首先,分析继电保护装置缺陷文本的记录特点,对非结构化文本进行数据清洗、数据标注以及数据增强处理。其次,基于BERT-BiLSTM-CRF模型构建MacBERT-BiLSTM-CRF模型进行实体抽取任务。然后,定义继电保护装置缺陷文本的关系抽取规则,结合实体抽取模型共同完成关系抽取任务。最后,构建继电保护装置缺陷知识图谱的模式层,并利用Neo4j图数据库实现知识图谱数据层的存储。算例分析表明,所提数据处理方法能够得到高质量BIO标注数据集。相比于传统BERT-BiLSTM-CRF模型,MacBERT-BiLSTM-CRF模型的实体抽取效果更好。基于模式层完成了继电保护装置缺陷知识图谱的构建与可视化展示,并提出继电保护装置缺陷辅助决策的应用流程与知识图谱的更新方法。

基于ChatGLM和提示微调的旅游知识图谱构建

为缓解旅游领域知识分散、信息碎片化的问题,提出一种基于ChatGLM(chat generative language model)和提示微调的实体关系抽取模型ChatGLM-ppt(ChatGLM with prompt and p-tuning)。该模型借助ChatGLM以对话形式完成实体关系抽取任务,并通过P-Tuning v2微调和添加提示模板的方法应对实体关系抽取中错误传播、实体冗余和关系重叠等问题。实验建立在自建的旅游领域数据集上,结果表明:在旅游领域实体关系抽取问题上ChatGLM-ppt模型F 1为92.19%,在处理重叠关系问题中F 1均大于90%,优于目前主流的实体关系抽取模型,证明该模型可有效提高实体关系抽取的准确率。进一步运用Neo4j图数据库构建旅游知识图谱,整合分散的旅游信息资源,对促进旅游业的数字化转型和智能化发展具有一定的参考意义。

融合实体和上下文信息的篇章关系抽取研究

篇章关系抽取旨在识别篇章中实体对之间的关系.相较于传统的句子级别关系抽取,篇章级别关系抽取任务更加贴近实际应用,但是它对实体对的跨句子推理和上下文信息感知等问题提出了新的挑战.本文提出融合实体和上下文信息(Fuse entity and context information,FECI)的篇章关系抽取方法,它包含两个模块,分别是实体信息抽取模块和上下文信息抽取模块.实体信息抽取模块从两个实体中自动地抽取出能够表示实体对关系的特征.上下文信息抽取模块根据实体对的提及位置信息,从篇章中抽取不同的上下文关系特征.本文在三个篇章级别的关系抽取数据集上进行实验,效果得到显著提升.

基于科技文献的锡铟材料知识图谱构建研究

随着科技文献数量的爆发性增长,垂直领域的企业面临着知识服务的挑战。为了帮助新材料领域企业有效利用科技文献信息资源,迫切需要使用人工智能技术对包含的材料性能等关键知识的专利及学术论文进行深入的知识建模,提供知识获取效率和准确性。以锡铟贵金属领域的10.48万篇科技文献为数据源,构建领域知识本体,利用BERT+BiLSTM+CRF模型进行命名实体识别,利用BERT+BiGRU神经网络模型进行关系抽取,将抽取结果存入图数据库Neo4j中并构建锡铟贵金属材料领域的知识图谱。所构建的知识图谱拥有18.19万个实体节点和23.47万条关系,能够实现多粒度的材料实体和关系的关联查询与可视化。基于锡铟科技文献构建知识图谱的方法拓展了新材料领域知识图谱构建的研究思路,为开展基于科技文献的垂直领域智能知识问答等应用提供了坚实的基础。

基于BERT古文预训练模型的实体关系联合抽取

古汉语文本承载着丰富的历史和文化信息,对这类文本进行实体关系抽取研究并构建相关知识图谱对于文化传承具有重要作用.针对古汉语文本中存在大量生僻汉字、语义模糊和复义等问题,提出了一种基于BERT古文预训练模型的实体关系联合抽取模型(entity relation joint extraction model based on BERT-ancient-Chinese pretrained model,JEBAC).首先,通过融合BiLSTM神经网络和注意力机制的BERT古文预训练模型(BERT-ancientChinese pre-trained model integrated BiLSTM neural network and attention mechanism,BACBA),识别出句中所有的subject实体和object实体,为关系和object实体联合抽取提供依据.接下来,将subject实体的归一化编码向量与整个句子的嵌入向量相加,以更好地理解句中subject实体的语义特征;最后,结合带有subject实体特征的句子向量和object实体的提示信息,通过BACBA实现句中关系和object实体的联合抽取,从而得到句中所有的三元组信息(subject实体,关系,object实体).在中文实体关系抽取DuIE2.0数据集和CCKS 2021的文言文实体关系抽取CCLUE小样本数据集上,与现有的方法进行了性能比较.实验结果表明,该方法在抽取性能上更加有效,F1值分别可达79.2%和55.5%.

基于实体知识的远程监督关系抽取

为了降低远程监督关系抽取标记数据的噪声,提出一种融合实体描述和自注意力机制的远程监督关系提取模型,模型基于多示例学习,考虑到实体知识和位置关系的综合作用,采用词、实体、实体描述和相对位置的拼接向量作为模型输入,将分段卷积神经网络作为句子编码器,结合改进的结构化自注意力机制,捕捉特征内部相关性,并构造头实体和尾实体的差向量作为注意力机制的监督信息,为句子分配权重。在纽约时报数据集上的实验结果表明,与已有模型相比,本文模型的性能指标均达到最大值。

基于潜在关系的实体关系联合抽取模型

实体关系联合抽取的作用是从特定文本中识别出实体和对应关系,同时它也是知识图谱构建和更新的基础。目前的联合抽取方法在追求性能的同时都忽略了抽取过程中的信息冗余。针对此问题,提出基于潜在关系的实体关系联合抽取模型,通过设计一种新的解码方式来减少预测过程中关系、实体和三元组的冗余信息,从整体上分为提取潜在实体对、解码关系两步来完成从句子中抽取三元组的任务。首先通过潜在实体对提取器预测实体间是否存在潜在关系,同时筛选出置信度高的实体对作为最终的潜在实体对;其次将关系解码视作多标签二分类任务,通过关系解码器预测每个潜在实体对之间全部关系的置信度;最后通过置信度确定关系数量和类型,以完成三元组的抽取任务。在两个通用数据集上的实验结果表明,所提模型相比基线模型在准确率和F1指标上的效果更好,验证了所提模型的有效性,消融实验也证明了模型内部各部分的有效性。