Xiaochi Wei

Embedding Factorization Models for Jointly Recommending Items and User Generated Lists

Existing recommender algorithms mainly focused on recommending individual items by utilizing user-item interactions. However, little attention has been paid to recommend user generated lists (e.g., playlists and booklists). On one hand, user generated lists contain rich signal about item co-occurrence, as items within a list are usually gathered based on a specific theme. On the other hand, a users preference over a list also indicate her preference over items within the list. We believe that 1) if the rich relevance signal within user generated lists can be properly leveraged, an enhanced recommendation for individual items can be provided, and 2) if user-item and user-list interactions are properly utilized, and the relationship between a list and its contained items is discovered, the performance of user-item and user-list recommendations can be mutually reinforced. Towards this end, we devise embedding factorization models, which extend traditional factorization method by incorporating item-item (item-item-list) co-occurrence with embedding-based algorithms. Specifically, we employ factorization model to capture users preferences over items and lists, and utilize embedding-based models to discover the co-occurrence information among items and lists. The gap between the two types of models is bridged by sharing items latent factors. Remarkably, our proposed framework is capable of solving the new-item cold-start problem, where items have never been consumed by users but exist in user generated lists. Overall performance comparisons and micro-level analyses demonstrate the promising performance of our proposed approaches.

Cross-Platform App Recommendation by Jointly Modeling Ratings and Texts

Over the last decade, the renaissance of Web technologies has transformed the online world into an application (App) driven society. While the abundant Apps have provided great convenience, their sheer number also leads to severe information overload, making it difficult for users to identify desired Apps. To alleviate the information overloading issue, recommender systems have been proposed and deployed for the App domain. However, existing work on App recommendation has largely focused on one single platform (e.g., smartphones), while it ignores the rich data of other relevant platforms (e.g., tablets and computers). In this article, we tackle the problem of cross-platform App recommendation, aiming at leveraging users’ and Apps’ data on multiple platforms to enhance the recommendation accuracy. The key advantage of our proposal is that by leveraging multiplatform data, the perpetual issues in personalized recommender systems—data sparsity and cold-start—can be largely alleviated. To this end, we propose a hybrid solution, STAR (short for “croSs-plaTform App Recommendation”) that integrates both numerical ratings and textual content from multiple platforms. In STAR, we innovatively represent an App as an aggregation of common features across platforms (e.g., App’s functionalities) and specific features that are dependent on the resided platform. In light of this, STAR can discriminate a user’s preference on an App by separating the user’s interest into two parts (either in the App’s inherent factors or platform-aware features). To evaluate our proposal, we construct two real-world datasets that are crawled from the App stores of iPhone, iPad, and iMac. Through extensive experiments, we show that our STAR method consistently outperforms highly competitive recommendation methods, justifying the rationality of our cross-platform App recommendation proposal and the effectiveness of our solution.

Tri-Rank: An Authority Ranking Framework in Heterogeneous Academic Networks by Mutual Reinforce

Recently, authority ranking has received increasing interests in both academia and industry, and it is applicable to many problems such as discovering influential nodes and building recommendation systems. Various graph-based ranking approaches like PageRank have been used to rank authors and papers separately in homogeneous networks. In this paper, we take venue information into consideration and propose a novel graph-based ranking framework, Tri-Rank, to co-rank authors, papers and venues simultaneously in heterogeneous networks. This approach is a flexible framework and it ranks authors, papers and venues iteratively in a mutually reinforcing way to achieve a more synthetic, fair ranking result. We conduct extensive experiments using the data collected from ACM Digital Library. The experimental results show that Tri-Rank is more effective and efficient than the state-of-the-art baselines including PageRank, HITS and Co-Rank in ranking authors. The papers and venues ranked by Tri-Rank also demonstrate that Tri-Rank is rational.

Version-sensitive mobile App recommendation

Being part and parcel of the daily life for billions of people all over the globe, the domain of mobile Applications (Apps) is the fastest growing sector of mobile market today. Users, however, are frequently overwhelmed by the vast number of released Apps and frequently updated versions. Towards this end, we propose a novel version-sensitive mobile App recommendation framework. It is able to recommend appropriate Apps to right users by jointly exploring the version progression and dual-heterogeneous data. It is helpful for alleviating the data sparsity problem caused by version division. As a byproduct, it can be utilized to solve the in-matrix and out-of-matrix cold-start problems. Considering the progression of versions within the same categories, the performance of our proposed framework can be further improved. It is worth emphasizing that our proposed version progression modeling can work as a plug-in component to be embedded into most of the existing latent factor-based algorithms. To support the online learning, we design an incremental update strategy for the framework to adapt the dynamic data in real-time. Extensive experiments on a real-world dataset have demonstrated the promising performance of our proposed approach with both offline and online protocols. Relevant data, code, and parameter settings are available at http://apprec.wixsite.com/version.

A novel unsupervised method for new word extraction

New words could benefit many NLP tasks such as sentence chunking and sentiment analysis. However, automatic new word extraction is a challenging task because new words usually have no fixed language pattern, and even appear with the new meanings of existing words. To tackle these problems, this paper proposes a novel method to extract new words. It not only considers domain specificity, but also combines with multiple statistical language knowledge. First, we perform a filtering algorithm to obtain a candidate list of new words. Then, we employ the statistical language knowledge to extract the top ranked new words. Experimental results show that our proposed method is able to extract a large number of new words both in Chinese and English corpus, and notably outperforms the state-of-the-art methods. Moreover, we also demonstrate our method increases the accuracy of Chinese word segmentation by 10% on corpus containing new words.创新点1.本文提出了一个基于领域特殊性和统计语言知识的新词抽取方法。首先, 采用基于领域特殊性的垃圾串过滤方法过滤垃圾串, 得到候选新词列表; 然后基于统计语言知识(词频、凝聚度和自由度)对新词进行抽取。实验验证了该方法的有效性、语言独立性和领域无关性。2.该方法能够有效提升中文分词系统的分词效果。

When Factorization Meets Heterogeneous Latent Topics: An Interpretable Cross-Site Recommendation Framework

Data sparsity is a well-known challenge in recommender systems. Previous studies alleviate this problem by incorporating the information within the corresponding social media site. In this paper, we solve this challenge by exploring cross-site information. Specifically, we examine: 1) how to effectively and efficiently utilize cross-site ratings and content features to improve recommendation performance and 2) how to make the recommendation interpretable by utilizing content features. We propose a joint model of matrix factorization and latent topic analysis. Heterogeneous content features are modeled by multiple kinds of latent topics. In addition, the combination of matrix factorization and latent topics makes the recommendation result interpretable. Therefore, the above two issues are simultaneously solved. Through a real-world dataset, where user behaviors in three social media sites are collected, we demonstrate that the proposed model is effective in improving recommendation performance and interpreting the rationale of ratings.

FCL: A New Network Words Extraction Approach Based on Statistical Language Knowledge

New network words could benefit many NLP tasks such as Chinese word segmentation and sentiment analysis. However, automatic new network words extraction is a challenging task because new network words usually have no fixed language pattern, and even appear with the new meanings of existing words. To tackle these problems, this paper proposes a novel approach of FCL to extract new network words. It not only considers domain specificity, but also combines with multiple statistical language knowledge. First, we perform a filtering algorithm to obtain a list of candidate new words. Then, we employ the statistical language knowledge to extract the top ranked new network words. Experimental results show that our proposed approach is able to extract a large number of new network words and notably outperforms the state-of-the-art methods. Moreover, we also demonstrate our approach increases the accuracy of word segmentation by 10 % on corpus containing new words.

Quality Matters: Assessing cQA Pair Quality via Transductive Multi-View Learning

Community-based question answering (cQA) sites have become important knowledge sharing platforms, as massive cQA pairs are archived, but the uneven quality of cQA pairs leaves information seekers unsatisfied. Various efforts have been dedicated to predicting the quality of cQA contents. Most of them concatenate different features into single vectors and then feed them into regression models. In fact, the quality of cQA pairs is influenced by different views, and the agreement among them is essential for quality assessment. Besides, the lacking of labeled data significantly hinders the quality prediction performance. Toward this end, we present a transductive multi-view learning model. It is designed to find a latent common space by unifying and preserving information from various views, including question, answer, QA relevance, asker, and answerer. Additionally, rich information in the unlabeled test cQA pairs are utilized via transductive learning to enhance the representation ability of the common space. Extensive experiments on real-world datasets have wellvalidated the proposed model.

I Know What You Want to Express: Sentence Element Inference by Incorporating External Knowledge Base

Sentence auto-completion is an important feature that saves users many keystrokes in typing the entire sentence by providing suggestions as they type. Despite its value, the existing sentence auto-completion methods, such as query completion models, can hardly be applied to solving the object completion problem in sentences with the form of (subject, verb, object), due to the complex natural language description and the data deficiency problem. Towards this goal, we treat an SVO sentence as a three-element triple (subject, sentence pattern, object), and cast the sentence object completion problem as an element inference problem. These elements in all triples are encoded into a unified low-dimensional embedding space by our proposed TRANSFER model, which leverages the external knowledge base to strengthen the representation learning performance. With such representations, we can provide reliable candidates for the desired missing element by a linear model. Extensive experiments on a real-world dataset have well-validated our model. Meanwhile, we have successfully applied our proposed model to factoid question answering systems for answer candidate selection, which further demonstrates the applicability of the TRANSFER model.