Search

Item concept modeling is commonly achieved by leveraging textual information. However, many existing models do not leverage the inferential property of concepts to capture word meanings, which therefore ignores the relatedness between correlated concepts, a phenomenon which we term conceptual “correlation sparsity.” In this paper, we distinguish between word modeling and concept modeling and propose an item concept modeling framework centering around the item concept network (ICN). ICN models and further enriches item concepts by leveraging the inferential property of concepts and thus addresses the correlation sparsity issue. Specifically, there are two stages in the proposed framework: ICN construction and embedding learning. In the first stage, we propose a generalized network construction method to build ICN, a structured network which infers expanded concepts for items via matrix operations. The second stage leverages neighborhood proximity to learn item and concept embeddings. With the proposed ICN, the resulting embedding facilitates both homogeneous and heterogeneous tasks, such as item-to-item and concept-to-item retrieval, and delivers related results which are more diverse than traditional keyword-matching-based approaches. As our experiments on two real-world datasets show, the framework encodes useful conceptual information and thus outperforms traditional methods in various item classification and retrieval tasks.

Mood and emotion play an important role when it comes to choosing musical tracks to listen to. In the field of music information retrieval and recommendation, emotion is considered contextual information that is hard to capture, albeit highly influential. In this study, we analyze the connection between users‘ emotional states and their musical choices. Particularly, we perform a large-scale study based on two data sets containing 560,000 and 90,000 #nowplaying tweets, respectively. We extract affective contextual information from hashtags contained in these tweets by applying an unsupervised sentiment dictionary approach. Subsequently, we utilize a state-of-the-art network embedding method to learn latent feature representations of users, tracks and hashtags. Based on both the affective information and the latent features, a set of eight ranking methods is proposed. We find that relying on a ranking approach that incorporates the latent representations of users and tracks allows for capturing a user's general musical preferences well (regardless of used hashtags or affective information). However, for capturing context-specific preferences (a more complex and personal ranking task), we find that ranking strategies that rely on affective information and that leverage hashtags as context information outperform the other ranking strategies.

Considering the temporal order of user-item interactions for recommendation forms a novel class of recommendation algorithms in recent years, among which sequential recommendation models are the most popular approaches. Although, theoretically, such fine-grained modeling should be beneficial to the recommendation performance, these sequential models in practice greatly suffer from the issue of data sparsity as there are a huge number of combinations for item sequences. To address the issue, we propose LSTPR, a graph-based matrix factorization model that incorporates both high-order graph information and long short-term user preferences into the modeling process. LSTPR explicitly distinguishes long-term and short-term user preferences and enriches the sparse interactions via random surfing on the user-item graph. Experiments on three recommendation datasets with temporal user-item information demonstrate that the proposed LSTPR model achieves significantly better performance than the seven baseline methods.

Customer reviews on platforms such as TripAdvisor and Amazon provide rich information about the ways that people convey sentiment on certain domains. Given these kinds of user reviews, this paper proposes UGSD, a representation learning framework for constructing domain-specific sentiment dictionaries from online customer reviews, in which we leverage the relationship between user-generated reviews and the ratings of the reviews to associate the reviewer sentiment with certain entities. The proposed framework has the following three main advantages. First, no additional annotations of words or external dictionaries are needed for the proposed framework; the only resources needed are the review texts and entity ratings. Second, the framework is applicable across a variety of user-generated content from different domains to construct domain-specific sentiment dictionaries. Finally, each word in the constructed dictionary is associated with a low-dimensional dense representation and a degree of relatedness to a certain rating, which enable us to obtain more fine-grained dictionaries and enhance the application scalability of the constructed dictionaries as the word representations can be adopted for various tasks or applications, such as entity ranking and dictionary expansion. The experimental results on three real-world datasets show that the framework is effective in constructing high-quality domain-specific sentiment dictionaries from customer reviews.

We propose an eXplainable Risk Ranking (XRR) model that uses multilevel encoders and attention mechanisms to analyze financial risks among companies. In specific, the proposed method utilizes the textual information in financial reports to rank the relative risks among companies and locate top high-risk companies; moreover, via attention mechanisms, XRR enables to highlight the critical words and sentences within financial reports that are most likely to influence financial risk and thus boasts better model explainability. Experimental results evaluated on 10-K financial reports show that XRR significantly outperforms several baselines, yielding up to 7.4% improvement in terms of ranking correlation metrics. Furthermore, in our experiments, the model explainability is evaluated by using finance-specific sentiment lexicons at word level and a newly-provided annotated reference list at the sentence level to examine the learned attention models.

Textual data is common and informative auxiliary information for recommender systems. Most prior art utilizes text for rating prediction, but rare work connects it to top-recommendation. Moreover, although advanced recommendation models capable of incorporating auxiliary information have been developed, none of these are specifically designed to model textual information, yielding a limited usage scenario for typical user-to-item recommendation. In this work, we present a framework of text-aware preference ranking (TPR) for top- recommendation, in which we comprehensively model the joint association of user-item interaction and relations between items and associated text. Using the TPR framework, we construct a joint likelihood function that explicitly describes two ranking structures: 1) item preference ranking (IPR) and 2) word relatedness ranking (WRR), where the former captures the item preference of each user and the latter captures the word relatedness of each item. As these two explicit structures are by nature mutually dependent, we propose TPR-OPT, a simple yet effective learning criterion that additionally includes implicit structures, such as relatedness between items and relatedness between words for each user for model optimization. Such a design not only successfully describes the joint association among users, words, and text comprehensively but also naturally yields powerful representations that are suitable for a range of recommendation tasks, including user-to-item, item-to-item, and user-to-word recommendation, as well as item-to-word reconstruction. In this paper, extensive experiments have been conducted on eight recommendation datasets, the results of which demonstrate that by including textual information from item descriptions, the proposed TPR model consistently outperforms state-of-the-art baselines on various recommendation tasks.

We propose the use of a word-level sentiment bidirectional LSTM in tandem with the self-attention mechanism for sentence-level sentiment prediction. In addition to the proposed model, we also present a finance report dataset for sentence-level financial risk detection. Experiments conducted on the proposed dataset together with two public review datasets attest the effectiveness of our model for sentence sentiment prediction.

While internalized “implicit knowledge” in pretrained transformers has led to fruitful progress in many natural language understanding tasks, how to most effectively elicit such knowledge remains an open question. Based on the text-to-text transfer transformer (T5) model, this work explores a template-based approach to extract implicit knowledge for commonsense reasoning on multiple-choice (MC) question answering tasks. Experiments on three representative MC datasets show the surprisingly good performance of our simple template, coupled with a logit normalization technique for disambiguation. Furthermore, we verify that our proposed template can be easily extended to other MC tasks with contexts such as supporting facts in open-book question answering settings. Starting from the MC task, this work initiates further research to find generic natural language templates that can effectively leverage stored knowledge in pretrained models.

Conversational search plays a vital role in conversational information seeking. As queries in information seeking dialogues are ambiguous for traditional ad-hoc information retrieval (IR) systems due to the coreference and omission resolution problems inherent in natural language dialogue, resolving these ambiguities is crucial. In this paper, we tackle conversational passage retrieval (ConvPR), an important component of conversational search, by addressing query ambiguities with query reformulation integrated into a multi-stage ad-hoc IR system. Specifically, we propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting. For the former, we expand conversational queries using important terms extracted from the conversational context with frequency-based signals. For the latter, we reformulate conversational queries into natural, standalone, human-understandable queries with a pretrained sequence-tosequence model. Detailed analyses of the two CQR methods are provided quantitatively and qualitatively, explaining their advantages, disadvantages, and distinct behaviors. Moreover, to leverage the strengths of both CQR methods, we propose combining their output with reciprocal rank fusion, yielding state-of-the-art retrieval effectiveness, 30% improvement in terms of NDCG@3 compared to the best submission of TREC CAsT 2019., Comment: 28 pages. Accepted to ACM Transactions on Information Systems, Special Issue on Conversational Search and Recommendation. The first two authors contributed equally. Code: https://github.com/castorini/chatty-goose

In this paper, we present a simple and robust watermarking scheme for color images. The scheme is based on the square-root-modulus technique employed in the integer wavelet domain, which allows a large number of data bits to be embedded in a host image. Simulations confirmed that marked images generated by the proposed scheme are tolerant to various attacks such as blurring, brightness, contrast, cropping, edge sharpening, inversion, JPEG/JPEG2000 compressions, noise-additions, and truncation. Additionally, the payload of the proposed method is significantly larger than that of existing watermarking techniques and the resulting perceived quality is not bad. Because the code is quite simple, it is suitable for the proposed method implemented in the mobile equipments or smart devices.

We attempt in this paper to utilize soft information in financial reports to analyze financial risk among companies. Specifically, on the basis of the text information in financial reports, which is the so-called soft information, we apply analytical techniques to study relations between texts and financial risk. Furthermore, we conduct a study on financial sentiment analysis by using a finance-specific sentiment lexicon to examine the relations between financial sentiment words and financial risk. A large collection of financial reports published annually by publicly-traded companies is employed to conduct our experiments; moreover, two analytical techniques – regression and ranking methods – are applied to conduct these analyses. The experimental results show that, based on a bag-of-words model, using only financial sentiment words results in performance comparable to using the whole texts; this confirms the importance of financial sentiment words with respect to risk prediction. In addition to this performance comparison, via the learned models, we draw attention to some strong and interesting correlations between texts and financial risk. These valuable findings yield greater insight and understanding into the usefulness of soft information in financial reports and can be applied to a broad range of financial and accounting applications.

In the Age of Big Data, graph embedding has received increasing attention for its ability to accommodate the explosion in data volume and diversity, which challenge the foundation of modern recommender systems. Respectively, graph facilitates fusing complex systems of interactions into a unified structure and distributed embedding enables efficient retrieval of entities, as in the case of approximate nearest neighbor (ANN) search. When combined, graph embedding captures relational information beyond entity interaction and towards a problem's underlying structure, as epitomized by struct2vec [20] and PinSage [26]. This session will start by brushing up on the basics about graphs and embedding methods and discussing their merits. We then quickly dive into using the mathematical formulation of graph embedding to derive the modular framework: Sampler-Mapper-Optimizer for Recommendation, or SMORe. We demonstrate existing models used for recommendation, such as MF and BPR, can all be assembled using three basic components: sampler, mapper, and optimizer. The tutorial is accompanied by a hands-on session, where we show how graph embedding can model complex systems through the multi-task learning and the cross-platform data sparsity alleviation tasks.

This paper attempts to conduct a sentence-level sentiment analysis with respect to financial risk on a collection of financial reports. Specifically, we first propose a simple yet efficient algorithm to generate financial sentiment phrases (senti-phrases), and then with the obtained senti-phrases, we utilize multiple sentence embedding models for better learning the representations of financial risk sentences. In order to verify the performance of the proposed approach, we conduct a risk classification task of financial sentences on a sentence-level labeled dataset of finance reports. Experimental results show that incorporating the obtained senti-phrases into the embedding-based models improves the classification performance.

We present collaborative similarity embedding (CSE), a unified framework that exploits comprehensive collaborative relations available in a user-item bipartite graph for representation learning and recommendation. In the proposed framework, we differentiate two types of proximity relations: direct proximity and k-th order neighborhood proximity. While learning from the former exploits direct user-item associations observable from the graph, learning from the latter makes use of implicit associations such as user-user similarities and item-item similarities, which can provide valuable information especially when the graph is sparse. Moreover, for improving scalability and flexibility, we propose a sampling technique that is specifically designed to capture the two types of proximity relations. Extensive experiments on eight benchmark datasets show that CSE yields significantly better performance than state-of-the-art recommendation methods., Comment: The shorten version is accepted by WWW'19

We present NavWalker, a flexible random walk-based approach for learning the representations of vertices in an information network. The proposed method enables us to incorporate different walk strategies into the sampling process of random walks, in order to further boost the network embedding techniques. Specifically, we formulate the proposed method by integrating the adjacency matrix of a network with a pre-defined information augmentation matrix. In contrast to SkipGram-based network embedding methods such as DeepWalk and Node2vec, which use only local network information to learn the representations, our method is flexible to further incorporate global or other auxiliary network information to guide the sampling process. Experiments on six real-world datasets demonstrate the advantages of the flexibility and its superior performance as compared to other state-of-the-art network embedding algorithms for the tasks of classification and recommendation.

The growing amount of public financial data makes it increasingly important to learn how to discover valuable information for financial decision making. This article proposes an approach to discovering financial keywords from a large number of financial reports. In particular, we apply the continuous bag-of-words (CBOW) model, a well-known continuous-space language model, to the textual information in 10-K financial reports to discover new finance keywords. In order to capture word meanings to better locate financial terms, we also present a novel technique to incorporate syntactic information into the CBOW model. Experimental results on four prediction tasks using the discovered keywords demonstrate that our approach is effective for discovering predictability keywords for post-event volatility, stock volatility, abnormal trading volume, and excess return predictions. We also analyze the discovered keywords that attest to the ability of the proposed method to capture both syntactic and contextual information between words. This shows the success of this method when applied to the field of finance.

Recommender systems are vital ingredients for many e-commerce services. In the literature, two of the most popular approaches are based on factorization and graph-based models; the former approach captures user preferences by factorizing the observed direct interactions between users and items, and the latter extracts indirect preferences from the graphs constructed by user-item interactions. In this paper we present HOP-Rec, a unified and efficient method that incorporates the two approaches. The proposed method involves random surfing on a graph to harvest high-order information among neighborhood items for each user. Instead of factorizing a transition matrix, our method introduces a confidence weighting parameter to simulate all high-order information simultaneously, for which we maintain a sparse user-item interaction matrix and enrich the matrix for each user using random walks. Experimental results show that our approach significantly outperforms the state of the art on a range of large-scale real-world datasets.

This paper presents a web-based information system, RiskFinder, for facilitating the analyses of soft and hard information in financial reports. In particular, the system broadens the analyses from the word level to sentence level, which makes the system useful for practitioner communities and unprecedented among financial academics. The proposed system has four main components: 1) a Form 10-K risk-sentiment dataset, consisting of a set of risk-labeled financial sentences and pre-trained sentence embeddings; 2) metadata, including basic information on each company that published the Form 10-K financial report as well as several relevant financial measures; 3) an interface that highlights risk-related sentences in the financial reports based on the latest sentence embedding techniques; 4) a visualization of financial time-series data for a corresponding company. This paper also conducts some case studies to showcase that the system can be of great help in capturing valuable insight within large amounts of textual information. The system is now online available at https://cfda.csie.org/RiskFinder/.

We present FRIDAYS, a financial risk information detecting and analyzing system that enables financial professionals to efficiently comprehend financial reports in terms of risk and domain-specific sentiment cues. Our system is designed to integrate multiple NLP models trained on financial reports but on different levels (i.e., word, multi-word, and sentence levels) and to illustrate the prediction results generated by the models. The system is available online at https://cfda.csie.org/FRIDAYS/.

The emergence of social collaboration platforms has created new ways for people or groups to interact and work collaboratively to achieve mutual goals. The research community has highlighted the importance of measuring influence in such social collaboration networks to recognize key contributors and better facilitate collaboration. However, classic graph-based approaches often fail to elaborate on relations between people and the items they collaborate on, which is the essence of such social collaboration platforms. Moreover, with traditional methods it is usually difficult to incorporate auxiliary information about users and items into the modeling process. Therefore, in this paper we draw an analogy between recommender systems and social collaboration networks, and propose a method to harness information about users and items to model influence diffusion in collaboration networks. With this analogy, we quantify social influence by measuring the latent influence of each user-item pair under a unified framework based on factorization machines. Experiments conducted on a real-world dataset collected from GitHub attest the effectiveness of the proposed framework in providing better rankings for top influencers than several baseline methods. In addition, interesting analyses and discussions on the results are also provided in the paper.

This paper attempts to conduct analysis for one certain type of user reviews; that is, the reviews on a super-entity (e.g., restaurant) involve descriptions for many sub-entities (e.g., dishes). To deal with such analysis, we propose a text embedding framework for ranking sub-entities from user reviews of a given super-entity. Experiments on two real-world datasets show that our method outperforms three baselines by a statistically significant amount. Intriguing cases from the experiments are discussed in the paper.

This paper proposes an item concept embedding (ICE) framework to model item concepts via textual information. Specifically, in the proposed framework there are two stages: graph construction and embedding learning. In the first stage, we propose a generalized network construction method to build a network involving heterogeneous nodes and a mixture of both homogeneous and heterogeneous relations. The second stage leverages the concept of neighborhood proximity to learn the embeddings of both items and words. With the proposed carefully designed ICE networks, the resulting embedding facilitates both homogeneous and heterogeneous retrieval, including item-to-item and word-to-item retrieval. Moreover, as a distributed embedding approach, the proposed ICE approach not only generates related retrieval results but also delivers more diverse results than traditional keyword-matching-based approaches. As our experiments on two real-world datasets show, ICE encodes useful textual information and thus outperforms traditional methods in various item classification and retrieval tasks.

In this work, we proposed a high-capacity robust watermarking scheme for color images. Based on integer wavelet domain (IWT), the proposed scheme utilized the idea of computing the offset of two square-root-values, a number of data bits can be embedded in a host image. Simulations indicated that our method did provide a large hiding-storage while the perceived quality is good. Further, the proposed method is tolerant of various attacks such as brightness, cropping, edge sharpening, blurring, ip horizontal, inversion, and rotation. Additionally, the payload for the proposed method is larger than that for existing techniques. abstract environment.

This paper proposes a novel ranking approach, cost-sensitive ordinal classification via regression (COCR), which respects the discrete nature of ordinal ranks in real-world data sets. In particular, COCR applies a theoretically sound method for reducing an ordinal classification to binary and solves the binary classification sub-tasks with point-wise regression. Furthermore, COCR allows us to specify mis-ranking costs to further improve the ranking performance; this ability is exploited by deriving a corresponding cost for a popular ranking criterion, expected reciprocal rank (ERR). The resulting ERR-tuned COCR boosts the benefits of the efficiency of using point-wise regression and the accuracy of top-rank prediction from the ERR criterion. Evaluations on four large-scale benchmark data sets, i.e., "Yahoo! Learning to Rank Challenge" and "Microsoft Learning to Rank," verify the significant superiority of COCR over commonly used regression approaches.

User queries to the Web tend to have more than one interpretation due to their ambiguity and other characteristics. How to diversify the ranking results to meet users' various potential information needs has attracted considerable attention recently. This paper is aimed at mining the subtopics of a query either indirectly from the returned results of retrieval systems or directly from the query itself to diversify the search results. For the indirect subtopic mining approach, clustering the retrieval results and summarizing the content of clusters is investigated. In addition, labeling topic categories and concept tags on each returned document is explored. For the direct subtopic mining approach, several external resources, such as Wikipedia, Open Directory Project, search query logs, and the related search services of search engines, are consulted. Furthermore, we propose a diversified retrieval model to rank documents with respect to the mined subtopics for balancing relevance and diversity. Experiments are conducted on the ClueWeb09 dataset with the topics of the TREC09 and TREC10 Web Track diversity tasks. Experimental results show that the proposed subtopic-based diversification algorithm significantly outperforms the state-of-the-art models in the TREC09 and TREC10 Web Track diversity tasks. The best performance our proposed algorithm achieves is ?-nDCG@5 0.307, IA-P@5 0.121, and ?#-nDCG@5 0.214 on the TREC09, as well as ?-nDCG@10 0.421, IA-P@10 0.201, and ?#-nDCG@10 0.311 on the TREC10. The results conclude that the subtopic mining technique with the up-to-date users' search query logs is the most effective way to generate the subtopics of a query, and the proposed subtopic-based diversification algorithm can select the documents covering various subtopics.

In this demonstration, we present FIN10K, a web-based information system that facilitates the analysis of textual information in financial reports. The proposed system has three main components: (1) a 10-K Corpus, including an inverted index of financial reports on Form 10-K, several numerical finance measures, and pre-trained word embeddings; (2) an information retrieval system; and (3) two data visualizations of the analyzed results. The system can be of great help in revealing valuable insights within large amounts of textual information. The system is now online available at http: //clip.csie.org/10K/.

A common scenario considered in recommender systems is to predict a user's preferences on unseen items based on his/her preferences on observed items. A major limitation of this scenario is that a user might be interested in different things each time when using the system, but there is no way to allow the user to actively alter or adjust the recommended results. To address this issue, we propose the idea of "query-based recommendation" that allows a user to specify his/her search intention while exploring new items, thereby incorporating the concept of information retrieval into recommendation systems. Moreover, the idea is more desirable when the user intention can be expressed in different ways. Take music recommendation as an example: the proposed system allows a user to explore new song tracks by specifying either a track, an album, or an artist. To enable such heterogeneous queries in a recommender system, we present a novel technique called "Heterogeneous Preference Embedding" to encode user preference and query intention into low-dimensional vector spaces. Then, with simple search methods or similarity calculations, we can use the encoded representation of queries to generate recommendations. This method is fairly flexible and it is easy to add other types of information when available. Evaluations on three music listening datasets confirm the effectiveness of the proposed method over the state-of-the-art matrix factorization and network embedding methods.

With the rapid growth of large-scaled social networks, the analysis of social network data has become an extremely challenging computational issue. To meet the challenge, it is possible to significantly reduce the complexity of the problem by properly clustering a large social network into groups, and then analyzing data within each group, or studying the relationship among groups. Hence, social network clustering can be regarded as one of the essential problems in social network analysis. To address the issue, we propose an evolutionary computation approach to social network clustering. We first formulate social network clustering as an optimization problem and then develop a genetic algorithm to solve the problem. We also applied the proposed approach to a case study based on data of some Facebook users.

This paper proposes a learning approach for the merging process in multilingual information retrieval (MLIR). To conduct the learning approach, we present a number of features that may influence the MLIR merging process. These features are mainly extracted from three levels: query, document, and translation. After the feature extraction, we then use the FRank ranking algorithm to construct a merge model. To the best of our knowledge, this practice is the first attempt to use a learning-based ranking algorithm to construct a merge model for MLIR merging. In our experiments, three test collections for the task of crosslingual information retrieval (CLIR) in NTCIR3, 4, and 5 are employed to assess the performance of our proposed method. Moreover, several merging methods are also carried out for a comparison, including traditional merging methods, the 2-step merging strategy, and the merging method based on logistic regression. The experimental results show that our proposed method can significantly improve merging quality on two different types of datasets. In addition to the effectiveness, through the merge model generated by FRank, our method can further identify key factors that influence the merging process. This information might provide us more insight and understanding into MLIR merging.

With the significant advancement of statistical timing and yield analysis algorithms, there is a strong need for accurate and analytical spatial correlation models. In this paper, we propose a novel spatial correlation modeling method that can not only capture the general spatial correlation relationship but also can generate highly accurate and analytical models. Our method, based on singular value decomposition, can generate sequences of polynomial weighted by the singular values. Experimental results from foundry measurement data show that our proposed approach is 3x accuracy improvement over several distance based spatial correlation modeling methods.

This paper provides a new perspective on the default prediction problem using deep learning algorithms. Via the advantages of deep learning, the representable factors of input data will no longer need to be explicitly extracted, but can be implicitly learned by the deep learning algorithms. We consider the stock returns of both default and solvent companies as input signals and adopt one of the deep learning architecture, Deep Belief Networks (DBN), to train the prediction models. The preliminary results show that the proposed approach outperforms traditional machine learning algorithms.

How will the reputations of individuals in a social network be influenced by their communities in a quantitative way? This work attempts to observe the collaborative events occurring at individuals involved in a social network to obtain such crucial knowledge. We propose a Factorization Machine approach to find out the latent social influence among the individuals based on their collaborations. Experiments conducted on a real-world DBLP dataset verify that the proposed approach can discover the latent social influence among individuals and provide a better predictive model than several baselines.

This paper proposes an approach to discover community leaders in a social network by means of a probabilistic time-based graph propagation model. In the study, community leaders are defined as those people who initiate a lot of influence chains according to the number of chains they belong to. To conduct the approach, we define an exponential time-decay function to measure the influence of leaders and construct the chains of leaders’ action-specific influence. Then, we build the general chains by normalizing over all possible users’ actions. In specific, this paper uses the variant of the Apriori algorithm called APPM to mine users’ influence paths. To the best of our knowledge, this work is the first attempt to use the action-specific influence chains for mining community leaders from a social network. In our experiments, two datasets are collected to examine the performance of the proposed algorithm: one is a social network dataset from Facebook consisting of 134 nodes and 517 edges, and another is a citation network dataset from DBLP and Google Scholar containing 2,525 authors, 3,240 papers, and 1,914 citations. In addition, several baselines are also carried out for comparison, including three naive and one user-involved approaches. The experimental results show that, compared with the baselines, for the task of detecting community leaders, the proposed method outperforms the baselines, and our method also obtains good performance on ranking community leaders.

This paper proposes to apply the continuous vector representations of words for discovering keywords from a financial sentiment lexicon. In order to capture more keywords, we also incorporate syntactic information into the Continuous Bag-ofWords (CBOW) model. Experimental results on a task of financial risk prediction using the discovered keywords demonstrate that the proposed approach is good at predicting financial risk.

This paper proposes a context-aware approach that recommends music to a user based on the user's emotional state predicted from the article the user writes. We analyze the association between user-generated text and music by using a real-world dataset with user, text, music tripartite information collected from the social blogging website LiveJournal. The audio information represents various perceptual dimensions of music listening, including danceability, loudness, mode, and tempo; the emotional text information consists of bag-of-words and three dimensional affective states within an article: valence, arousal and dominance. To combine these factors for music recommendation, a factorization machine-based approach is taken. Our evaluation shows that the emotional context information mined from user-generated articles does improve the quality of recommendation, comparing to either the collaborative filtering approach or the content-based approach.

Due to more and more request of visual entertainment with improved perceptual realism, stereo video offering enhanced realism and interactivity is highly desired. Usually, the stereo video is packed into a single video and each view preserves only half resolution to achieve an efficient delivery. In this paper, a novel frame-compatible stereo video coding technique based on content-aware video retargeting is presented. Despite of combing the stereo video into a single channel by uniform downsampling, we propose to sub-sample the stereo video in an unequal way, by taking the saliency map of the video into considering. During the reconstruction of the stereo video with original resolution, the regions with higher saliency attention are less distorted, relying on a smaller downsampling factor, instead of 2. The experimental results reveal that the proposed technique achieves up to 43% bitrate saving as compared to the most popular frame-compatible stereo formats.

This paper attempts to use soft information in finance to rank the risk levels of a set of companies. Specifically, we deal with a ranking problem with a collection of financial reports, in which each report is associated with a company. By using text information in the reports, which is so-called the soft information, we apply learning-to-rank techniques to rank a set of companies to keep them in line with their relative risk levels. In our experiments, a collection of financial reports, which are annually published by publicly-traded companies, is employed to evaluate our ranking approach; moreover, a regression-based approach is also carried out for comparison. The experimental results show that our ranking approach not only significantly outperforms the regression-based one, but identifies some interesting relations between financial terms.

This paper proposes an approach to discovering community leaders in social network by means of a probabilistic time-based graph propagation model. To conduct the approach, we define an exponential decay function for influence as a function of time, and build action-specific influence chains by multiplying path propagation values; then, we create general influence chains by normalizing over all possible actions. In the study, our approach identifies community leaders as those people whose initiated influence chains are relatively more than the chains they involved. In our experiments, a small Facebook network dataset with 134 nodes and 517 edges is employed to assess the performance of the proposed method. In addition, several baselines are also carried out for comparison, including three naive and one user-involved approaches. The experimental results show that, compared with the baselines, the proposed method can effectively identify community leaders within the social network, achieving 0.8 in terms of F-measure.

This paper proposes a learning approach for the merging process in multilingual information retrieval (MLIR). To conduct the learning approach, we also present a large number of features that may influence the MLIR merging process; these features are mainly extracted from three levels: query, document, and translation. After the feature extraction, we then use the FRank ranking algorithm to construct a merge model; to our knowledge, this practice is the first attempt to use a learning-based ranking algorithm to construct a merge model for MLIR merging. In our experiments, three test collections for the task of crosslingual information retrieval (CLIR) in NTCIR3, 4, and 5 are employed to assess the performance of our proposed method; moreover, several merging methods are also carried out for a comparison, including traditional merging methods, the 2-step merging strategy, and the merging method based on logistic regression. The experimental results show that our method can significantly improve merging quality on two different types of datasets. In addition to the effectiveness, through the merge model generated by FRank, our method can further identify key factors that influence the merging process; this information might provide us more insight and understanding into MLIR merging.

With the significant advancement of statistical timing and yield analysis algorithms, there is a strong need for accurate and analytical spatial correlation models. In this paper, we propose a novel spatial correlation modeling method not only can capture the general spatial correlation relationship but also can generate highly accurate and analytical models. Our method, based on Singular Value Decomposition (SVD), can generate sequences of polynomial weighted by the singular values. Experimental results from foundry measurement data show that our proposed approach is 5X accuracy improvement over several distance based spatial correlation modeling methods.

Most of the thyroid nodules are heterogeneous with various internal components, which confuse many radiologists and physicians with their various echo patterns in thyroid nodules. A lot of texture extraction methods were used to characterize the thyroid nodules. Accordingly, the thyroid nodules could be classified by the corresponding textural features. In this paper, five support vector machines (SVM) were adopted to select the significant textural features and to classify the nodular lesions of thyroid. Experimental results showed the proposed method classifies the thyroid nodules correctly and efficiently. The comparison results demonstrated that the capability of feature selection of the proposed method was similar to the sequential floating forward selection (SFFS) method. However, the proposed method is faster than the SFFS method.

The paper is concerned with learning to rank, which is to construct a model or a function for ranking objects. Learning to rank is useful for document retrieval, collaborative filtering, and many other applications. Several methods for learning to rank have been proposed, which take object pairs as 'instances' in learning. We refer to them as the pairwise approach in this paper. Although the pairwise approach offers advantages, it ignores the fact that ranking is a prediction task on list of objects. The paper postulates that learning to rank should adopt the listwise approach in which lists of objects are used as 'instances' in learning. The paper proposes a new probabilistic method for the approach. Specifically it introduces two probability models, respectively referred to as permutation probability and top k probability, to define a listwise loss function for learning. Neural Network and Gradient Descent are then employed as model and algorithm in the learning method. Experimental results on information retrieval show that the proposed listwise approach performs better than the pairwise approach.

This paper compares the utilization of ConceptNet and WordNet in query expansion. Spreading activation selects candidate terms for query expansion from these two resources. Three measures including discrimination ability, concept diversity, and retrieval performance are used for comparisons. The topics and document collections in the ad hoc track of TREC-6, TREC-7 and TREC-8 are adopted in the experiments. The results show that ConceptNet and WordNet are complementary. Queries expanded with WordNet have higher discrimination ability. In contrast, queries expanded with ConceptNet have higher concept diversity. The performance of queries expanded by selecting the candidate terms from ConceptNet and WordNet outperforms that of queries without expansion, and queries expanded with a single resource.

IR with reference corpus is one approach when dealing with relevant sentences detection, which takes the result of IR as the representation of query (sentence). Lack of information and language difference are two major issues in relevant detection among multilingual sentences. This paper refers to a parallel corpus for information expansion and translation, and introduces different representations, i.e. sentence-vector, document-vector and term-vector. Both sentence-aligned and document-aligned corpora, i.e., Sinorama corpus and HKSAR corpus, are used. The factors of aligning granularity, the corpus domain, the corpus size, the language basis, and the term selection strategy are addressed. The experiment results show that MRR 0.839 is achieved for similarity computation between multilingual sentences when larger finer grain parallel corpus of the same domain as test data is adopted. Generally speaking, the sentence-vector approach is superior to the term-vector approach when sentence-aligned corpus is employed. The document-vector approach is better than the term-vector approach if document-aligned corpus is used. Considering the language issue, Chinese basis is more suitable to English basis in our experiments. We also employ the translated TREC novelty test bed to evaluate the overall performance. The experimental results show that multilingual relevance detection has 80% of the performance of monolingual relevance detection. That indicates the feasibility of IR with reference corpus approach in relevant sentence detection.

The major challenging issue to determine the relevance and the novelty of sentences is the amount of information used in similarity computation among sentences. An information retrieval (IR) with reference corpus approach is proposed. A sentence is considered as a query to a reference corpus, and similarity is measured in terms of the weighting vectors of document lists ranked by IR systems. Two sentences are regarded as similar if they are related to the similar document lists returned by IR systems. A dynamic threshold setting method is presented. Besides IR with reference corpus, we also use IR systems to retrieve sentences from given sentences. The corpus-based approach with dynamic thresholds outperforms direct retrieval approach. The average F-measure of relevance and novelty detection using Okapi system was 0.212 and 0.207, 57.14% and 58.64% of human performance, respectively.

Information Retrieval (IR) aims to discover relevant information according to a user's information need. The classic Probability Ranking Principle (PRP) forms the theoretical basis for probabilistic IR models. This ranking principle, however, neglects the uncertainty introduced through the estimations from retrieval models. Inspired by the Post-Modern Portfolio Theory (PMPT), this paper proposes a mean-semivariance framework to handle the uncertainty. The proposed framework not only deals with the uncertainty but has the ability to distinguish bad surprises (downside uncertainty) and good surprises (upside uncertainty) when optimizing a ranking list. The experimental results shows that the proposed method improves the IR performance over the PRP baseline in terms of most of IR evaluation metrics; moreover, the results suggest that the mean-semivariance framework can further boost the top-position ranking quality.