Combining lexical, syntactic and prosodic cues for improved online dialog act tagging

Prosody is an important cue for identifying dialog acts. In this paper, we show that modeling the sequence of acoustic–prosodic values as n-gram features with a maximum entropy model for dialog act (DA) tagging can perform better than conventional approaches that use coarse representation of the prosodic contour through summative statistics of the prosodic contour. The proposed scheme for exploiting prosody results in an absolute improvement of 8.7% over the use of most other widely used representations of acoustic correlates of prosody. The proposed scheme is discriminative and exploits context in the form of lexical, syntactic and prosodic cues from preceding discourse segments. Such a decoding scheme facilitates online DA tagging and offers robustness in the decoding process, unlike greedy decoding schemes that can potentially propagate errors. Our approach is different from traditional DA systems that use the entire conversation for offline dialog act decoding with the aid of a discourse model. In contrast, we use only static features and approximate the previous dialog act tags in terms of lexical, syntactic and prosodic information extracted from previous utterances. Experiments on the Switchboard-DAMSL corpus, using only lexical, syntactic and prosodic cues from three previous utterances, yield a DA tagging accuracy of 72% compared to the best case scenario with accurate knowledge of previous DA tags (oracle), which results in 74% accuracy.     

限定领域口语对话系统中超出领域话语的对话行为识别

由于领域外话语具有内容短小、表达多样性、开放性及口语化等特点,限定领域口语对话系统中超出领域话语的对话行为识别是一个挑战。该文提出了一种结合外部无标签微博数据的随机森林对话行为识别方法。该文采用的微博数据无需根据应用领域特点专门收集和挑选,又与口语对话同样具有口语化和表达多样性的特点,其训练得到的词向量在超出领域话语出现超出词汇表字词时提供了有效的相似性扩展度量。随机森林模型具有较好的泛化能力,适合训练数据有限的分类任务。中文特定领域的口语对话语料库测试表明,该文提出的超出领域话语的对话行为识别方法取得了优于最大熵、卷积神经网络等短文本分类研究进展中的方法的效果。     

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。     

An analysis of prosodic information for the recognition of dialogue acts in a multimodal corpus in Mexican Spanish

This paper presents empirical results of an analysis on the role of prosody in the recognition of dialogue acts and utterance mood in a practical dialogue corpus in Mexican Spanish. The work is configured as a series of machine-learning experimental conditions in which models are created by using intonational and other data as predictors and dialogue act tagging data as targets. We show that utterance mood can be predicted from intonational information, and that this mood information can then be used to recognize the dialogue act.     

Sentence alignment using P-NNT and GMM

Parallel corpora have become an essential resource for work in multilingual natural language processing. However, sentence aligned parallel corpora are more efficient than non-aligned parallel corpora for cross-language information retrieval and machine translation applications. In this paper, we present two new approaches to align English–Arabic sentences in bilingual parallel corpora based on probabilistic neural network (P-NNT) and Gaussian mixture model (GMM) classifiers. A feature vector is extracted from the text pair under consideration. This vector contains text features such as length, punctuation score, and cognate score values. A set of manually prepared training data was assigned to train the probabilistic neural network and Gaussian mixture model. Another set of data was used for testing. Using the probabilistic neural network and Gaussian mixture model approaches, we could achieve error reduction of 27% and 50%, respectively, over the length based approach when applied on a set of parallel English–Arabic documents. In addition, the results of (P-NNT) and (GMM) outperform the results of the combined model which exploits length, punctuation and cognates in a dynamic framework. The GMM approach outperforms Melamed and Moore’s approaches too. Moreover these new approaches are valid for any languages pair and are quite flexible since the feature vector may contain more, less or different features, such as a lexical matching feature and Hanzi characters in Japanese–Chinese texts, than the ones used in the current research.     

Sentence similarity based on semantic nets and corpus statistics

Sentence similarity measures play an increasingly important role in text-related research and applications in areas such as text mining, Web page retrieval, and dialogue systems. Existing methods for computing sentence similarity have been adopted from approaches used for long text documents. These methods process sentences in a very high-dimensional space and are consequently inefficient, require human input, and are not adaptable to some application domains. This paper focuses directly on computing the similarity between very short texts of sentence length. It presents an algorithm that takes account of semantic information and word order information implied in the sentences. The semantic similarity of two sentences is calculated using information from a structured lexical database and from corpus statistics. The use of a lexical database enables our method to model human common sense knowledge and the incorporation of corpus statistics allows our method to be adaptable to different domains. The proposed method can be used in a variety of applications that involve text knowledge representation and discovery. Experiments on two sets of selected sentence pairs demonstrate that the proposed method provides a similarity measure that shows a significant correlation to human intuition.     

结合字形特征与迭代学习的金融领域命名实体识别

针对中文金融文本领域的命名实体识别,该文从汉字自身特点出发,设计了结合字形特征、迭代学习以及双向长短时记忆网络和条件随机场的神经网络模型。该模型是一种完全端到端且不涉及任何特征工程的模型,其将汉字的五笔表示进行编码以进行信息增强,同时利用迭代学习的策略不断对模型整体预测结果进行改进。由于现有的命名实体识别研究在金融领域缺乏高质量的有标注的语料库资源,所以该文构建了一个大规模的金融领域命名实体语料库HITSZ-Finance,共计31 210个文本句,包含4类实体。该文在语料库HITSZ-Finance上进行了一系列实验,实验结果均表明模型的有效性。     

Learning to Recognize Objects with Little Supervision

This paper shows (i) improvements over state-of-the-art local feature recognition systems, (ii) how to formulate principled models for automatic local feature selection in object class recognition when there is little supervised data, and (iii) how to formulate sensible spatial image context models using a conditional random field for integrating local features and segmentation cues (superpixels). By adopting sparse kernel methods, Bayesian learning techniques and data association with constraints, the proposed model identifies the most relevant sets of local features for recognizing object classes, achieves performance comparable to the fully supervised setting, and obtains excellent results for image classification.     

Exploring the fine-grained analysis and automatic detection of irony on Twitter

To push the state of the art in text mining applications, research in natural language processing has increasingly been investigating automatic irony detection, but manually annotated irony corpora are scarce. We present the construction of a manually annotated irony corpus based on a fine-grained annotation scheme that allows for identification of different types of irony. We conduct a series of binary classification experiments for automatic irony recognition using a support vector machine (SVM) that exploits a varied feature set and compare this method to a deep learning approach that is based on an LSTM network and (pre-trained) word embeddings. Evaluation on a held-out corpus shows that the SVM model outperforms the neural network approach and benefits from combining lexical, semantic and syntactic information sources. A qualitative analysis of the classification output reveals that the classifier performance may be further enhanced by integrating implicit sentiment information and context- and user-based features.     

Lexical association measures and collocation extraction

We present an extensive empirical evaluation of collocation extraction methods based on lexical association measures and their combination. The experiments are performed on three sets of collocation candidates extracted from the Prague Dependency Treebank with manual morphosyntactic annotation and from the Czech National Corpus with automatically assigned lemmas and part-of-speech tags. The collocation candidates were manually labeled as collocational or non-collocational. The evaluation is based on measuring the quality of ranking the candidates according to their chance to form collocations. Performance of the methods is compared by precision-recall curves and mean average precision scores. The work is focused on two-word (bigram) collocations only. We experiment with bigrams extracted from sentence dependency structure as well as from surface word order. Further, we study the effect of corpus size on the performance of the individual methods and their combination.     

Using Bayesian Networks to Manage Uncertainty in Student Modeling

When a tutoring system aims to provide students with interactive help, it needs to know what knowledge the student has and what goals the student is currently trying to achieve. That is, it must do both assessment and plan recognition. These modeling tasks involve a high level of uncertainty when students are allowed to follow various lines of reasoning and are not required to show all their reasoning explicitly. We use Bayesian networks as a comprehensive, sound formalism to handle this uncertainty. Using Bayesian networks, we have devised the probabilistic student models for Andes, a tutoring system for Newtonian physics whose philosophy is to maximize student initiative and freedom during the pedagogical interaction. Andes’ models provide long-term knowledge assessment, plan recognition, and prediction of students’ actions during problem solving, as well as assessment of students’ knowledge and understanding as students read and explain worked out examples. In this paper, we describe the basic mechanisms that allow Andes’ student models to soundly perform assessment and plan recognition, as well as the Bayesian network solutions to issues that arose in scaling up the model to a full-scale, field evaluated application. We also summarize the results of several evaluations of Andes which provide evidence on the accuracy of its student models.This revised version was published online in July 2005 with corrections to the author name VanLehn.     

Statistical Translation of Text and Speech: First Results with the RWTH System

In this paper, we describe a first version of a system for statisticaltranslation and present experimental results. The statistical translationapproach uses two types of information: a translation model and a languagemodel. The language model used is a standard bigram model. The translationmodel is decomposed into lexical and alignment models. After presenting the details of the alignment model, we describe the search problem and present a dynamic programming-based solution for the special case of monotone alignments.So far, the system has been tested on two limited-domain tasks for which abilingual corpus is available: the EuTrans traveller task (Spanish–English,500-word vocabulary) and the Verbmobil task (German–English, 3000-wordvocabulary). We present experimental results on these tasks. In addition to the translation of text input, we also address the problem of speech translation and suitable integration of the acoustic recognition process and the translation process.     

Optimising dynamic graphical models for video content analysis

A key problem in video content analysis using dynamic graphical models is to learn a suitable model structure given observed visual data. We propose a completed likelihood AIC (CL-AIC) scoring function for solving the problem. CL-AIC differs from existing scoring functions in that it aims to optimise explicitly both the explanation and prediction capabilities of a model simultaneously. CL-AIC is derived as a general scoring function suitable for both static and dynamic graphical models with hidden variables. In particular, we formulate CL-AIC for determining the number of hidden states for a hidden Markov model (HMM) and the topology of a dynamically multi-linked HMM (DML-HMM). The effectiveness of CL-AIC on learning the optimal structure of a dynamic graphical model especially given sparse and noisy visual date is shown through comparative experiments against existing scoring functions including Bayesian information criterion (BIC), Akaike’s information criterion (AIC), integrated completed likelihood (ICL), and variational Bayesian (VB). We demonstrate that CL-AIC is superior to the other scoring functions in building dynamic graphical models for solving two challenging problems in video content analysis: (1) content based surveillance video segmentation and (2) discovering causal/temporal relationships among visual events for group activity modelling.     

Automatic dialogue act recognition with syntactic features

This work studies the usefulness of syntactic information in the context of automatic dialogue act recognition in Czech. Several pieces of evidence are presented in this work that support our claim that syntax might bring valuable information for dialogue act recognition. In particular, a parallel is drawn with the related domain of automatic punctuation generation and a set of syntactic features derived from a deep parse tree is further proposed and successfully used in a Czech dialogue act recognition system based on conditional random fields. We finally discuss the possible reasons why so few works have exploited this type of information before and propose future research directions to further progress in this area.     

动态迁移实体块信息的跨领域中文实体识别模型

由于中文文本之间没有分隔符,难以识别中文命名实体的边界.此外,在垂直领域中难以获取充足的标记完整的语料,例如医疗领域和金融领域等垂直领域.为解决上述不足,提出一种动态迁移实体块信息的跨领域中文实体识别模型(TES-NER),将跨领域共享的实体块信息(entity span)通过基于门机制(gate mechanism)的动态融合层,从语料充足的通用领域(源领域)动态迁移到垂直领域(目标领域)上的中文命名实体模型,其中,实体块信息用于表示中文命名实体的范围.TES-NER模型首先通过双向长短期记忆神经网络(BiLSTM)和全连接网络(FCN)构建跨领域共享实体块识别模块,用于识别跨领域共享的实体块信息以确定中文命名实体的边界;然后,通过独立的基于字的双向长短期记忆神经网络和条件随机场(BiLSTM-CRF)构建中文命名实体识别模块,用于识别领域指定的中文命名实体;最后构建动态融合层,将实体块识别模块抽取得到的跨领域共享实体块信息通过门机制动态决定迁移到领域指定的命名实体识别模型上的量.设置通用领域(源领域)数据集为标记语料充足的新闻领域数据集(MSRA),垂直领域(目标领域)数据集为混合领域(OntoNotes 5.0)、金融领域(Resume)和医学领域(CCKS 2017)这3个数据集,其中,混合领域数据集(OntoNotes 5.0)是融合了6个不同垂直领域的数据集.实验结果表明,提出的模型在OntoNotes 5.0、Resume和CCKS 2017这3个垂直领域数据集上的F1值相比于双向长短期记忆和条件随机场模型(BiLSTM-CRF)分别高出2.18%、1.68%和0.99%.     

TermFinder: log-likelihood comparison and phrase-based statistical machine translation models for bilingual terminology extraction

Bilingual termbanks are important for many natural language processing applications, especially in translation workflows in industrial settings. In this paper, we apply a log-likelihood comparison method to extract monolingual terminology from the source and target sides of a parallel corpus. The initial candidate terminology list is prepared by taking all arbitrary n-gram word sequences from the corpus. Then, a well-known statistical measure (the Dice coefficient) is employed in order to remove any multi-word terms with weak associations from the candidate term list. Thereafter, the log-likelihood comparison method is applied to rank the phrasal candidate term list. Then, using a phrase-based statistical machine translation model, we create a bilingual terminology with the extracted monolingual term lists. We integrate an external knowledge source—the Wikipedia cross-language link databases—into the terminology extraction (TE) model to assist two processes: (a) the ranking of the extracted terminology list, and (b) the selection of appropriate target terms for a source term. First, we report the performance of our monolingual TE model compared to a number of the state-of-the-art TE models on English-to-Turkish and English-to-Hindi data sets. Then, we evaluate our novel bilingual TE model on an English-to-Turkish data set, and report the automatic evaluation results. We also manually evaluate our novel TE model on English-to-Spanish and English-to-Hindi data sets, and observe excellent performance for all domains.     

基于预训练表示模型的英语词语简化方法

词语简化是将给定句子中的复杂词替换成意义相等的简单替代词,从而达到简化句子的目的.已有的词语简化方法只依靠复杂词本身而不考虑其上下文信息来生成候选替换词,这将不可避免地产生大量的虚假候选词.为此,提出了一种基于预语言训练表示模型的词语简化方法,利用预训练语言表示模进行候选替换词的生成和排序.基于预语言训练表示模型的词语简化方法在候选词生成过程中,不仅不需要任何语义词典和平行语料,而且能够充分考虑复杂词本身和上下文信息产生候选替代词.在候选替代词排序过程中,基于预语言训练表示模型的词语简化方法采用了5个高效的特征,除了常用的词频和词语之间相似度特征之外,还利用了预训练语言表示模的预测排名、基于基于预语言训练表示模型的上、下文产生概率和复述数据库PPDB三个新特征.通过3个基准数据集进行验证,基于预语言训练表示模型的词语简化方法取得了明显的进步,整体性能平均比最先进的方法准确率高出29.8%.     

Random one-dependence estimators

Many approaches attempt to improve naive Bayes and have been broadly divided into five main categories: (1) structure extension; (2) attribute weighting; (3) attribute selection; (4) instance weighting; (5) instance selection, also called local learning. In this paper, we work on the approach of structure extension and single out a random Bayes model by augmenting the structure of naive Bayes. We called it random one-dependence estimators, simply RODE. In RODE, each attribute has at most one parent from other attributes and this parent is randomly selected from log₂m (where m is the number of attributes) attributes with the maximal conditional mutual information. Our work conducts the randomness into Bayesian network classifiers. The experimental results on a large number of UCI data sets validate its effectiveness in terms of classification, class probability estimation, and ranking.     

CRF和词典相结合的蒙古文地名识别研究

蒙古语在命名实体识别方面开展过人名的识别,但在地名的识别方面还没有开展相应的研究。首次实现了基于条件随机场模型的蒙古文地名识别。首先从蒙古语黏着性特点分析入手,研究了蒙古语语料库中地名的存在形式以及各类地名的特点,针对蒙古语语料库中地名的特点,在词汇特征、指示词特征、特征词特征等特征基础上引入了词性特征。之后通过地名词典补召了未识别的地名。以内蒙古大学开发的100万词规模的标注语料库为训练数据,该模型的地名识别性能达到了94.68%的准确率、84.40%的召回率和89.24%的F值。