面向微博文本的情绪标注语料库构建

文本情绪分析研究近年来发展迅速,但相关的中文情绪语料库,特别是面向微博文本的语料库构建尚不完善。为了对微博文本情绪表达特点进行分析以及对情绪分析算法性能进行评估,该文在对微博文本情绪表达特点进行深入观察和分析的基础上,设计了一套完整的情绪标注规范。遵循这一规范,首先对微博文本进行了微博级情绪标注,对微博是否包含情绪及有情绪微博所包含的情绪类别进行多标签标注。而后,对微博中的句子进行有无情绪及情绪类别进行标注,并标注了各情绪类别对应的强度。目前,已完成14000条微博,45431句子的情绪标注语料库构建。应用该语料库组织了NLP&CC2013中文微博情绪分析评测,有力地促进了微博情绪分析相关研究。     

DO WE AGREE? MEASURING AGREEMENT ON THE HUMAN JUDGMENTS IN EMOTION ANNOTATION OF NEWS SENTENCES

An emotional text may be judged to belong to multiple emotion categories because it may evoke different emotions with varying degrees of intensity. For emotion analysis of text in a supervised manner, it is required to annotate text corpus with emotion categories. Because emotion is a very subjective entity, producing reliable annotation is of prime requirement for developing a robust emotion analysis model, so it is wise to have the data set annotated by multiple human judges and generate an aggregated data set provided that the emotional responses provided by different annotators over the data set exhibit substantial agreement. In reality, multiple emotional responses for an emotional text are common. So, the data set is a multilabel one where a single data item may belong to more than one category simultaneously. This article presents a new agreement measure to compute interannotator reliability in multilabel annotation. The new reliability coefficient has been applied to measure the quality of an emotion text corpus. The procedure for generating aggregated data and some corpus cleaning techniques are also discussed.     

一种基于情绪表达与情绪认知分离的新型情绪词典

目前的情绪词典通常对情绪词语进行情绪类别和强度的标注,但缺乏对词语的情绪表达和情绪认知结果进行区分的能力。同时,直接在词语条目上进行标注经常由于词语的语义歧义导致情绪标注结果存在歧义。该文在对个体情绪产生和迁移机制进行分析的基础上,建立了基于“刺激认知—反射表达”的文本情绪计算框架。并在此框架下对情绪相关词语的功能和特性进行分析,探索了一种新型情绪词典建设方法。首先,引入HowNet提供的词语语义信息,将同一词语转变为不同语义的多个词条进行标注减少情绪标注歧义。其次,将词语的情绪表达方式和情绪认知结果加以区分,分别标注从不同角度观测到的词条情绪类别和强度,同时对词语的情绪表达和情绪认知类型进行了细化分类。最终初步构建出一个具有清晰框架、丰富情绪信息和较低歧义的新型情绪词典。     

基于Active Learning的中文分词领域自适应

在新闻领域标注语料上训练的中文分词系统在跨领域时性能会有明显下降。针对目标领域的大规模标注语料难以获取的问题,该文提出Active learning算法与n-gram统计特征相结合的领域自适应方法。该方法通过对目标领域文本与已有标注语料的差异进行统计分析,选择含有最多未标记过的语言现象的小规模语料优先进行人工标注,然后再结合大规模文本中的n-gram统计特征训练目标领域的分词系统。该文采用了CRF训练模型,并在100万句的科技文献领域上,验证了所提方法的有效性,评测数据为人工标注的300句科技文献语料。实验结果显示,在科技文献测试语料上,基于Active Learning训练的分词系统在各项评测指标上均有提高。
     

Segment-based emotion recognition from continuous Mandarin Chinese speech

Recognition of emotion in speech has recently matured to one of the key disciplines in speech analysis serving next generation human-machine interaction and communication. However, compared to automatic speech recognition, that emotion recognition from an isolated word or a phrase is inappropriate for conversation. Because a complete emotional expression may stride across several sentences, and may fetch-up on any word in dialogue. In this paper, we present a segment-based emotion recognition approach to continuous Mandarin Chinese speech. In this proposed approach, the unit for recognition is not a phrase or a sentence but an emotional expression in dialogue. To that end, the following procedures are presented: First, we evaluate the performance of several classifiers in short sentence speech emotion recognition architectures. The results of the experiments show that the WD-KNN classifier achieves the best accuracy for the 5-class emotion recognition what among the five classification techniques. We then implemented a continuous Mandarin Chinese speech emotion recognition system with an emotion radar chart which is based on WD-KNN; this system can represent the intensity of each emotion component in speech. This proposed approach shows how emotions can be recognized by speech signals, and in turn how emotional states can be visualized.     

加权维吾尔语句子倾向性分析

准确可靠的文本倾向性分析是网络舆情分析与网络内容安全的前提.本文提出了利用中文极性情感词典HowNet、NTUSD以及大连理工大学发布的褒贬情感词词典进行并交运算,选择并翻译为维吾尔语词汇,借助于维吾尔语同义近义词词典,扩展构建了维吾尔语极性情感词典;然后分析总结了否定词、程度副词以及句中的转折连词等情感修饰成分对维吾尔语句子情感极性的影响,并量化为情感词权值;最后设计了基于维吾尔语极性情感词和权值相结合的加权句子情感极性判定算法.利用自建语料库进行测试,并与汉语倾向性判定实验结果比较,证明了本算法进行维吾尔语句子褒贬情感性分析基本是有效地.     

基于PLSA的新闻评论情绪类别自动标注方法

针对大规模语料手动标注困难的问题，提出利用概率潜在语义分析（PLSA）模型的新闻评论自动标注方法.利用PLSA计算获得语料集的"文档-主题"和"词语-主题"概率矩阵；基于情感本体库和"词语-主题"概率矩阵，认为某一类情绪词汇出现的概率最高的主题与词汇的情绪类别相同，对主题进行情绪类别标注；最后，基于"文档-主题"概率矩阵，认为出现在某一主题概率最高的文档与主题的情绪类别相同，通过"词汇-主题-文档"三者的关系，达到自动标注的效果.实验结果表明，本文提出的方法准确率可达到90%以上.     

基于语义角色标注的汉语句子相似度算法

在语义角色标注过程中,经常需要检索相似的已标注语料,以便进行参考和分析。现有方法未能充分利用动词及其支配的成分信息,无法满足语义角色标注的相似句检索需求。基于此,本文提出一种新的汉语句子相似度计算方法。该方法基于已标注好语义角色的语料资源,以动词为分析核心,通过语义角色分析、标注句型的相似匹配、标注句型间相似度计算等步骤来实现句子语义的相似度量。为达到更好的实验效果,论文还综合比较了基于知网、词向量等多种计算词语相似度的算法,通过分析与实验对比,将实验效果最好的算法应用到句子相似度计算的研究中。实验结果显示,基于语义角色标注的句子相似度计算方法相对传统方法获得了更好的测试结果。     

Estimation of word emotions based on part of speech and positional information

Recently, studies on emotion recognition technology have been conducted in the fields of natural language processing, speech signal processing, image data processing, and brain wave analysis, with the goal of letting the computer understand ambiguous information such as emotion or sensibility. This paper statistically studies the features of Japanese and English emotional expressions based on an emotion annotated parallel corpus and proposes a method to estimate emotion of the emotional expressions in the sentence. The proposed method identifies the words or phrases with emotion, which we call emotional expressions, and estimates the emotion category of the emotional expressions by focusing on the three kinds of features: part of speech of emotional expression, position of emotional expression, and part of speech of the previous/next morpheme of the target emotional expression.     

Automatically annotating a five-billion-word corpus of Japanese blogs for sentiment and affect analysis

This paper presents our research on automatic annotation of a five-billion-word corpus of Japanese blogs with information on affect and sentiment. We first perform a study in emotion blog corpora to discover that there has been no large scale emotion corpus available for the Japanese language. We choose the largest blog corpus for the language and annotate it with the use of two systems for affect analysis: ML-Ask for word- and sentence-level affect analysis and CAO for detailed analysis of emoticons. The annotated information includes affective features like sentence subjectivity (emotive/non-emotive) or emotion classes (joy, sadness, etc.), useful in affect analysis. The annotations are also generalized on a two-dimensional model of affect to obtain information on sentence valence (positive/negative), useful in sentiment analysis. The annotations are evaluated in several ways. Firstly, on a test set of a thousand sentences extracted randomly and evaluated by over forty respondents. Secondly, the statistics of annotations are compared to other existing emotion blog corpora. Finally, the corpus is applied in several tasks, such as generation of emotion object ontology or retrieval of emotional and moral consequences of actions.     

EmoTales: creating a corpus of folk tales with emotional annotations

Emotions are inherent to any human activity, including human–computer interactions, and that is the reason why recognizing emotions expressed in natural language is becoming a key feature for the design of more natural user interfaces. In order to obtain useful corpora for this purpose, the manual classification of texts according to their emotional content has been the technique most commonly used by the research community. The use of corpora is widespread in Natural Language Processing, and the existing corpora annotated with emotions support the development, training and evaluation of systems using this type of data. In this paper we present the development of an annotated corpus oriented to the narrative domain, called EmoTales, which uses two different approaches to represent emotional states: emotional categories and emotional dimensions. The corpus consists of a collection of 1,389 English sentences from 18 different folk tales, annotated by 36 different people. Our model of the corpus development process includes a post-processing stage performed after the annotation of the corpus, in which a reference value for each sentence was chosen by taking into account the tags assigned by annotators and some general knowledge about emotions, which is codified in an ontology. The whole process is presented in detail, and revels significant results regarding the corpus such as inter-annotator agreement, while discussing topics such as how human annotators deal with emotional content when performing their work, and presenting some ideas for the application of this corpus that may inspire the research community to develop new ways to annotate corpora using a large set of emotional tags.     

A comparative study of dictionaries and corpora as methods for language resource addition

In this paper, we investigate the relative effect of two strategies for language resource addition for Japanese morphological analysis, a joint task of word segmentation and part-of-speech tagging. The first strategy is adding entries to the dictionary and the second is adding annotated sentences to the training corpus. The experimental results showed that addition of annotated sentences to the training corpus is better than the addition of entries to the dictionary. In particular, adding annotated sentences is especially efficient when we add new words with contexts of several real occurrences as partially annotated sentences, i.e. sentences in which only some words are annotated with word boundary information. According to this knowledge, we performed real annotation experiments on invention disclosure texts and observed word segmentation accuracy. Finally we investigated various language resource addition cases and introduced the notion of non-maleficence, asymmetricity, and additivity of language resources for a task. In the WS case, we found that language resource addition is non-maleficent (adding new resources causes no harm in other domains) and sometimes additive (adding new resources helps other domains). We conclude that it is reasonable for us, NLP tool providers, to distribute only one general-domain model trained from all the language resources we have.     

基于朴素贝叶斯与潜在狄利克雷分布相结合的情感分析

针对情感分析需要大量人工标注语料的难点,提出了一种面向无指导情感分析的层次性生成模型。该模型将朴素贝叶斯(NB)模型和潜在狄利克雷分布(LDA)相结合,仅仅需要合适的情感词典,不需要篇章级别和句子级别的标注信息即可同时对网络评论的篇章级别和句子级别的情感倾向进行分析。该模型假设每个句子而不是每个单词拥有一个潜在的情感变量;然后,该情感变量再以朴素贝叶斯的方式生成一系列独立的特征。在该模型中,朴素贝叶斯假设的引入使得该模型可以结合自然语言处理(NLP)相关的技术,例如依存分析、句法分析等,用以提高无指导情感分析的性能。在两个情感语料数据集上的实验结果显示,该模型能够自动推导出篇章级别和句子级别的情感极性,该模型的正确率显著优于其他无指导的方法,甚至接近部分半指导或有指导的研究方法。     

融合概念对齐信息的中文AMR语料库的构建

作为一种新的句子语义表示方法,抽象语义表示(AMR)将一个句子抽象为单根有向无环图,目前已经建立了较大规模的英文语料库。然而,句子中的词语和AMR图的概念对齐信息缺失,使得自动分析效果和语料标注质量受到影响,同时中文尚无较大规模的AMR语料库。该文介绍了中文AMR语料库的构建工作,针对汉语特点调整了AMR的标注体系,增加对复句关系的标注,提出了融合概念对齐的一体化标注方案,解决了中英文输入法频繁切换的问题,增加了错别字纠正和未标注词高亮功能,提高了标注效率。然后,从CTB中选取了6 923句进行人工标注,形成中文AMR语料库,统计得到图和环的比例分别为48%和1%,以及利用对齐信息才能获取的非投影句的比例32%,为中文AMR的理论和自动分析研究奠定基础。     

基于上下文相关字向量的中文命名实体识别

命名实体识别(NER)旨在识别出文本中的专有名词,并对其进行分类。由于用于监督学习的训练数据通常由人工标注,耗时耗力,因此很难得到大规模的标注数据。为解决中文命名实体识别任务中因缺乏大规模标注语料而造成的数据稀缺问题,以及传统字向量不能解决的一字多义问题,文中使用在大规模无监督数据上预训练的基于上下文相关的字向量,即利用语言模型生成上下文相关字向量以改进中文NER模型的性能。同时,为解决命名实体识别中的未登录词问题,文中提出了基于字语言模型的中文NER系统。把语言模型学习到的字向量作为NER模型的输入,使得同一中文汉字在不同语境中有不同的表示。文中在6个中文NER数据集上进行了实验。实验结果表明,基于上下文相关的字向量可以很好地提升NER模型的性能,其平均性能F1值提升了4.95%。对实验结果进行进一步分析发现,新系统在OOV实体识别上也可以取得很好的效果,同时对一些特殊类型的中文实体识别也有不错的表现。     

一种基于情感句模的文本情感分类方法

考虑到同类型的情感句往往具有相同或者相似的句法和语义表达模式,该文提出了一种基于情感句模的文本情感自动分类方法。首先,将情感表达相关句模人工分为3大类105个二级分类;然后,设计了一种利用依存特征、句法特征和同义词特征的句模获取方法,从标注情感句中半自动地获取情感句模。最后,通过对输入句进行情感句模分类实现文本情感分类。在NLP&CC2013中文微博情绪分类评测语料及RenCECps博客语料的实验结果显示,该文提出的分类方法准确率显著高于基于词特征支持向量机分类器。     

基于深度半监督的柬语句子级情感分类

针对柬语标注数据较少、语料稀缺,柬语句子级情感分析任务进步缓慢的问题,提出了一种基于深度半监督CNN(convolutional neural networks)的柬语句子级情感极性分类方法.该方法通过融合词典嵌入的分开卷积CNN模型,利用少量已有的柬语情感词典资源提升句子级情感分类任务性能.首先构建柬语句子词嵌入和词典嵌入,通过使用不同的卷积核对两部分嵌入分别进行卷积,将已有情感词典信息融入到CNN模型中去,经过最大延时池化得到最大输出特征,把两部分最大输出特征拼接后作为全连接层输入;然后通过结合半监督学习方法——时序组合模型,训练提出的深度神经网络模型,利用标注与未标注语料训练,降低对标注语料的需求,进一步提升模型情感分类的准确性.结果 证明,通过半监督方法时序组合模型训练,在人工标记数据相同的情况下,该方法相较于监督方法在柬语句子级情感分类任务上准确率提升了3.89％.     

基于耦合关系的情感词语义分析方法

针对传统话题模型不能很好地获取文本情感信息并进行情感分类的问题,提出了情感LDA（latent Dirichlet allocation）模型,并通过对文本情感进行建模分析,提出了情感词耦合关系的LDA模型。该模型不但考虑了情感词的话题语境,而且考虑了词的情感耦合关系,并且通过引入情感变量对情感词的概率分布进行控制,采用隐马尔科夫模型对情感词耦合关系的转移进行建模分析。实验表明,该模型可以对情感词耦合关系和话题同时进行分析,不仅能有效地进行文本情感建模,而且提升了情感分类结果的准确度。     

基于图排序的词汇情感消歧研究

词汇情感消歧是文本情感倾向性分析的关键技术之一。该文在分析比较了词汇情感消歧和词义消歧异同后,从情感分析角度出发,提出了基于图排序的词汇情感消歧方法。该方法通过自动获取和人工校正相结合的方式获得多情感词汇,然后根据语义关系构建词义关系图,进而在词义关系图上迭代计算直至收敛,最后选择多情感词汇的词义中权值最大的词义作为结果输出,从而实现情感消歧。该文分别在新浪微博语料库和情感语料库上验证了该方法的有效性。