Creating knowledge bases based on the crowd-sourced wikis, like Wikipedia, has attracted significant research interest in the field of intelligent Web. However, the derived taxonomies usually contain many mistakenly imported taxonomic relations due to the difference between the user-generated subsumption relations and the semantic taxonomic relations. Current approaches to solving the problem still suffer the following issues: (i) the heuristic-based methods strongly rely on specific language dependent rules. (ii) the corpus-based methods depend on a large-scale high-quality corpus, which is often unavailable. In this paper, we formulate the cross-lingual taxonomy derivation problem as the problem of cross-lingual taxonomic relation prediction. We investigate different linguistic heuristics and language independent features, and propose a cross-lingual knowledge validation based dynamic adaptive boosting model to iteratively reinforce the performance of taxonomic relation prediction. The proposed approach successfully overcome the above issues, and experiments show that our approach significantly outperforms the designed state-of-the-art comparison methods.

Sentiment analysis from large-scale networked data attracts increasing attention in recent years. Most previous works on sentiment prediction mainly focus on text or image data. However, voice is the most natural and direct way to express people's sentiments in real-time. With the rapid development of smart phone voice dialogue applications (e.g., Siri and Sogou Voice Assistant), the large-scale networked voice data can help us better quantitatively understand the sentimental world we live in. In this paper, we study the problem of sentiment prediction from large-scale networked voice data. In particular, we first investigate the data observations and underlying sentiment patterns in human-mobile voice communication. Then we propose a deep sparse neural network (DSNN) model to incorporate acoustic features, content information and geo-information to automatically predict sentiments. The effectiveness of the proposed model is verified by the experiments on a real dataset from Sogou Voice Assistant application.

Click models are developed to interpret clicks by making assumptions on how users browse the search result page. Most existing click models implicitly assume that all users are homogeneous and act in the same way when browsing the search results. However, a number of researches have shown that users have diverse behavioral patterns, which is also observed in this paper by eye-tracking experiments and click-through log analysis. As a uniform click model for all users can hardly capture the diverse click behavior, in this paper we incorporate user preferences into both a variety of existing click models and a novel click model. The experimental results on a large-scale click-through data set show consistent and significant performance improvement of the click models with user preferences integrated.

In modern search engines, an increasing number of search result pages (SERPs) are federated from multiple specialized search engines (called verticals, such as Image or Video). As an effective approach to interpret users' click-through behavior as feedback information, most click models were designed to reduce the position bias and improve ranking performance of ordinary search results, which have homogeneous appearances. However, when vertical results are combined with ordinary ones, significant differences in presentation may lead to user behavior biases and thus failure of state-of-the-art click models. With the help of a popular commercial search engine in China, we collected a large scale log data set which contains behavior information on both vertical and ordinary results. We also performed eye-tracking analysis to study user's real-world examining behavior. According these analysis, we found that different result appearances may cause different behavior biases both for vertical results (local effect) and for the whole result lists (global effect). These biases include: examine bias for vertical results (especially those with multimedia components), trust bias for result lists with vertical results, and a higher probability of result revisitation for vertical results. Based on these findings, a novel click model considering these biases besides position bias was constructed to describe interaction with SERPs containing verticals. Experimental results show that the new Vertical-aware Click Model (VCM) is better at interpreting user click behavior on federated searches in terms of both log-likelihood and perplexity than existing models.

In this paper, we utilize tags in Twitter (the hashtags) as an indicator of events. We first study the properties of hashtags for event detection. Based on several observations, we proposed three attributes of hashtags, including (1) instability for temporal analysis, (2) Twitter meme possibility to distinguish social events from virtual topics or memes, and (3) authorship entropy for mining the most contributed authors. Based on these attributes, breaking events are discovered with hashtags, which cover a wide range of social events among different languages in the real world.

Combating Web spam is one of the greatest challenges for Web search engines. State-of-the-art anti-spam techniques focus mainly on detecting varieties of spam strategies, such as content spamming and link-based spamming. Although these anti-spam approaches have had much success, they encounter problems when fighting against a continuous barrage of new types of spamming techniques. We attempt to solve the problem from a new perspective, by noticing that queries that are more likely to lead to spam pages/sites have the following characteristics: 1) they are popular or reflect heavy demands for search engine users and 2) there are usually few key resources or authoritative results for them. From these observations, we propose a novel method that is based on click-through data analysis by propagating the spamicity score iteratively between queries and URLs from a few seed pages/sites. Once we obtain the seed pages/sites, we use the link structure of the click-through bipartite graph to discover other pages/sites that are likely to be spam. Experiments show that our algorithm is both efficient and effective in detecting Web spam. Moreover, combining our method with some popular anti-spam techniques such as TrustRank achieves improvement compared with each technique taken individually.

New Event Detection (NED) aims at detecting from one or multiple streams of news stories that which one is reported on a new event (i.e. not reported previously). With the overwhelming volume of news available today, there is an increasing need for a NED system which is able to detect new events more efficiently and accurately. In this paper we propose a new NED model to speed up the NED task by using news indexing-tree dynamically. Moreover, based on the observation that terms of different types have different effects for NED task, two term reweighting approaches are proposed to improve NED accuracy. In the first approach, we propose to adjust term weights dynamically based on previous story clusters and in the second approach, we propose to employ statistics on training data to learn the named entity reweighting model for each class of stories. Experimental results on two Linguistic Data Consortium (LDC) datasets TDT2 and TDT3 show that the proposed model can improve both efficiency and accuracy of NED task significantly, compared to the baseline system and other existing systems.

Addressed in this paper is the issue of semantic relationship extraction from semi-structured documents. Many research efforts have been made so far on the semantic information extraction. However, much of the previous work focuses on detecting `isolated' semantic information by making use of linguistic analysis or linkage information in web pages and limited research has been done on extracting semantic relationship from the semi-structured documents. In this paper, we propose a method for semantic relationship extraction by using the logical information in the semi-structured document (semi-structured document usually has various types of structure information, e.g. a semi-structured document may be hierarchical laid out). To the best of our knowledge, extracting semantic relationships by using logical information has not been investigated previously. A probabilistic approach has been proposed in the paper. Features used in the probabilistic model have been defined.