A deep learning based method benefiting from characteristics of patents for semantic relation classification

The deep learning has become an important technique for semantic relation classification in patent texts. Previous studies just borrowed the relevant models from generic texts to patent texts while keeping structure of the models unchanged. Due to significant distinctions between patent texts and generic ones, this enables the performance of these models in the patent texts to be reduced dramatically. To highlight these distinct characteristics in patent texts, seven annotated corpora from different fields are comprehensively compared in terms of several indicators for linguistic characteristics. Then, a deep learning based method is proposed to benefit from these characteristics. Our method exploits the information from other similar entity pairs as well as that from the sentences mentioning a focal entity pair. The latter stems from the conventional practices, and the former from our meaningful observation: the stronger the connection between two entity pairs is, the more likely they belong to the same relation type. To measure quantitatively the connection between two entity pairs, a similarity indicator on the basis of association rules is raised. Extensive experiments on the corpora of TFH-2020 and ChemProt demonstrate that our method for semantic relation classification is capable of benefiting from characteristic of patent texts.     

基于OCC模型和LSTM模型的财经微博文本情感分类研究

为了解决财经微博文本中网民情感状态转移的时序数据分析问题,本文提出一个基于认知情感评价模型(Ortony,Clore&Collins,OCC)和长短期记忆模型(long short term memory,LSTM)的财经微博文本情感分类模型(OCC-LSTM)。基于OCC模型从网民认知角度建立情感规则,对财经微博文本进行情感标注,并作为LSTM模型进行深度学习的训练集;基于LSTM模型,使用深度学习中的TensorFlow框架和Keras模块建立相应的实验模型,进行海量微博数据情感分类,并结合13家上市公司3年的微博文本数据进行实证研究和模型验证对比。实证研究结果发现本文提出的模型取得了89.45%的准确率,高于采用传统的机器学习方式的支持向量机方法 (support vector machine,SVM)和基于深度学习的半监督RAE方法 (semi-supervised recursive auto encoder)。     

学术文本中细粒度知识实体的关联分析

考察特定领域文本中蕴含的细粒度知识实体的使用情况,对知识实体的评估和选择具有重要意义。学术文本中的细粒度知识实体通常具有多个类型、多种关联关系,挖掘知识实体的同质与异质关联关系,有助于深入了解特定领域知识实体的实际使用情况。目前相关研究大多针对学术文本中单一知识实体的抽取和评估,缺乏对知识实体间关系的关注,在一定程度上限制了基于实体抽取进行知识发现的能力。文章以自然语言处理领域为例,对学术论文全文中的细粒度知识实体关联数据进行挖掘,并通过可视化方式揭示关联数据中蕴含的信息。主要是选取全国计算语言学会议2009-2018年间收录的中文论文为原始语料,人工标注论文中使用的知识实体,并针对NLP特点将其细分为“指标实体”“工具实体”“资源实体”“方法实体”4种类型;结合关联规则挖掘算法Apriori和复杂网络分析软件构建知识实体关联网络,揭示该领域常用的知识实体,以及这些知识实体的使用相关性。     

一个中文文本自动分类数学模型

本文提出了一种根据汉字统计特性和基于实例映射的中文文本自动分类模型。该模型采用汉字字频向量作为文本的表示方法。它的显著特点是引入线性最小二乘方拟合（ＬｉｎｅａｒＬｅａｓｔＳｑｕａｒｅＦｉｔ,ＬＬＳＦ）技术建立文本分类器模型,通过对训练集语料的手工分类标引以及对文本和类别间的相关性判定的学习,实现了基于全局最小错误率的汉字———类别两个向量空间的映射函数,并用该函数对测试文本进行分类。     

数字人文下的典籍深度学习实体自动识别模型构建及应用研究

[目的/意义]典籍是我国传统文化、思想和智慧的载体,结合数字人文的数据获取、标注和分析方法对典籍进行实体自动识别,对于后续应用研究具有重要意义。[方法/过程]基于经过自动分词与人工标注的25本先秦典籍构建古籍语料库,分别基于不同规模的语料库和Bi-LSTM、Bi-LSTM-Attention、Bi-LSTM-CRF、Bi-LSTM-CRF-Attention、Bi-RNN和Bi-RNN-CRF、BERT等7种深度学习模型,从中抽取构成历史事件的相应实体并进行效果对比。[结果/结论]在全部语料上训练得到的Bi-LSTM-Attention与Bi-RNN-CRF模型的准确率分别达到89.79%和89.33%,证实了深度学习应用于大规模文本数据集的可行性。     

More than Bags of Words: Sentiment Analysis with Word Embeddings

ABSTRACT

Moving beyond the dominant bag-of-words approach to sentiment analysis we introduce an alternative procedure based on distributed word embeddings. The strength of word embeddings is the ability to capture similarities in word meaning. We use word embeddings as part of a supervised machine learning procedure which estimates levels of negativity in parliamentary speeches. The procedure’s accuracy is evaluated with crowdcoded training sentences; its external validity through a study of patterns of negativity in Austrian parliamentary speeches. The results show the potential of the word embeddings approach for sentiment analysis in the social sciences.     

基于Uni LM模型的学术文摘观点自动生成研究

[目的 /意义]将海量学术文本观点提取工作由人工转向机器,提高效率的同时又能够保证观点提取的准确性、客观性。[方法 /过程]使用UniLM统一语言预训练模型,训练过程中对模型进行精调,以人工标注数据集进行机器学习。将学术文摘作为长度为a的文本序列,经过机器学习,生成长度为b的句子序列(a≥b),并且作为学术论文观点句输出。[结果 /结论 ]研究结果表明：UniLM模型对于规范型文摘、半规范型文摘、非规范型文摘观点生成精准度分别为94.36%、77.27%、57.43%,规范型文摘生成效果最好。将机器学习模型应用于长文本观点生成,为学术论文观点生成提供一种新方法。不足之处在于本文模型依赖文摘的结构性,对非规范型文摘观点生成效果有所欠缺。     

基于字频向量的中文文本自动分类系统

本文提出了一种根据汉字统计特性和基于实例映射的中文文本自动分类方法。该方法采用汉字字频向量作为文本的表示方法。它的显著特点是引入线性最小二乘方估计技术建立文本分类器模型,通过对训练集语料的手工分类标引以及对文本和类别间的相关性判定的学习,实现了基于全局最小错误率的汉字一类别两个向量空间的映射函数,并用该函数对测试文本进行分类。     

基于最大熵模型的学术缩写自动识别

为实现海量英文学术文本中缩写词及对应缩写定义的识别,本文提出了一种自动缩写识别算法 MELearn-AI。该算法在人工标注数据集的基础上,从序列标注的角度,通过最大熵模型实现了计算机领域 英文学术文本中的自动缩写识别。MELearn-AI 在本文构建的评测数据集“Paren-sen”上得到了95.8% 的 查准率和86.3% 的查全率,相对于其他两组对照实验的效果有较为明显的提升。本文提出的自动缩写识别 方法能够在计算机领域的学术文本上取得令人满意的效果,有助于更好地理解并利用该领域术语。     

Sentiment classification: a lexical similarity based approach for extracting subjectivity in documents

With the growth of social media, document sentiment classification has become an active area of research in this decade. It can be viewed as a special case of topical classification applied only to subjective portions of a document (sources of sentiment). Hence, the key task in document sentiment classification is extracting subjectivity. Existing approaches to extract subjectivity rely heavily on linguistic resources such as sentiment lexicons and complex supervised patterns based on part-of-speech (POS) information. This makes the task of subjective feature extraction complex and resource dependent. In this work, we try to minimize the dependency on linguistic resources in sentiment classification. We propose a simple and statistical methodology called review summary (RSUMM) and use it in combination with well-known feature selection methods to extract subjectivity. Our experimental results on a movie review dataset prove the effectiveness of the proposed methodology.     

基于深度学习的MOOC论坛探索型对话识别方法研究

[目的/意义]大规模在线开放课程论坛具有丰富的用户评论数据。从大量未区分的评论数据中，自动识别出知识密度较高的探索型对话并挖掘其潜在价值，对于改善教师教学质量以及提高学生知识水平具有重要影响。[方法/过程]首先利用GloVe方法训练词向量，加强对文本语义的理解，然后利用卷积神经网络自动学习文本特征，提出一种基于深度学习的探索型对话自动识别模型，并在学堂在线平台《心理学概论》课程论坛标注数据集上进行实证与对比研究。[结果/结论]实验结果显示，利用GloVe方法预训练词向量以及在训练过程中不断对词向量进行学习修正能够提高模型效果。该模型识别探索型对话的F1值为0.94，相较于传统的朴素贝叶斯方法（0.88）、逻辑斯谛回归方法（0.89）、决策树方法（0.88）以及随机森林方法（0.88）取得较大提升，具有较高的实用性和较低的学习成本。     

荷兰翻译图书市场一瞥

介绍荷兰翻译图书市场的历史、现状以及荷语图书在法国的翻译情况,探讨英语翻译图书挤占其他语言翻译图书市场空间的现象,分析荷兰的法译荷图书与法国的荷译法图书呈完全相反的发展趋势的原因.     

基于条件随机场的学术期刊中理论的自动识别方法

[目的/意义]从学术期刊中抽取其中的理论是对文献进行内容分析的前提,实现理论名称识别的自动化可以提高内容分析的效率。[方法/过程]将理论识别视为一类命名实体识别问题,总结现有的命名实体识别的常用方法,提出一个基于语义泛化思想的命名实体识别方法,选取词性、知网义原等外部知识,采用CRF模型对《情报学报》1822篇论文的标题和摘要进行实验。[结果/结论]实验表明,识别准确率最高达到95.38%,但召回率较低;训练语料规模对性能影响较大,不同程度的语义泛化方法对准确率和召回率有复杂影响。如何选择语义特征、语义标注和语义消歧是需要解决的新问题。     

英语广告语篇的语言艺术特点

广告是一门综合艺术。广告创意是现代广告的灵魂,是引起消费者注意、激发消费者购买欲望的驱动力。它的实质是对商 品或服务进行艺术化的渲染和推销。本文着重分析英语广告语篇的语言艺术特征与技巧在语用原则和消费者心理上的体现。     

Reading Format Attitudes in the Time of COVID

The objective of this paper is to investigate the impact of the COVID-19-related changes to educational delivery on students' academic reading format preferences and behaviors. Pre-pandemic studies showed that students preferred print when needing to engage in academic texts for their coursework, and that under certain circumstances, students learned better when using print texts. During the pandemic however, many institutions implemented a sudden shift to remote learning and electronic readings. We questioned whether students would adjust their learning strategies to accommodate the abrupt change, and whether the increased experience with e-formats would boost their favorable attitudes towards digital reading. This study's data from students at a North American university does not support this hypothesis. While some respondents did report improved attitudes towards e-reading during COVID, most attitudes were less favorable or reflected no change. Nearly half the respondents stated that they highlighted and annotated their readings less than they did before, and over a third said they completed their assigned readings less frequently. Negative feelings may reflect a new trend in attitudes or they may be a temporary outcome of general screen fatigue. The findings reinforce the importance of providing print format options for students during this time.     

基于深度学习CNN模型的图像情感特征抽取研究

[目的/意义]以用户情感为线索的图像检索已成为机器学习研究的热点，但图像情感特征标注的语料数据多来源于对图像低层特征的抽取，从而导致图像检索过程单一化和程式化。本文提出了一种基于深度学习的图像情感特征抽取的算法，将图像底层特征融合到图像的高层情感语义当中，为实现图像的情感语义检索提供了参考。[方法/过程]利用改进的卷积网络模型，将数据集图像的颜色、纹理作为输入，经多层运算自动提取图像的情感信息，并通过反向传播算法计算出改进后模型的情感检索准确率，构造出准确率较高且过拟合程度低的图像情感特征提取模型。[结果/结论]应用改进的卷积神经网络模型，实现了对图像情感特征的抽取，相较于原模型提升了10%的检索准确率。     

Dictionary-Based Cross-Language Information Retrieval: Learning Experiences from CLEF 2000–2002

In this study the basic framework and performance analysis results are presented for the three year long development process of the dictionary-based UTACLIR system. The tests expand from bilingual CLIR for three language pairs Swedish, Finnish and German to English, to six language pairs, from English to French, German, Spanish, Italian, Dutch and Finnish, and from bilingual to multilingual. In addition, transitive translation tests are reported. The development process of the UTACLIR query translation system will be regarded from the point of view of a learning process. The contribution of the individual components, the effectiveness of compound handling, proper name matching and structuring of queries are analyzed. The results and the fault analysis have been valuable in the development process. Overall the results indicate that the process is robust and can be extended to other languages. The individual effects of the different components are in general positive. However, performance also depends on the topic set and the number of compounds and proper names in the topic, and to some extent on the source and target language. The dictionaries used affect the performance significantly.     

附加情感特征的在线问答社区信息质量自动化评价

[目的/意义] 考察在线问答社区信息中的情感特征以及其对在线问答社区信息质量自动化评价的影响。[方法/过程] 综合以往研究,提取Yahoo! Answers中的回答信息的文本特征、用户特征、时序特征等,并提出附加情感标注的回答特征,利用Weka机器学习的方法进行信息质量自动化分类预测。[结果/结论] 结果显示,在线问答社区信息中具有一定的情感特征且情感特征的加入能够提高分类预测的准确率。     

基于Word2vec的情感分析在品牌认知中的应用研究

[目的/意义]通过基于Word2vec的文本情感分析技术对某显示器品牌的产品与服务的在线评论进行分析,研究消费者的品牌认知和品牌口碑,为管理者建立更科学的品牌管理体系提供有针对性的建议。[方法/过程]首先利用自然语言处理技术,对评论语料库进行预处理,结合深度学习的Word2vec词向量技术构建产品特征词和情感词词库,进一步构造情感概念对进行情感评分,并将其用于分析品牌产品特定特征的用户情感。[结果/结论]通过Word2vec构建的情感词典相较于传统方法（例如一般的情绪词表）进行情感分析,在情感分析的准确率上有所提高,再结合有效的情感概念对构造与情感评分,可以有效地理解用户的品牌认知。     

Biomedical term extraction: overview and a new methodology

Terminology extraction is an essential task in domain knowledge acquisition, as well as for information retrieval. It is also a mandatory first step aimed at building/enriching terminologies and ontologies. As often proposed in the literature, existing terminology extraction methods feature linguistic and statistical aspects and solve some problems related (but not completely) to term extraction, e.g. noise, silence, low frequency, large-corpora, complexity of the multi-word term extraction process. In contrast, we propose a cutting edge methodology to extract and to rank biomedical terms, covering all the mentioned problems. This methodology offers several measures based on linguistic, statistical, graphic and web aspects. These measures extract and rank candidate terms with excellent precision: we demonstrate that they outperform previously reported precision results for automatic term extraction, and work with different languages (English, French, and Spanish). We also demonstrate how the use of graphs and the web to assess the significance of a term candidate, enables us to outperform precision results. We evaluated our methodology on the biomedical GENIA and LabTestsOnline corpora and compared it with previously reported measures.