A novel probabilistic retrieval model is presented. It forms a basis to interpret the TF-IDF term weights as making relevance decisions. simulates local decision-making for every location of document, and combines all these “local” decisions “document-wide” decision document. The significance interpreting in this way potential to: (1) establish unifying perspective about information decision-making; (2) develop advanced TF-IDF-related future elaborate models. Our simplified basic ranking...

Automatically identifying rumors from online social media especially microblogging websites is an important research issue. Most of existing work for rumor detection focuses on modeling features related to microblog contents, users and propagation patterns, but ignore the importance variation these context during message over time. In this study, we propose a novel approach capture temporal characteristics based time series rumor's lifecycle, which technique applied incorporate various...

This paper outlines the requirements and components for a proposed Document Analysis System, which assists user in encoding printed documents computer processing. Several critical functions have been investigated technical approaches are discussed. The first is segmentation classification of digitized into regions text images. A nonlinear, run-length smoothing algorithm has used this purpose. By using regular features lines, linear adaptive scheme discriminates from others. second technique...

Automatic rumor detection is technically very challenging. In this work, we try to learn discriminative features from tweets content by following their non-sequential propagation structure and generate more powerful representations for identifying different type of rumors. We propose two recursive neural models based on a bottom-up top-down tree-structured networks representation learning classification, which naturally conform the layout tweets. Results public Twitter datasets demonstrate...

How fake news goes viral via social media? does its propagation pattern differ from real stories? In this paper, we attempt to address the problem of identifying rumors, i.e., information, out microblog posts based on their structure. We firstly model diffusion with trees, which provide valuable clues how an original message is transmitted and developed over time. then propose a kernel-based method called Propagation Tree Kernel, captures high-order patterns differentiating different types...

This paper explores the possibility of using instrumental variable method to estimate parameters linear time-invariant discrete-time systems. The existence optimal estimates is established, methods for their approximate computation are given, and an on-line identification scheme based on recursive proposed. Experimental results included.

Rumors can cause devastating consequences to individual and/or society. Analysis shows that widespread of rumors typically results from deliberately promoted information campaigns which aim shape collective opinions on the concerned news events. In this paper, we attempt fight such chaos with itself make automatic rumor detection more robust and effective. Our idea is inspired by adversarial learning method originated Generative Adversarial Networks (GAN). We propose a GAN-style approach,...

In recent years, an unhealthy phenomenon characterized as the massive spread of fake news or unverified information (i.e., rumors) has become increasingly a daunting issue in human society. The rumors commonly originate from social media outlets, primarily microblogging platforms, being viral afterwards by wild, willful propagation via large number participants. It is observed that rumorous posts often trigger versatile, mostly controversial stances among participating users. Thus,...

Zhongyu Wei, Qianlong Liu, Baolin Peng, Huaixiao Tou, Ting Chen, Xuanjing Huang, Kam-fai Wong, Xiangying Dai. Proceedings of the 56th Annual Meeting Association for Computational Linguistics (Volume 2: Short Papers). 2018.

Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users. One common alternative to use user simulator. However, simulator usually lacks the language complexity of human interlocutors and biases in its design may tend degrade agent. To address these issues, we present Deep Dyna-Q, which our knowledge first deep RL framework that integrates planning for policy learning. We incorporate into model environment,...

Quotations are crucial for successful explanations and persuasions in interpersonal communications. However, finding what to quote a conversation is challenging humans. This work studies automatic quotation recommendation online conversations. Unlike the previous works that only consider semantic-level modeling, we adopt topic-level representation facilitate recommendation. A hierarchical architecture based on pretrained language model adopted representation, neural topic employed learn...

It is difficult to identify sentence importance from a single point of view.In this paper, we propose learning-based approach combine various features.They are categorized as surface, content, relevance and event features.Surface features related extrinsic aspects sentence.Content measure based on contentconveying words.Event represent sentences by events they contained.Relevance evaluate its relatedness with other sentences.Experiments show that the combined improved summarization...

The majority of NLG evaluation relies on automatic metrics, such as BLEU . In this paper, we motivate the need for novel, system- and data-independent methods: We investigate a wide range including state-of-the-art word-based novel grammar-based ones, demonstrate that they only weakly reflect human judgements system outputs generated by data-driven, end-to-end NLG. also show metric performance is data- system-specific. Nevertheless, our results suggest metrics perform reliably at...

Claim verification is generally a task of verifying the veracity given claim, which critical to many downstream applications. It cumbersome and inefficient for human fact-checkers find consistent pieces evidence, from solid verdict could be inferred against claim. In this paper, we propose novel end-to-end hierarchical attention network focusing on learning represent coherent evidence as well their semantic relatedness with Our model consists three main components: 1) A coherence-based layer...

Component-based software development approach is based on the idea to develop systems by selecting appropriate off-the-shelf components and then assemble them with a well-defined architecture. Because new paradigm very different from traditional approach, quality assurance (QA) for component-based topic in engineering community. In this paper, we survey current technologies, describe their advantages disadvantages, discuss features they inherit. We also address QA issues software. As major...

Globalization has triggered a rapid increase in cross-border mergers and acquisitions (M&As). However, research shows that only 17 percent of M&As create shareholder value. One the main reasons for this poor track record is top management's lack attention to nonfinancial aspects (e.g., sociocultural aspects) M&As. With growth Web 2.0 applications, online environmental scanning provides executives with unprecedented opportunities tap into collective web intelligence develop better insights...

We propose Neural Reasoner, a framework for neural network-based reasoning over natural language sentences. Given question, Reasoner can infer multiple supporting facts and find an answer to the question in specific forms. has 1) interaction-pooling mechanism, allowing it examine facts, 2) deep architecture, model complicated logical relations tasks. Assuming no particular structure exists is able accommodate different types of forms expressions. Despite complexity, still be trained...

Memory networks have shown expressive performance on aspect based sentiment analysis. However, ordinary memory only capture word-level information and lack the capacity for modeling complicated expressions which consist of multiple words. Targeting this problem, we propose a novel convolutional network incorporates an attention mechanism. This model sequentially computes weights units corresponding to multi-words. may both words multi-words in sentences aspect-based Experimental results show...

This paper presents a new method - adversarial advantage actor-critic (Adversarial A2C), which significantly improves the efficiency of dialogue policy learning in task-completion systems. Inspired by generative networks (GAN), we train discriminator to differentiate responses/actions generated agents from experts. Then, incorporate as another critic into (A2C) framework, encourage agent explore state-action within regions where takes actions similar those Experimental results movie-ticket...

Rumor spread in social media severely jeopardizes the credibility of online content. Thus, automatic debunking rumors is great importance to keep a healthy environment. While facing dubious claim, people often dispute its truthfulness sporadically their posts containing various cues, which can form useful evidence with long-distance dependencies. In this work, we propose learn discriminative features from microblog by following non-sequential propagation structure and generate more powerful...

Abstract Dialogue policy learning (DPL) is a key component in task-oriented dialogue (TOD) system. Its goal to decide the next action of system, given state at each turn based on learned policy. Reinforcement (RL) widely used optimize this In process, user regarded as environment and system agent. paper, we present an overview recent advances challenges from perspective RL. More specifically, identify problems summarize corresponding solutions for RL-based learning. addition, provide...