Exploring the Interactions of Storylines from Informative News Events

Today＇s news readers can be easily overwhelmed by the numerous news articles online. To cope with information overload, online news media publishes timelines for continuously developing news topics. However, the timeline summary does not show the relationship of storylines, and is not intuitive for readers to comprehend the development of a complex news topic. In this paper, we study a novel problem of exploring the interactions of storylines in a news topic. An interaction of two storylines is signified by informative news events that play a key role in both storylines. Storyline interactions can indicate key phases of a news topic, and reveal the latent connections among various aspects of the story. We address the coherence between news articles which is not considered in traditional similarity-based methods, and discover salient storyline interactions to form a clear, global picture of the news topic. User preference can be naturally integrated into our method to generate query-specific results. Comprehensive experiments on ten news topics show the effectiveness of our method over alternative approaches.     

对话管理中基于槽特征有限状态自动机的方法研究

对话系统的研究已经成为人机交互技术发展的新热点。而对话管理则是其中最重要的组成部分．该文在当前对话管理的各种实现方法的基础上，提出了一种基于槽特征的自动机设计方法，其中应用了状态压缩和状态集、动作集的子空间划分。并着重以确认过程为例，阐述了确认策略控制函数及其对对话过程的影响．文中还提出了一种树形的意图分层结构，并将这种分层结构应用于主题检测与主题切换，成功解决了多主题对话系统的主题切换问题．最后，实验表明该文提出的设计方案在策略控制、主题检测与主题切换等方面具有较好性能，同时也具有一定扩展性．     

Mining microblog user interests based on TextRank with TF-IDF factor

It is of great value and significance to model the interests of microblog user in terms of business and sociology. This paper presents a framework for mining and analyzing personal interests from microblog text with a new algorithm which integrates term frequency-inverse document frequency (TF-IDF) with TextRank. Firstly, we build a three-tier category system of user interest based on Wikipedia. In order to obtain the keywords of interest, we preprocess the posts, comments and reposts in different categories to select the keywords which appear both in the category system and microblogs. We then assign weight to each category and calculate the weight of keyword to get TF-IDF factors. Finally we score the ranking of each keyword by the TextRank algorithm with TF-IDF factors. Experiments on real Sina microblog data demonstrate that the precision of our approach significantly outperforms other existing methods.     

基于知识图谱的保险领域对话系统构建

在当前人工智能技术发展的热潮中,对话系统已经越来越实用化。与一般的闲聊对话系统不同,特定领域的对话系统是基于知识,带有上下文推理的实用性对话系统。保险领域是典型的特定领域,介绍了一种保险相关领域对话系统的基本构建方法 ,可以帮助用户快速、实用地在某特定领域和场景下构建对话系统,且具有一定的推广性和拓展性。     

Guided Structure-Aware Review Summarization

Although the goal of traditional text summarization is to generate summaries with diverse information,most of those applications have no explicit definition of the information structure.Thus,it is difficult to generate truly structureaware summaries because the information structure to guide summarization is unclear.In this paper,we present a novel framework to generate guided summaries for product reviews.The guided summary has an explicitly defined structure which comes from the important aspects of products.The proposed framework attempts to maximize expected aspect satisfaction during summary generation.The importance of an aspect to a generated summary is modeled using Labeled Latent Dirichlet Allocation.Empirical experimental results on consumer reviews of cars show the effectiveness of our method.     

A Unified Active Learning Framework for Biomedical Relation Extraction

Supervised machine learning methods have been employed with great success in the task of biomedical relation extraction.However,existing methods are not practical enough,since manual construction of large training data is very expensive.Therefore,active learning is urgently needed for designing practical relation extraction methods with little human effort.In this paper,we describe a unified active learning framework.Particularly,our framework systematically addresses some practical issues during active learning process,including a strategy for selecting informative data,a data diversity selection algorithm,an active feature acquisition method,and an informative feature selection algorithm,in order to meet the challenges due to the immense amount of complex and diverse biomedical text.The framework is evaluated on proteinprotein interaction(PPI) extraction and is shown to achieve promising results with a significant reduction in editorial effort and labeling time.     

一种半监督的中文垃圾微博过滤方法

微博作为目前国内外最活跃的信息分享平台之一,其中却充斥着大量的垃圾内容。因此,如何从给定话题的微博数据中,过滤掉与话题不相关的垃圾微博、保留话题相关微博,成为迫切需要解决的问题。该文提出了一种半监督的中文微博过滤方法,基于朴素贝叶斯分类模型和最大期望算法,实现了利用少量标注数据的垃圾微博过滤算法,其优势是仅仅利用少量标注数据就可以获得较为理想的过滤性能。分别对十个话题140 000余条新浪微博数据进行过滤,该文提出的模型准确度和F值优于朴素贝叶斯和支持向量机模型。
     

Leveraging Large Data with Weak Supervision for Joint Feature and Opinion Word Extraction

Product feature and opinion word extraction is very important for fine granular sentiment analysis. In this paper, we leverage large-scale unlabeled data for joint extraction of feature and opinion wor...     

《现代自然语言生成》

《现代自然语言生成》系统地总结了以神经网络为代表的现代自然语言生成技术,并由浅入深地介绍了自然语言生成的基本思想、模型、算法和框架。为了让读者更全面的理解自然语言生成技术,本书从基础模型、优化方法、生成方式、生成机制等方向对已有技术进行了归纳,同时也辅助讲解了常见的生成任务和评价方法。     

ChatGPT：潜力、前景和局限

<正>1绪论 最近,OpenA I发布了对话生成预训练模型Transformer(Chat Generative Pre-trained Transformer,ChatGPT)(Schulmanetal.,2022)(https://chat.openai.com),其展现的能力令人印象深刻,吸引了工业界和学术界的广泛关注。这是首次在大型语言模型（large language model, LLM）内很好地解决如此多样的开放任务。为更好地理解ChatGPT,这里我们简要介绍其历史,讨论其优点和不足,指出几个潜在应用,最后分析它对可信赖人工智能、会话搜索引擎和通用人工智能（artificial general intelligence, AGI）发展的影响。