基于Wikipedia的短文本语义相关度计算方法

语义相关度计算是自然语言处理领域的研究热点。现有的以文本相似度计算代替文本相关度计算的方法存在不足之处。提出从语形相似性和组元相关性两个方面来综合度量短文本之间的语义相关性,并提出2个以Wikipedia作为外部知识库的短文本相关度计算算法:最大词语关联法和动态组块法。在一个网络短文本测试集上对算法进行测评。实验结果表明,该算法与典型相似度计算算法比较,在正确率方面提高了20%以上。     

Choosing Rhetorical Structures To Plan Instructional Texts

This paper discusses a fundamental problem in natural language generation: how to organize the content of a text in a coherent and natural way. In this research, we set out to determine the semantic content and the rhetorical structure of texts and to develop heuristics to perform this process automatically within a text generation framework. The study was performed on a specific language and textual genre: French instructional texts. From a corpus analysis of these texts, we determined nine senses typically communicated in instructional texts and seven rhetorical relations used to present these senses. From this analysis, we then developed a set of presentation heuristics that determine how the senses to be communicated should be organized rhetorically in order to create a coherent and natural text. The heuristics are based on five types of constraints: conceptual, semantic, rhetorical, pragmatic, and intentional constraints. To verify the heuristics, we developed the spin natural language generation system, which performs all steps of text generation but focuses on the determination of the content and the rhetorical structure of the text.     

一种宋词自动生成的遗传算法及其机器实现

主要针对宋词这种特殊的汉语诗歌体裁,开展了有关自动生成算法及其实现方法的探索性研究.研究工作主要根据宋词特点,设计了基于平仄的编码方式、基于句法和语义加权值的适应度函数、基于精英主义和轮盘赌算法的选择策略,采用部分映射和启发式交叉算子和启发式变异算子,从而构建了一种基于遗传算法的宋词生成计算模型并进行了系统实现.实验结果表明,所建立的计算模型及其软件系统,初步实现了机器自动生成宋词的目标,对于给定的主题词和词牌,基本上能够自动生成有一定欣赏价值的宋词.论文的工作也填补了我国在汉语诗歌自动生成研究方面的不足     

面向任务的基于深度学习的多轮对话系统与技术

自然语言是人类智慧的结晶,以自然语言的形式与计算机进行交互是人们长久以来的期待.随着自然语言处理技术的发展与深度学习方法的兴起,人机对话系统成为了新的研究热点.人机对话系统按照功能可以分为任务导向型对话系统、闲聊型对话系统、问答型对话系统.任务导向型对话系统是一种典型的人机对话系统,旨在帮助用户完成某些特定的任务,有着...     

Representing and applying knowledge for argumentation in a social context

The concept of argumentation in AI is based almost exclusively on the use of formal, abstract representations. Despite their appealing computational properties, these abstractions become increasingly divorced from their real world counterparts, and, crucially, lose the ability to express the rich gamut of natural argument forms required for creating effective text. In this paper, the demands that socially situated argumentation places on knowledge representation are explored, and the various problems with existing formalisations are discussed. Insights from argumentation theory and social psychology are then adduced as key contributions to a notion of social context which is both computationally tractable and suitably expressive for handling the complexities of argumentation found in natural language.     

天气预报文本生成系统中的天气图处理器

上海市气象局,上海２０００３０摘要：天气预报文本自动生成促进了天气预报的科学化、客观化、高效化。借助于天气图处理器,可以融入预报员的长期丰富的预报经验,使预报准确性得到提高。介绍了天气预报文本自动生成系统中的天气图处理器的设计和实现,并对相关数据接口作了介绍。     

Automatically producing tailored web materials for public administration

Public administration organizations commonly produce citizen-focused, informational materials describing public programs and the conditions under which citizens or citizen groups are eligible for these programs. The organizations write these materials for generic audiences because of the excessive human resource costs that would be required to produce personalized materials for everyone. Unfortunately, generic materials tend to be longer and harder to understand than materials tailored for particular citizens. Our work explores the feasibility and effectiveness of automatically producing tailored materials. We have developed an adaptive hypermedia application system that automatically produces tailored informational materials and have evaluated it in a series of studies. The studies demonstrate that: (1) subjects prefer tailored materials over generic materials, even if the tailoring requires answering a set of demographic questions first; (2) tailored materials are more effective at supporting subjects in their task of learning about public programs; and (3) the time required to specify the demographic information on which the tailoring is based does not significantly slow down the subjects in their information seeking task.     

Analysing and evaluating the task of automatic tweet generation: Knowledge to business

In this paper a study concerning the evaluation and analysis of natural language tweets is presented. Based on our experience in text summarisation, we carry out a deep analysis on user's perception through the evaluation of tweets manual and automatically generated from news. Specifically, we consider two key issues of a tweet: its informativeness and its interestingness. Therefore, we analyse: (1) do users equally perceive manual and automatic tweets?; (2) what linguistic features a good tweet may have to be interesting, as well as informative? The main challenge of this proposal is the analysis of tweets to help companies in their positioning and reputation on the Web. Our results show that: (1) automatically informative and interesting natural language tweets can be generated as a result of summarisation approaches; and (2) we can characterise good and bad tweets based on specific linguistic features not present in other types of tweets.     

Generating and evaluating evaluative arguments

Evaluative arguments are pervasive in natural human communication. In countless situations people attempt to advise or persuade their interlocutors that something is desirable (vs. undesirable) or right (vs. wrong). With the proliferation of on-line systems serving as personal advisors and assistants, there is a pressing need to develop general and testable computational models for generating and presenting evaluative arguments. Previous research on generating evaluative arguments has been characterized by two major limitations. First, researchers have tended to focus only on specific aspects of the generation process. Second, the proposed approaches were not empirically tested. The research presented in this paper addresses both limitations. We have designed and implemented a complete computational model for generating evaluative arguments. For content selection and organization, we devised an argumentation strategy based on guidelines from argumentation theory. For expressing the content in natural language, we extended and integrated previous work in computational linguistics on generating evaluative arguments. The key knowledge source for both tasks is a quantitative model of user preferences. To empirically test critical aspects of our generation model, we have devised and implemented an evaluation framework in which the effectiveness of evaluative arguments can be measured with real users. Within the framework, we have performed an experiment to test two basic hypotheses on which the design of the computational model is based; namely, that our proposal for tailoring an evaluative argument to the addressee's preferences increases its effectiveness, and that differences in conciseness significantly influence argument effectiveness. The second hypothesis was confirmed in the experiment. In contrast, the first hypothesis was only marginally confirmed. However, independent testing by other researchers has recently provided further support for this hypothesis.     

用创新计算动力学研究神经网络的组合创新

创新计算动力学研究创新的基本规律,不仅为创新的机械化实现奠定基础,也为人类的创新活动提供规则化支持。文中利用创新计算动力学的基本定律研究神经网络技术的组合创新活动,归纳了组合创新的重要前提,同时证明了神经网络的组合创新过程是符合创新计算的基本定律之联想与组合定律。最后,提出了相似组合、对立组合和信息域关联组合三种具体的组合创新模式。由于创新活动的广泛性和创新计算动力学的一般性,它们对于神经网络的未来发展以及其它理论或技术的创新都具有一定的启发意义。     

现当代文学作品的作者身份识别研究

主要利用了SVM统计机器学习模型对中国现当代文学八位代表人物的作品进行了作者身份识别研究,在识别过程中选取了以词汇为基础的多种统计量作为识别特征,并且采取了基于低密度多特征的训练方法,在跨文体的作品的作者身份识别中取得了非常优异的识别性能。     

Feminism and procedural content generation: toward a collaborative politics of computational creativity

ABSTRACT

Games now inhabit a space where creativity is no longer centered around human authorship. The use of procedural content generation has been embraced by industry, academics and fans as a means for reducing labor cost, providing additional replayable content for players, investigating computational creativity in a complex and multifaceted domain and enabling new kinds of playable experiences. This incorporation of computational creative labor confuses authorship, labor politics and responsibility for rhetoric embedded in the procedures by complicating the way in which the computer is portrayed to users, researchers and other developers. We can apply feminist methodologies attentive to questions of difference and power in systemic structures in order to better understand each of these questions in turn. This article presents an analysis of the post-anthropocentric phenomenon of computer creativity within games, via a feminist analysis of procedural content generating algorithms, its role in game design and its public portrayal.     

基于NLTK的中文文本内容抽取方法

NLTK是Python中用于自然语言处理的第三方模块,但处理中文文本具有一定局限性.利用NLTK对中文文本中的信息内容进行抽取与挖掘,采用同语境词提取、双连词搭配提取、概率统计以及篇章分析等方法,得到一个适用于中文文本的NLTK文本内容抽取框架,及其具体的实现方法.经实证分析表明,在抽取结果中可以找到反映文本特点的语料内容,得到抽取结果与文本主题具有较强相关性的结论.     

The German Vorfeld and Local Coherence

We present a method for improving local coherence in German with a positive effect on automatically as well as human-generated texts. We demonstrate that local coherence crucially depends on which constituent occupies the initial position in a sentence. To support our hypothesis, we provide statistical evidence based on a corpus investigation and on results of an experiment with human judges. Additionally, we implement our findings in a generation module for determining the Vorfeld constituent automatically.     

All the Truth About NEvAr

The use of Evolutionary Computation approaches to generate images has reached a great popularity. This led to the emergence of a new art form—Evolutionary Art—and to the proliferation of Evolutionary Art Tools. In this paper, we present an Evolutionary Art Tool, NEvAr, the experimental results achieved, and the work methodology used to generate images. In NEvAr, useful individuals are stored in a database in order to allow their reuse. This database is playing an increasingly important role in the creation of new images, which led us to the development of automatic seeding procedures, also described. The automation of fitness assignment is one of our present research interests. We will, therefore, describe some preliminary results achieved with our current approach to automatic evaluation.