As one of the most popular Social Networking Services (SNS) in China, Weibo is generating massive contents, relations and users? behavior data. Many challenges exist in how to analyze Weibo data. Most works focus on Weibo clustering and topic classification based on analyzing the text contents only. However, the traditional approaches do not work well because most messages on Weibo are very short Chinese sentences. This paper aims to propose a new approach to cluster the Weibo data by analyzing the users? reposting behavior data besides the text contents. To verify the proposed approach, a data set of users? real behaviors from the actual SNS platform is utilized. Experimental results show that the proposed method works better than previous works which depend on the text analysis only.

Wikipedia's infoboxes contain rich structured information of various entities, which have been explored by the DBpedia project to generate large scale Linked Data sets. Among all the infobox attributes, those attributes having hyperlinks in its values identify semantic relations between entities, which are important for creating RDF links between DBpedia's instances. However, quite a few hyperlinks have not been anotated by editors in infoboxes, which causes lots of relations between entities being missing in Wikipedia. In this paper, we propose an approach for automatically discovering the missing entity links in Wikipedia's infoboxes, so that the missing semantic relations between entities can be established. Our approach first identifies entity mentions in the given infoboxes, and then computes several features to estimate the possibilities that a given attribute value might link to a candidate entity. A learning model is used to obtain the weights of different features, and predict the destination entity for each attribute value. We evaluated our approach on the English Wikipedia data, the experimental results show that our approach can effectively find the missing relations between entities, and it significantly outperforms the baseline methods in terms of both precision and recall.

As one of the most common language phenomena in bilingual settings, code-switching has been studied widely to explore its nature and features. In the current study, the author set out to explore the effect of syntactic alignment on Chinese-English bilinguals' code-switched sentence production using a picture-describing task with a structural priming paradigm. The structural priming paradigm has been frequently used to explore the mechanisms of sentence production. The effect of syntactic alignment was observed, indicating Chinese-English bilinguals were inclined to produce code-switched sentences with the same syntactic structure between Chinese and English. The findings provide empirical evidence not only supporting structural priming during bilingual code-switched sentence production, but also extending the interactive alignment model (Pickering and Garrod, 2004) to interpret code-switching during bilingual sentence production. Implications for code-switching and bilingual sentence processing are discussed.

This study investigates the production and comprehension of subject relative clause (SRC) and object relative clause (ORC) in English by Chinese EFL learners. Two experiments are reported. Using a sentence completion task to elicit the production of relative clauses (RCs), Experiment 1 examined the distributional patterns of SRC and ORC and showed that SRC was more frequently distributed than ORC. In addition, animacy and verb type had effects on the asymmetric distribution of SRC and ORC. Using a word-by-word moving-window self-paced reading paradigm, Experiment 2 further compared reading times (RTs) of SRC and ORC containing different animacy and verb type configurations. Reading difficulties in ORC were observed, and comprehension difficulties of certain configurations of animacy and verb type just mirrored their frequencies in the first experiment. Taken together, the processing asymmetry of SRC and ORC has been observed in both comprehension and production processes. Comprehension difficulties are believed to stem from the asymmetric distributions of sentence patterns involving different animacy and verb type configurations. These findings suggest that comprehension difficulties are correlated with the distributional patterns, which could provide strong support to the Production-Distribution-Comprehension account, the experience-based approach applicable in language acquisition.