基于深度学习和迁移学习的领域自适应中文分词

为了提高专业领域中文分词性能,以及弥补专业领域大规模标注语料难以获取的不足,该文提出基于深度学习以及迁移学习的领域自适应分词方法。首先,构建包含词典特征的基于深度学习的双向长短期记忆条件随机场(BI-LSTM-CRF)分词模型,在通用领域分词语料上训练得到模型参数;接着,以建设工程法律领域文本作为小规模分词训练语料,对通用领域语料的BI-LSTM-CRF分词模型进行参数微调,同时在模型的词典特征中加入领域词典。实验结果表明,迁移学习减少领域分词模型的迭代次数,同时,与通用领域的BI-LSTM-CRF模型相比,该文提出的分词方法在工程法律领域的分词结果F1值提高了7.02%,与预测时加入领域词典的BI-LSTM-CRF模型相比,分词结果的F1值提高了4.22%。该文提出的分词模型可以减少分词的领域训练语料的标注,同时实现分词模型跨领域的迁移。     

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。
     

基于表示学习的中文分词

为提高中文分词的准确率和未登录词（OOV）识别率,提出了一种基于字表示学习方法的中文分词系统。首先使用Skip-gram模型将文本中的词映射为高维向量空间中的向量;其次用K-means聚类算法将词向量聚类,并将聚类结果作为条件随机场（CRF）模型的特征进行训练;最后基于该语言模型进行分词和未登录词识别。对词向量的维数、聚类数及不同聚类算法对分词的影响进行了分析。基于第四届自然语言处理与中文计算会议（NLPCC2015）提供的微博评测语料进行测试,实验结果表明,在未利用外部知识的条件下,分词的F值和OOV识别率分别达到95.67%和94.78%,证明了将字的聚类特征加入到条件随机场模型中能有效提高中文短文本的分词性能。     

面向军事领域的中文分词技术研究

在分词模型跨领域分词时,其性能会有明显的下降。由于标注军队遗留系统开发文档语料的工作比较复杂,本文提出n-gram与词典相结合的中文分词领域自适应方法。该方法通过提取目标语料的n-gram特征训练适应特征领域的分词模型,然后利用领域词典对分词结果进行逆向最大匹配的校正。实验结果表明,在军队遗留系统相关文档语料上,该方法训练的分词模型将F值提高了12.4%。     

基于FMM和CRFs双层分词模型的研究

中文分词是众多自然语言处理任务的基本工作。该文提出了一个用双层模型进行中文分词的方法。首先在低层利用前向最大匹配算法（FMM）进行粗分词,并将切分结果传至高层;在高层利用CRFs对文本重新进行标注,其中低层的识别结果作为CRFs的一项特征,最后将对每个字的标注结果转换为相应的分词结果。,跟以前单独利用CRF进行分词的模型相比．低层模型的加入对CRFs模型的标注起到了重要的辅助作用。在北京大学标注的1998年1月份的人民日报语料上进行了大量的实验,取得了精确率93．31％,召回车92．75％的切分结果,证明该方法是切实可行的。     

基于自监督学习的维基百科家庭关系抽取

传统有监督的关系抽取方法需要大量人工标注的训练语料,而半监督方法则召回率较低,对此提出了一种基于自监督学习来抽取人物家庭关系的方法。该方法首先将中文维基百科的半结构化信息--家庭关系三元组映射到自由文本中,从而自动生成已标注的训练语料;然后,使用基于特征的关系抽取方法从中文维基百科的文本中获取人物间的家庭关系。在一个人工标注的家庭关系网络测试集上的实验结果表明,该方法优于自举方法,其F1指数达到77%,说明自监督学习可以较为有效地抽取人物家庭关系。     

统计与词典相结合的领域自适应中文分词

基于统计的中文分词方法由于训练语料领域的限制,导致其领域自适应性能力较差。相比分词训练语料,领域词典的获取要容易许多,而且能为分词提供丰富的领域信息。该文通过将词典信息以特征的方式融入到统计分词模型(该文使用CRF统计模型)中来实现领域自适应性。实验表明,这种方法显著提高了统计中文分词的领域自适应能力。当测试领域和训练领域相同时,分词的F-measure值提升了2%;当测试领域和训练领域不同时,分词的F-measure值提升了6%。     

基于条件随机场的无监督中文词性标注

中文词性标注是中文信息处理领域的一项基础工作。提出了一种基于条件随机场CRFs(Conditional Random Fields)模型的无监督的中文词性标注方法。首先利用词典对获得的已分好词的生文本进行词性标注,得到初始标注语料,然后利用CRFs对语料进行迭代标注,逐步优化标注结果。并以宾州树库为实验语料,考察了不同规模的标注数据对模型性能的影响,在四份不同规模语料上的实验表明,词性标注正确率提高了1.88%～2.26%。     

基于BLSTM-CRF的领域知识点实体识别技术

传统的中文分词方法是一种基于单词标注的传统机器学习方法,但学习方法需要人工配置和提取中文文本的特征。缺点是同义词库维度较高且CPU训练模型较长。本文针对以上问题进行了研究,构建了内嵌条件随机场的长短时神经网络模型,使用长短时神经网络隐含层的上下文向量作为输出层标注的特征,使用内嵌的条件随机场模型表示标注之间的约束关系采用双向LSTM和CRF相结合的训练方法进行特定领域知识点的中文分词。对中文分词测试常用语料库的实验比较表明,基于BLSTM和CRF网络模型的方法可以获得比传统机器学习方法更好的性能;使用六字标记并添加预训练的字嵌入向量可以实现相对较好的分词性能;BLSTM-CRF网络模型方法更易于推广并应用于其他自然语言处理中的序列标注任务。     

一种基于统计的分词标注一体化方法

分词标注是中文信息处理的基础。传统方法的处理步骤大都是首先对文本进行预处理,得到文本的粗分模型,在此基础上对词语进行词性标注。粗分模型集合的大小取决于采用的分词方法,粗分模型的准确性直接影响着后续处理结果的准确性。提出一种基于统计的分词标注一体化方法即概率全切分标注模型,该方法的特点是将分词、标注两部分工作融为一体同时进行,在利用全切分获得所有可能分词结果的过程中,计算出每种词串的联合概率,同时利用马尔可夫模型计算出每种词串所有可能标记序列的概率,由此得到最可能的处理结果。该方法提高了结果的召回率和准确率     

A hybrid method for entity hyponymy acquisition in Chinese complex sentences

Extracting entity hyponymy in Chinese complex sentences can be a highly difficult process. This paper proposes a novel hybrid approach that combines parsing with supervised learning and semi-supervised learning. First, conditional random fields (CRF) model is employed to obtain the candidate domain named entity. Pattern matching is then used to acquire candidate hyponymy. Next, predicate and symbol features, syntactic analysis, and semantic roles are introduced into the CRF features template to identify the hyponymy entity pairs. Finally, analysis of both the parallel relationship of entities among sentences and entity pairs in simple sentences is conducted to obtain the hyponymy entity pairs in Chinese complex sentences. The experimental results show that the proposed method reduces the manual work required for CRF markers and has an improved overall performance in comparison with the baseline methods.     

Lexicon based semantic detection of sentiments using expected likelihood estimate smoothed odds ratio

Sentiment analysis is an active research area in today’s era due to the abundance of opinionated data present on online social networks. Semantic detection is a sub-category of sentiment analysis which deals with the identification of sentiment orientation in any text. Many sentiment applications rely on lexicons to supply features to a model. Various machine learning algorithms and sentiment lexicons have been proposed in research in order to improve sentiment categorization. Supervised machine learning algorithms and domain specific sentiment lexicons generally perform better as compared to the unsupervised or semi-supervised domain independent lexicon based approaches. The core hindrance in the application of supervised algorithms or domain specific sentiment lexicons is the unavailability of sentiment labeled training datasets for every domain. On the other hand, the performance of algorithms based on general purpose sentiment lexicons needs improvement. This research is focused on building a general purpose sentiment lexicon in a semi-supervised manner. The proposed lexicon defines word semantics based on Expected Likelihood Estimate Smoothed Odds Ratio that are then incorporated with supervised machine learning based model selection approach. A comprehensive performance comparison verifies the superiority of our proposed approach.     

基于迁移学习的讽刺检测

准确的讽刺检测对于情感分析等任务至关重要.传统的方法严重依赖于离散的人工制定的特征.现有的研究大多将讽刺检测作为一种标准的监督学习文本分类任务,但是监督学习需要有大量数据,而这些数据的收集和标注都存在困难.由于目标任务有限的数据集可能导致讽刺检测的低性能,为此将讽刺检测作为一种迁移学习任务,将讽刺标记文本的监督学习与外部分析资源的知识转移相结合.通过转移的资源知识来改进神经网络模型,以此提升对目标任务的检测性能.在公开可用的数据集上的实验结果表明,提出的基于迁移学习的讽刺检测模型优于现有较先进的讽刺检测模型.     

基于典型相关分析的多视图跨领域情感分类

跨领域的文本分类,是指利用有标记领域的知识去帮助另一个概率分布不同的,未标记领域的知识进行分类的问题。从多视图学习的视角提出一个新的跨领域文本分类的方法(MTV算法)。通过在核空间典型相关分析中引入与标记相关的信息,MTV算法可以得到一个判别性能更优的公共子空间。在多个情感类文本数据上的实验表明,MTV算法可以大大提升传统监督式学习算法面对领域迁移时的分类性能,并且在引入判别式的核空间典型相关分析后,进一步优化性能。     

Knowledge-guided unsupervised rhetorical parsing for text summarization

Automatic text summarization (ATS) has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale corpora. However, there is still no guarantee that the generated summaries are grammatical, concise, and convey all salient information as the original documents have. To make the summarization results more faithful, this paper presents an unsupervised approach that combines rhetorical structure theory, deep neural model, and domain knowledge concern for ATS. This architecture mainly contains three components: domain knowledge base construction based on representation learning, the attentional encoder–decoder model for rhetorical parsing, and subroutine-based model for text summarization. Domain knowledge can be effectively used for unsupervised rhetorical parsing thus rhetorical structure trees for each document can be derived. In the unsupervised rhetorical parsing module, the idea of translation was adopted to alleviate the problem of data scarcity. The subroutine-based summarization model purely depends on the derived rhetorical structure trees and can generate content-balanced results. To evaluate the summary results without golden standard, we proposed an unsupervised evaluation metric, whose hyper-parameters were tuned by supervised learning. Experimental results show that, on a large-scale Chinese dataset, our proposed approach can obtain comparable performances compared with existing methods.     

基于半监督学习的中文社交文本事件聚类方法

面向社交媒体的事件聚类旨在根据事件特征实现短文本聚类.目前,事件聚类模型主要分为无监督模型和有监督模型.无监督模型聚类效果较差,有监督聚类模型依赖大量标注数据.基于此,该文提出了一种半监督事件聚类模型(SemiEC),该模型在小规模标注数据的基础上,利用LSTM表征事件,并基于线性模型计算文本相似度,进行增量聚类.然后...     

Label Propagation through Linear Neighborhoods

In many practical data mining applications such as text classification, unlabeled training examples are readily available, but labeled ones are fairly expensive to obtain. Therefore, semi supervised learning algorithms have aroused considerable interests from the data mining and machine learning fields. In recent years, graph-based semi supervised learning has been becoming one of the most active research areas in the semi supervised learning community. In this paper, a novel graph-based semi supervised learning approach is proposed based on a linear neighborhood model, which assumes that each data point can be linearly reconstructed from its neighborhood. Our algorithm, named linear neighborhood propagation (LNP), can propagate the labels from the labeled points to the whole data set using these linear neighborhoods with sufficient smoothness. A theoretical analysis of the properties of LNP is presented in this paper. Furthermore, we also derive an easy way to extend LNP to out-of-sample data. Promising experimental results are presented for synthetic data, digit, and text classification tasks.     

特定领域的命名实体识别方法的研究

在特定领域的命名实体识别技术中,针对不同领域有各种不同的识别方法。不同领域文本具有其独特的文本特征,这导致已有领域的识别方法难以适应新的特定领域。针对该问题,提出一种基于条件随机场、半监督学习和主动学习相结合的方法,将其形成一个统一的技术框架来适应各个特定领域的命名实体识别。该方法首先选取特定文本的基本通用特征构建特征集合,训练条件随机场对特定领域进行命名实体的初步识别,再通过主动选取置信度低于选定阈值的样本进行人工标注,并迭代扩展训练样本来达到高识别效果。为验证所提方法,针对轨道交通领域文本进行了实验,实验结果表明该方法行之有效,在轨道交通领域取得了较好的识别效果。     

基于深度学习的医疗命名实体识别

在较为深入地研究医疗文本实体识别的现有方法的基础上,设计一种基于深度学习的医疗文本实体识别方法。本文在医疗文本数据集上进行实体识别对比实验,所识别目标实体包含疾病,症状,药品,治疗方法和检查五大类。实验结果表明,设计的深度神经网络模型能够很好的应用到医疗文本实体识别,本文所设计的方法比传统算法（如CRF）具有较少人工特征干预及更高的准确率和召回率等优点。     

Boosting for transfer learning from multiple data sources

Transfer learning aims at adapting a classifier trained on one domain with adequate labeled samples to a new domain where samples are from a different distribution and have no class labels. In this paper, we explore the transfer learning problems with multiple data sources and present a novel boosting algorithm, SharedBoost. This novel algorithm is capable of applying for very high dimensional data such as in text mining where the feature dimension is beyond several ten thousands. The experimental results illustrate that the SharedBoost algorithm significantly outperforms the traditional methods which transfer knowledge with supervised learning techniques. Besides, SharedBoost also provides much better classification accuracy and more stable performance than some other typical transfer learning methods such as the structural correspondence learning (SCL) and the structural learning in the multiple sources transfer learning problems.