Content annotation for the semantic web: an automatic web-based approach

Semantic Annotation is required to add machine-readable content to natural language text. A global initiative such as the Semantic Web directly depends on the annotation of massive amounts of textual Web resources. However, considering the amount of those resources, a manual semantic annotation of their contents is neither feasible nor scalable. In this paper we introduce a methodology to partially annotate textual content of Web resources in an automatic and unsupervised way. It uses several well-established learning techniques and heuristics to discover relevant entities in text and to associate them to classes of an input ontology by means of linguistic patterns. It also relies on the Web information distribution to assess the degree of semantic co-relation between entities and classes of the input domain ontology. Special efforts have been put in minimizing the amount of Web accesses required to evaluate entities in order to ensure the scalability of the approach. A manual evaluation has been carried out to test the methodology for several domains showing promising results.     

利用提示调优实现两阶段模型复用的关系实体抽取方法

关系实体抽取旨在从非结构化文本中识别命名实体并抽取实体间语义关系,现有的两阶段关系实体抽取方法存在模型无法复用、调优参数量大等问题,不便于工程实现。利用提示调优对已有方法进行改进,提出两阶段模型复用的关系实体抽取方法REPT（a model-reused method of two-staged relations and entities extraction with prompt tuning）。首先微调预训练语言模型进行关系分类,而后利用提示调优并复用前一阶段微调的预训练语言模型抽取实体。实验结果表明,该方法在调优参数只占基线模型约50%的情况下,达到与SOTA模型相媲美的性能。     

Exploiting semantic annotations for open information extraction: an experience in the biomedical domain

The increasing amount of unstructured text published on the Web is demanding new tools and methods to automatically process and extract relevant information. Traditional information extraction has focused on harvesting domain-specific, pre-specified relations, which usually requires manual labor and heavy machinery; especially in the biomedical domain, the main efforts have been directed toward the recognition of well-defined entities such as genes or proteins, which constitutes the basis for extracting the relationships between the recognized entities. The intrinsic features and scale of the Web demand new approaches able to cope with the diversity of documents, where the number of relations is unbounded and not known in advance. This paper presents a scalable method for the extraction of domain-independent relations from text that exploits the knowledge in the semantic annotations. The method is not geared to any specific domain (e.g., protein–protein interactions and drug–drug interactions) and does not require any manual input or deep processing. Moreover, the method uses the extracted relations to compute groups of abstract semantic relations characterized by their signature types and synonymous relation strings. This constitutes a valuable source of knowledge when constructing formal knowledge bases, as we enable seamless integration of the extracted relations with the available knowledge resources through the process of semantic annotation. The proposed approach has successfully been applied to a large text collection in the biomedical domain and the results are very encouraging.     

Mining temporal explicit and implicit semantic relations between entities using web search engines

In this paper, we study the problem of mining temporal semantic relations between entities. The goal of the studied problem is to mine and annotate a semantic relation with temporal, concise, and structured information, which can release the explicit, implicit, and diversity semantic relations between entities. The temporal semantic annotations can help users to learn and understand the unfamiliar or new emerged semantic relations between entities. The proposed temporal semantic annotation structure integrates the features from IEEE and Renlifang. We propose a general method to generate temporal semantic annotation of a semantic relation between entities by constructing its connection entities, lexical syntactic patterns, context sentences, context graph, and context communities. Empirical experiments on two different datasets including a LinkedIn dataset and movie star dataset show that the proposed method is effective and accurate. Different from the manually generated annotation repository such as Wikipedia and LinkedIn, the proposed method can automatically mine the semantic relation between entities and does not need any prior knowledge such as ontology or the hierarchical knowledge base. The proposed method can be used on some applications, which proves the effectiveness of the proposed temporal semantic relations on many web mining tasks.     

Semantic context based refinement for news video annotation

Automatic video annotation is to bridge the semantic gap and facilitate concept based video retrieval by detecting high level concepts from video data. Recently, utilizing context information has emerged as an important direction in such domain. In this paper, we present a novel video annotation refinement approach by utilizing extrinsic semantic context extracted from video subtitles and intrinsic context among candidate annotation concepts. The extrinsic semantic context is formed by identifying a set of key terms from video subtitles. The semantic similarity between those key terms and the candidate annotation concepts is then exploited to refine initial annotation results, while most existing approaches utilize textual information heuristically. Similarity measurements including Google distance and WordNet distance have been investigated for such a refinement purpose, which is different with approaches deriving semantic relationship among concepts from given training datasets. Visualness is also utilized to discriminate individual terms for further refinement. In addition, Random Walk with Restarts (RWR) technique is employed to perform final refinement of the annotation results by exploring the inter-relationship among annotation concepts. Comprehensive experiments on TRECVID 2005 dataset have been conducted to demonstrate the effectiveness of the proposed annotation approach and to investigate the impact of various factors.     

基于ALBERT-BGRU-CRF的中文命名实体识别方法

命名实体识别是知识图谱构建、搜索引擎、推荐系统等上层自然语言处理任务的重要基础,中文命名实体识别是对一段文本序列中的专有名词或特定命名实体进行标注分类。针对现有中文命名实体识别方法无法有效提取长距离语义信息及解决一词多义的问题,提出一种基于ALBERT-双向门控循环单元（BGRU）-条件随机场（CRF）模型的中文命名实体识别方法。使用ALBERT预训练语言模型对输入文本进行词嵌入获取动态词向量,有效解决了一词多义的问题。采用BGRU提取上下文语义特征进一步理解语义,获取长距离词之间的语义特征。将拼接后的向量输入至CRF层并利用维特比算法解码,降低错误标签输出概率。最终得到实体标注信息,实现中文命名实体识别。实验结果表明,ALBERT-BGRU-CRF模型在MSRA语料库上的中文命名实体识别准确率和召回率分别达到95.16%和94.58%,同时相比于片段神经网络模型和CNN-BiLSTM-CRF模型的F1值提升了4.43和3.78个百分点。     

A Novel Framework for Semantic Annotation and Personalized Retrieval of Sports Video

Sports video annotation is important for sports video semantic analysis such as event detection and personalization. In this paper, we propose a novel approach for sports video semantic annotation and personalized retrieval. Different from the state of the art sports video analysis methods which heavily rely on audio/visual features, the proposed approach incorporates web-casting text into sports video analysis. Compared with previous approaches, the contributions of our approach include the following. 1) The event detection accuracy is significantly improved due to the incorporation of web-casting text analysis. 2) The proposed approach is able to detect exact event boundary and extract event semantics that are very difficult or impossible to be handled by previous approaches. 3) The proposed method is able to create personalized summary from both general and specific point of view related to particular game, event, player or team according to user's preference. We present the framework of our approach and details of text analysis, video analysis, text/video alignment, and personalized retrieval. The experimental results on event boundary detection in sports video are encouraging and comparable to the manually selected events. The evaluation on personalized retrieval is effective in helping meet users' expectations.     

A novel framework for semantic entity identification and relationship integration in large scale text data

Semantic entities carry the most important semantics of text data. Therefore, the identification and the relationship integration of semantic entities are very important for applications requiring semantics of text data. However, current strategies are still facing many problems such as semantic entity identification, new word identification and relationship integration among semantic entities. To address these problems, a two-phase framework for semantic entity identification with relationship integration in large scale text data is proposed in this paper. In the first semantic entities identification phase, we propose a novel strategy to extract unknown text semantic entities by integrating statistical features, Decision Tree (DT), and Support Vector Machine (SVM) algorithms. Compared with traditional approaches, our strategy is more effective in detecting semantic entities and more sensitive to new entities that just appear in the fresh data. After extracting the semantic entities, the second phase of our framework is for the integration of Semantic Entities Relationships (SER) which can help to cluster the semantic entities. A novel classification method using features such as similarity measures and co-occurrence probabilities is applied to tackle the clustering problem and discover the relationships among semantic entities. Comprehensive experimental results have shown that our framework can beat state-of-the-art strategies in semantic entity identification and discover over 80% relationship pairs among related semantic entities in large scale text data.     

基于本体知识库的自动语义标注*

为了产生语义Web中的元数据,需要提取Web文档中的语义信息。面对海量的Web文档,自动语义标注相对人工和半自动的语义标注是可行的方法。提出的基于本体知识库的自动语义标注方法,旨在提高标注的质量。为识别出文档中的候选命名实体,设计了语义词典的逻辑结构,论述了以实体之间语义关联路径计算语义距离的方法。语义标注中的复杂问题是语义消歧,提出了基于最短路径的语义消歧方法和基于n-gram的语义消歧方法。采用这种方法对文档进行语义标注,将标注结果持久化为语义索引,为实现语义信息检索提供基础。针对构建的测试数据集,进行的标注实验表明该方法能够依据本体知识库,有效地对Web文档进行自动语义标注。     

基于多特征因子融合的中文短文本实体消歧

现有中文短文本实体消歧模型在消歧过程中大多只考虑指称上下文与候选实体描述的语义匹配特征,对同一查询文本中候选实体间的共现特征以及候选实体与实体指称类别相似特征等有效的消歧特征考虑不足。针对这些问题,本文首先利用预训练语言模型获得指称上下文与候选实体描述的语义匹配特征;然后,针对实体嵌入和指称类别嵌入提出共现特征与类别特征;最后,通过融合上述特征实现基于多特征因子融合实体消歧模型。实验结果表明本文提出的共现特征及类别特征在实现实体消歧中的可行性和有效性,以及本文提出的基于多特征因子融合的实体消歧方法能够取得更好的消歧效果。     

文本摘要常用数据集和方法研究综述

文本摘要成为人们从互联网上海量文本信息中便捷获取知识的重要手段。现有方法都是在特定数据集上进行训练和效果评价,包括一些公用数据集和作者自建数据集。已有综述文献对现有方法进行全面细致的总结,但大多都是对方法进行总结,而缺少对数据集的详细描述。该文从调研数据集的角度出发,对文本摘要常用数据集及在该数据集上的经典和最新方法进行综述。对公用数据集的综述包括数据来源、语言及获取方式等,对自建数据集的总结包括数据规模、获取和标注方式等。对于每一种公用数据集,给出了文本摘要问题的形式化定义。同时,对经典和最新方法在特定数据集上的实验效果进行了分析。最后,总结了已有常用数据集和方法的现状,并指出存在的一些问题。     

一种轻量级的汉语语义角色标注规范

作为主流的浅层语义表示形式,语义角色标注一直是自然语言处理领域的研究热点之一。目前学术界已有的语义角色标注规范(PropBank规范和北大规范)主要存在三个问题:①基于片段的论元表示让标注难度加大; ②PropBank中谓词框架的定义难度较大; ③北大规范缺乏省略论元的标注。经过充分调研,该文尝试融合已有的中英文语义角色标注规范的优点,同时结合实际标注中遇到的问题,制定了一种轻量级的适合非语言学背景的标注者参与的中文语义角色标注规范。第一,采用基于词的论元表示,避免了片段边界的确定,从而降低标注难度;第二,标注者直接根据句子上下文信息,标注谓词相关论元角色,而无须预先定义每个谓词的所有语义框架;第三,显式标注句子中省略的核心论元,更准确地刻画句子的语义信息。此外,为了保证标注一致性和提高数据标注质量,规范针对各种复杂语言现象,给出了明确的优先级规定和难点分析。     

SREC: Discourse-level semantic relation extraction from text

Semantic relation extraction is a significant topic in semantic web and natural language processing with various important applications such as knowledge acquisition, web and text mining, information retrieval and search engine, text classification and summarization. Many approaches such rule base, machine learning and statistical methods have been applied, targeting different types of relation ranging from hyponymy, hypernymy, meronymy, holonymy to domain-specific relation. In this paper, we present a computational method for extraction of explicit and implicit semantic relation from text, by applying statistic and linear algebraic approaches besides syntactic and semantic processing of text.     

基于上下文信息的中文命名实体消岐方法研究

在语义标注过程中,为了消除文本中给定的命名实体与知识库中实体映射过程中出现的歧义问题,提出了一种基于上下文信息相似度值排序的命名实体消歧方法。消岐方法包括实体表示预处理、候选实体列表构建和相似度值排序算法三部分。针对命名实体指称多样性问题,使用实体表示预处理方法抽取标准实体。然后利用中文在线百科构建语义知识库,得到标准实体的语义列表。同时提出利用相似度值排序方法解决标准实体与语义列表映射的指称歧义性问题,对于在知识库中未找到语义的实体采用HAC聚类算法进行消岐处理。实验结果表明,本文提出的方法能够有效的把中文网页真实数据集中文本的实体映射到知识库中对应无歧义的实体上。     

基于机器翻译的跨语言关系抽取

训练语料库的规模对基于机器学习的命名实体间语义关系抽取具有重要的作用,而语料库的人工标注需要花费大量的时间和人力。该文提出了使用机器翻译的方法将源语言的关系实例转换成目标语言的关系实例,并通过实体对齐策略将它们加入到目标语言的训练集中,从而使资源丰富的源语言帮助欠资源的目标语言进行语义关系抽取。在ACE2005中英文语料库上的关系抽取实验表明,无论是将中文翻译成英文,还是将英文翻译成中文,都对另一种语言的关系抽取具有帮助作用。特别是当目标语言的训练语料库规模较小时,这种帮助就尤其显著。     

An intensive case study on kernel-based relation extraction

Relation extraction refers to a method of efficiently detecting and identifying predefined semantic relationships within a set of entities in text documents. Numerous relation extractionfc techniques have been developed thus far, owing to their innate importance in the domain of information extraction and text mining. The majority of the relation extraction methods proposed to date is based on a supervised learning method requiring the use of learning collections; such learning methods can be classified into feature-based, semi-supervised, and kernel-based techniques. Among these methods, a case analysis on a kernel-based relation extraction method, considered the most successful of the three approaches, is carried out in this paper. Although some previous survey papers on this topic have been published, they failed to select the most essential of the currently available kernel-based relation extraction approaches or provide an in-depth comparative analysis of them. Unlike existing case studies, the study described in this paper is based on a close analysis of the operation principles and individual characteristics of five vital representative kernel-based relation extraction methods. In addition, we present deep comparative analysis results of these methods. In addition, for further research on kernel-based relation extraction with an even higher performance and for general high-level kernel studies for linguistic processing and text mining, some additional approaches including feature-based methods based on various criteria are introduced.     

语义角色的精细等级及其在信息处理中的应用

本文首先讨论语义角色的三种精细程度不一的分类层级,介绍它们各自在语言信息处理系统中的有关应用。接着,分别介绍三种为语言信息处理服务的语义资源对于语义角色的不同处理: (i)加州大学伯克利分校框架网的语义角色——基于场景的语义框架中的框架元素; (ii)宾州大学命题库的语义角色——基于特定动词的编了号的原型角色; (iii)北京大学中文网库的语义角色——基于特定谓词的各论元成分的论旨角色。最后,从建库目标、方法论、标注内容和系统构成等方面,比较这三个语义关系标注语料库的同异。     

Conceptual feature generation for textual information using a conceptual network constructed from Wikipedia

A proper semantic representation of textual information underlies many natural language processing tasks. In this paper, a novel semantic annotator is presented to generate conceptual features for text documents. A comprehensive conceptual network is automatically constructed with the aid of Wikipedia that has been represented as a Markov chain. Furthermore, semantic annotator gets a fragment of natural language text and initiates a random walk to generate conceptual features that represent topical semantic of the input text. The generated conceptual features are applicable to many natural language processing tasks where the input is textual information and the output is a decision based on its context. Consequently, the effectiveness of the generated features is evaluated in the task of document clustering and classification. Empirical results demonstrate that representing text using conceptual features and considering the relations between concepts can significantly improve not only the bag of words representation but also other state‐of‐the‐art approaches.     

面向中文电子病历的多粒度医疗实体识别

在现有的面向中文临床电子病历的命名实体识别任务中,实体标注粒度通常过细或过粗,过细的标注结果难以找到实际应用场景,而过粗的标注结果通常需要在进行复杂的处理后,才能明确实体的规范形式和语义类型,以便于后续的数据挖掘应用。为简化处理步骤,根据常见的7类粗粒度临床实体的特点,定义了用以解释粗粒度实体的9类细粒度解析实体。同时,针对多粒度实体的特点,提出了基于多任务学习和自注意力机制的多粒度临床实体识别模型,并在真实的医院电子病历库中标注了5000条包含多粒度实体的文本以验证模型的效果。实验结果表明,该模型优于主流的序列标注模型,在粗、细粒度实体识别任务中,两者的F 1值分别达到了92.88和85.48。     

融合注意力机制的药用植物文本命名实体识别

药用植物文本的命名实体识别对中医药领域的信息抽取和知识图谱构建起着重要作用。针对药用植物属性文本存在长序列语义稀疏的问题,提出一种基于注意力机制的双向长短时记忆网络(BiLSTM)和条件随机场(CRF)模型相结合的疾病实体识别方法（BiLSTM+ATT-CRF,BAC）。首先对药用植物属性文本进行预处理和半自动化标注构建数据集,并进行预训练得到低维词向量;然后将这些低维词向量输入BiLSTM网络中,得到双向语义依赖的特征向量;Attention层把注意力集中到与当前输出特征高度相关的信息上;最后通过条件随机场（CRF）算法获取最优的标签序列并解码输出。实验结果表明,BAC方法针对药用植物属性文本的长序列语义稀疏问题,疾病命名实体识别效果较传统方法更优。利用BAC方法训练好的模型从1680条文本句子中识别疾病命名实体,共抽取出1422个疾病实体。与药用植物名称进行匹配,共抽取出4316个药用植物治疗疾病的三元组数据。