Search

Generating semantically and emotionally context-consistent responses is key to intelligent dialogue systems. Previous works mainly refer to the context in the dialogue history to generate semantically related responses, ignoring the potential emotion in the conversation. In addition, existing methods mainly fail to consider the emotional changes of interlocutors and emotional categories simultaneously. However, emotion is crucial to reflect the interlocutor’s intent. In this paper, we propose an Emotion Capture Chat Machine (ECCM) that is able to capture the explicit and underlying emotional signal in the context to generate appropriate responses. In detail, we design a hierarchical recursive encoder-decoder framework with two enhanced self-attention encoders to capture the semantic signal and emotional signal, respectively, which are then fused in the decoder to produce the response. In general, we consider the dynamic and potential information of emotion to generate the response in multi-turn dialogues in the field of both daily conversation and psychological counseling. Our experimental results on a daily Chinese conversation dataset and a psychological counseling dataset show that ECCM outperforms the state-of-the-art baselines in terms of Perplexity, Distinct-1, Distinct-2, and manual evaluation. In addition, we find that ECCM performs well for input contexts with different lengths.

Session-aware recommendation is a special form of sequential recommendation, where users' previous interactions before current session are available. Recently, Recurrent Neural Network (RNN) based models are widely used in sequential recommendation tasks with great success. Previous works mainly focus on the interaction sequences of the current session without analyzing a user's long-term preferences. In this paper, we propose a joint neural network (JNN) for session-aware recommendation, which employs a Convolutional Neural Network(CNN) and a RNN to process the long-term historical interactions and the short-term sequential interactions respectively. Then, we apply a fully-connected neural network to study the complex relationship between these two types of features, which aims to generate a unified representation of the current session. Finally, a recommendation score for given items is generated by a bi-linear scheme upon the session representation. We conduct our experiments on three public datasets, showing that JNN outperforms the state-of-the-art baselines on all datasets in terms of Recall and Mean Reciprocal Rank (MRR). The outperforming results indicate that proper handling of historical interactions can improve the effectiveness of recommendation. The experimental results show that JNN is more prominent in samples with short current session or long historical interactions.

Hierarchical context modeling plays an important role in the response generation for multi-turn conversational systems. Previous methods mainly model context as multiple independent utterances and rely on attention mechanisms to obtain the context representation. They tend to ignore the explicit responds-to relationships between adjacent utterances and the special role that the user's latest utterance (the query) plays in determining the success of a conversation. To deal with this, we propose a multi-turn response generation model named KS-CQ, which contains two crucial components, the Keep and the Select modules, to produce a neighbor-aware context representation and a context-enriched query representation. The Keep module recodes each utterance of context by attentively introducing semantics from its prior and posterior neighboring utterances. The Select module treats the context as background information and selectively uses it to enrich the query representing process. Extensive experiments on two benchmark multi-turn conversation datasets demonstrate the effectiveness of our proposal compared with the state-of-the-art baselines in terms of both automatic and human evaluations.

Collaborative filtering (CF) aims to make recommendations for users by detecting user’s preference from the historical user–item interactions. Existing graph neural networks (GNN) based methods achieve satisfactory performance by exploiting the high-order connectivity between users and items, however they suffer from the poor training efficiency problem and easily introduce bias for information propagation. Moreover, the widely applied Bayesian personalized ranking (BPR) loss is insufficient to provide supervision signals for training due to the extremely sparse observed interactions. To deal with the above issues, we propose the Efficient Graph Collaborative Filtering (EGCF) method. Specifically, EGCF adopts merely one-layer graph convolution to model the collaborative signal for users and items from the first-order neighbors in the user–item interactions. Moreover, we introduce contrastive learning to enhance the representation learning of users and items by deriving the self-supervisions, which is jointly trained with the supervised learning. Extensive experiments are conducted on two benchmark datasets, i.e., Yelp2018 and Amazon-book, and the experimental results demonstrate that EGCF can achieve the state-of-the-art performance in terms of Recall and normalized discounted cumulative gain (NDCG), especially on ranking the target items at right positions. In addition, EGCF shows obvious advantages in the training efficiency compared with the competitive baselines, making it practicable for potential applications.

Purpose The purpose of this paper is to investigate how nonprofit service providers can better engage their customers through online communication. It identifies two communication styles and three communication functions, and examines their impact on customer commenting, customer liking and customer sharing. Design/methodology/approach Similar to Python for Facebook, a software package for the automatic retrieval of web page content was developed specifically for this study to extract data from the microblog Sina Weibo. Following the successful retrieval of 1,500 randomly selected messages from 34 universities in China, a two-level regression was performed using Mplus 7 to examine the association between the proposed relationships. Findings The findings reveal that messages with a friendly communication style increase both the number of comments and their positive tone; an authoritative style has no effect on customer engagement. The functions associated with message content (spreading information, building community or promoting action) influence customer liking and sharing. Building community tends to engage more customers than spreading information; promoting action often generates the least customer engagement in social media settings. Originality/value The study fills an important research gap in the service marketing literature as it pertains to nonprofit service organizations (i.e. universities) by identifying two types of online identities based on the communication style and the messages posted on social media. This study is the first to investigate the relationship between identity type and audience engagement, and to analyze the moderating factors of this relationship.

The design of distributed control plane is an essential part of SDN. While there is an urgent need for verifying the control plane, little, however, is known about how to validate that the control plane offers assurable performance, especially across various failures. Such validation is hard due to two fundamental challenges. First, the number of potential failure scenarios could be exponential or even non-enumerable. Second, it is still an open problem to model the performance change when the control plane employs different failure recovery strategies. In this paper, we first characterize the validation of the distributed control plane as a robust optimization problem and further propose a robust validation framework to verify whether a control plane provides assurable performance across various failure scenarios and multiple failure recovery strategies. Then, we prove that identifying an optimal recovery strategy is NP-hard after developing an optimization model of failure recovery. Accordingly, we design two efficient failure recovery strategies, which can well approximate the optimal strategy and further exhibit good performance against potential failures. Furthermore, we design the capacity augmentation scheme when the control plane fails to accommodate the worst failure scenario even with the optimal failure recovery strategy. We have conducted extensive evaluations based on an SDN test bed and large-scale simulations over real network topologies. The evaluation results show the efficiency and effectiveness of the proposed validation framework.

Text representation, which converts text spans into real-valued vectors or matrices, is a crucial tool for machines to understand the semantics of text. Although most previous works employed classic methods based on statistics and neural networks, such methods might suffer from data sparsity and insensitivity to the text structure, respectively. To address the above drawbacks, we propose a general and structure-sensitive framework, i.e., the hierarchical architecture. Specifically, we incorporate the hierarchical architecture into three existing neural network models for document representation, thereby producing three new representation models for document classification, i.e., TextHFT, TextHRNN, and TextHCNN. Our comprehensive experimental results on two public datasets demonstrate the effectiveness of the hierarchical architecture. With a comparable (or substantially less) time expense, our proposals obtain significant improvements ranging from 4.65 to 35.08% in terms of accuracy against the baseline. We can conclude that the hierarchical architecture can enhance the classification performance. In addition, we find that the benefits provided by the hierarchical architecture can be strengthened as the document length increases.

Answer selection is an essential step in a question answering (QA) system. Traditional methods for this task mainly focus on developing linguistic features that are limited in practice. With the great success of deep learning method in distributed text representation, deep learning-based answer selection approaches have been well investigated, which mainly employ only one neural network, i.e., convolutional neural network (CNN) or long short term memory (LSTM), leading to failures in extracting some rich sentence features. Thus, in this paper, we propose a collaborative learning-based answer selection model (QA-CL), where we deploy a parallel training architecture to collaboratively learn the initial word vector matrix of the sentence by CNN and bidirectional LSTM (BiLSTM) at the same time. In addition, we extend our model by incorporating the sentence embedding generated by the QA-CL model into a joint distributed sentence representation using a strong unsupervised baseline weight removal (WR), i.e., the QA-CLWR model. We evaluate our proposals on a popular QA dataset, InsuranceQA. The experimental results indicate that our proposed answer selection methods can produce a better performance compared with several strong baselines. Finally, we investigate the models’ performance with respect to different question types and find that question types with a medium number of questions have a better and more stable performance than those types with too large or too small number of questions.

Session-based recommendation aims to model a user’s intent and predict an item that the user may interact with in the next step based on an ongoing session. Existing session-based recommender systems mainly aim to model the sequential signals based on Recurrent Neural Network (RNN) structures or the item transition relations between items with Graph Neural Network (GNN) based frameworks to identify a user’s intent for recommendation. However, in real scenarios, there may be strong sequential signals existing in users’ adjacent behaviors or multi-step transition relations among different items. Thus, either RNN- or GNN-based methods can only capture limited information for modeling complex user behavior patterns. RNNs pay attention to the sequential relations among consecutive items, while GNNs focus on structural information, i.e., how to enrich the item embedding with its adjacent items. In this paper, we propose a Collaborative Co-attention Network for Session-based Recommendation (CCN-SR) to incorporate both sequential and structural information, as well as capture the co-relations between them for obtaining an accurate session representation. To be specific, we first model the ongoing session with an RNN structure to capture the sequential information among items. Meanwhile, we also construct a session graph to learn the item representations with a GNN structure. Then, we design a co-attention network upon these two structures to capture the mutual information between them. The designed co-attention network can enrich the representation of each node in the session with both sequential and structural information, and thus generate a more comprehensive representation for each session. Extensive experiments are conducted on two public e-commerce datasets, and the results demonstrate that our proposed model outperforms state-of-the-art baseline model for session based recommendation in terms of both Recall and MRR. We also investigate different combination strategies and the experimental results verify the effectiveness of our proposed co-attention mechanism. Besides, our CCN-SR model achieves better performance than baseline models with different session lengths.

Event detection classifies unlabeled sentences into event labels, which can benefit numerous applications, including information retrieval, question answering and script learning. One of the major obstacles to event detection in reality is insufficient training data. To deal with the low-resources problem, we investigate few-shot event detection in this paper and propose TaLeM, a novel taxonomy-aware learning model, consisting of two components, i.e., the taxonomy-aware self-supervised learning framework (TaSeLF) and the taxonomy-aware prototypical networks (TaPN). Specifically, TaSeLF mines the taxonomy-aware distance relations to increases the training examples, which alleviates the generalization bottleneck brought by the insufficient data. TaPN introduces the Poincare embeddings to represent the label taxonomy, and integrates them into a task-adaptive projection networks, which tackles problems of the class centroids distribution and the taxonomy-aware embedding distribution in the vanilla prototypical networks. Extensive experiments in the four types of meta tasks demonstrate the superiority of our proposal over the strong baselines, and further verify the effectiveness and importance of modeling the label taxonomy. Besides, TaSeLF can be a flexible plug-in for the other taxonomy-based few-shot classification tasks.

Currently, with the deepening of development and open of China's border, issues of border joint defense become increasingly arduous. Traditional means of cooperation and coordination are far from being able to align requirements; information systems of different joint defense units are difficult to interconnect and interoperate; the previous results of joint defense informatization are difficult to inherit. The main reason is the lack of border joint defense information construction with a top-level design approach. Via the lens of top-level design, this paper establishes a multi-viewpoint architecture framework and transformation process, develops the as-is and to-be joint defense architecture, and finally analyzes transformation principles from the as-is architecture to to-be architecture. This paper mainly explores the architecture transformation mechanisms under the border joint defense scenario.

Text representation can aid machines in understanding text. Previous work on text representation often focuses on the so-called forward implication, i.e., preceding words are taken as the context of later words for creating representations, thus ignoring the fact that the semantics of a text segment is a product of the mutual implication of words in the text: later words contribute to the meaning of preceding words. We introduce the concept of interaction and propose a two-perspective interaction representation, that encapsulates a local and a global interaction representation. Here, a local interaction representation is one that interacts among words with parent-children relationships on the syntactic trees and a global interaction interpretation is one that interacts among all the words in a sentence. We combine the two interaction representations to develop a Hybrid Interaction Representation (HIR). Inspired by existing feature-based and fine-tuning-based pretrain-finetuning approaches to language models, we integrate the advantages of feature-based and fine-tuning-based methods to propose the Pre-train, Interact, Fine-tune (PIF) architecture. We evaluate our proposed models on five widely-used datasets for text classification tasks. Our ensemble method, outperforms state-of-the-art baselines with improvements ranging from 2.03% to 3.15% in terms of error rate. In addition, we find that, the improvements of PIF against most state-of-the-art methods is not affected by increasing of the length of the text., 32 pages, 5 figures

Session-based recommendation is a challenging task. Without access to a user's historical user-item interactions, the information available in an ongoing session may be very limited. Previous work on session-based recommendation has considered sequences of items that users have interacted with sequentially. Such item sequences may not fully capture complex transition relationship between items that go beyond inspection order. Thus graph neural network (GNN) based models have been proposed to capture the transition relationship between items. However, GNNs typically propagate information from adjacent items only, thus neglecting information from items without direct connections. Importantly, GNN-based approaches often face serious overfitting problems. We propose Star Graph Neural Networks with Highway Networks (SGNN-HN) for session-based recommendation. The proposed SGNN-HN applies a star graph neural network (SGNN) to model the complex transition relationship between items in an ongoing session. To avoid overfitting, we employ highway networks (HN) to adaptively select embeddings from item representations. Finally, we aggregate the item embeddings generated by the SGNN in an ongoing session to represent a user's final preference for item prediction. Experiments on two public benchmark datasets show that SGNN-HN can outperform state-of-the-art models in terms of P@20 and MRR@20 for session-based recommendation.

Given an occurred event, human can easily predict the next event or reason the preceding event, yet which is difficult for machine to perform such event reasoning. Event representation bridges the connection and targets to model the process of event reasoning as a machine-readable format, which then can support a wide range of applications in information retrieval, e.g., question answering and information extraction. Existing work mainly resorts to a joint training to integrate all levels of training loss in event chains by a simple loss summation, which is easily trapped into a local optimum. In addition, the scenario knowledge in event chains is not well investigated for event representation. In this paper, we propose a unified fine-tuning architecture, incorporated with scenario knowledge for event representation, i.e., UniFA-S, which mainly consists of a unified fine-tuning architecture (UniFA) and a scenario-level variational auto-encoder (S-VAE). In detail, UniFA employs a multi-step fine-tuning to integrate all levels of training and S-VAE applies a stochastic variable to implicitly represent the scenario-level knowledge. We evaluate our proposal from two aspects, i.e., the representation and inference abilities. For the representation ability, our ensemble model UniFA-S can beat state-of-the-art baselines for two similarity tasks. For the inference ability, UniFA-S can outperform the best baseline, achieving 4.1%-8.2% improvements in terms of accuracy for various inference tasks.

The application of pose assessment on rehabilitation training has gradually received attention in recent years. However, current evaluation indicators of these methods are mostly based on the score or scoring function that defined by users, which is too subjective and hard to be used by patients directly. In this paper, we conceptualized a new idea for pose matching, namely pose-guided matching that aims at providing objective and accurate score, feedback and guidance (i.e. guided) to the patients when the pose is compared to the standard pose. More specifically, we proposed a pair-based Siamese Convolutional Neural Network (SCNN) abbreviated ST-AMCNN to realize the idea of pose-guided matching on the eight-section brocade dataset which is one of the most representative traditional rehabilitation exercises in China. We simplified the multi-stages pose matching by merging two standalone modules (i.e. alignment and matching module) into a one-stage task. Such that, only one loss function is required to tune, which reduces the computational complexity. On top of the Spatial Transformer Networks (STN) employed as an alignment module, we proposed a new Attention-based Multi-Scale Convolution (AMC) to match different posture parts (i.e. multi-scale). Furthermore, the proposed AMC can assign more weight to useful pose features as opposed to other irrelevant features e.g. background features for performance gain. Finally, Gradient-weighted Class Activation Mapping (Grad-CAM) is adopted to visualize the matching result for the learner. Experimental results indicate that ST-AMCNN achieves a competitive performance than the state-of-the-art models and can provide accurate feedback for learners on rehabilitation training. Simultaneously, the proposed method is also deployed in client software for testing.

Fact verification aims to retrieve related evidence from raw text to verify the correctness of a given claim. Existing works mainly leverage the single-granularity features for the representation learning of evidences, i.e., sentence features, ignoring other features like entity-level and context-level features. In addition, they usually focus on improving the prediction accuracy while lacking the interpretability of the inference process, which leads to unreliable results. Thus, in this paper, to investigate how to utilize multi-granularity semantic units for evidence representation as well as to improve the explainability of evidence reasoning, we propose a Hierarchical Reasoning-based Heterogeneous Graph Neural Network for fact verification (HHGN). HHGN combines multiple features of entity, sentence as well as context for evidence representation, and employs a heterogeneous graph to capture their semantic relations. Inspired by the human inference process, we design a hierarchical reasoning-based node updating strategy to propagate the evidence features. Then, we extract the potential reasoning paths from the graph to predict the label, which aggregates the results of different paths weighted by their relevance to the claim. We evaluate our proposal on FEVER, a large-scale benchmark dataset for fact verification. Our experimental results demonstrate the superiority of HHGN over the competitive baselines in both single evidence and multiple evidences settings. In addition, HHGN presents reasonable interpretability in the form of aggregating the features of relevant entity units and selecting the evidence sentences with high confidence.

Fact verification aims to evaluate the authenticity of a given claim based on the evidence sentences retrieved from Wikipedia articles. Existing works mainly leverage the natural language inference methods to model the semantic interaction of claim and evidence, or further employ the graph structure to capture the relation features between multiple evidences. However, previous methods have limited representation ability in encoding complicated units of claim and evidences, and thus cannot support sophisticated reasoning. In addition, a limited amount of supervisory signals lead to the graph encoder could not distinguish the distinctions of different graph structures and weaken the encoding ability. To address the above issues, we propose a Knowledge-Enhanced Graph Attention network (KEGA) for fact verification, which introduces a knowledge integration module to enhance the representation of claims and evidences by incorporating external knowledge. Moreover, KEGA leverages an auxiliary loss based on contrastive learning to fine-tune the graph attention encoder and learn the discriminative features for the evidence graph. Comprehensive experiments conducted on FEVER, a large-scale benchmark dataset for fact verification, demonstrate the superiority of our proposal in both the multi-evidences and single-evidence scenarios. In addition, our findings show that the background knowledge for words can effectively improve the model performance.

We propose a J-NCF method for recommender systems. The J-NCF model applies a joint neural network that couples deep feature learning and deep interaction modeling with a rating matrix. Deep feature learning extracts feature representations of users and items with a deep learning architecture based on a user-item rating matrix. Deep interaction modeling captures non-linear user-item interactions with a deep neural network using the feature representations generated by the deep feature learning process as input. J-NCF enables the deep feature learning and deep interaction modeling processes to optimize each other through joint training, which leads to improved recommendation performance. In addition, we design a new loss function for optimization, which takes both implicit and explicit feedback, point-wise and pair-wise loss into account. Experiments on several real-word datasets show significant improvements of J-NCF over state-of-the-art methods, with improvements of up to 8.24% on the MovieLens 100K dataset, 10.81% on the MovieLens 1M dataset, and 10.21% on the Amazon Movies dataset in terms of HR@10. NDCG@10 improvements are 12.42%, 14.24% and 15.06%, respectively. We also conduct experiments to evaluate the scalability and sensitivity of J-NCF. Our experiments show that the J-NCF model has a competitive recommendation performance with inactive users and different degrees of data sparsity when compared to state-of-the-art baselines., 30 pages

Answer selection focuses on selecting the correct answer for a question. Most previous work on answer selection achieves good performance by employing an RNN, which processes all question and answer sentences with the same feature extractor regardless of the sentence length. These methods often encounter the problem of long-term dependencies. To address this issue, we propose a Length-adaptive Neural Network (LaNN) for answer selection that can auto-select a neural feature extractor according to the length of the input sentence. In particular, we propose a flexible neural structure that applies a BiLSTM-based feature extractor for short sentences and a Transformer-based feature extractor for long sentences. To the best of our knowledge, LaNN is the first neural network structure that can auto-select the feature extraction mechanism based on the input. We quantify the improvements of LaNN against several competitive baselines on the public WikiQA dataset, showing significant improvements over the state-of-the-art.

Fact verification aims to retrieve relevant evidence from a knowledge base, e.g., Wikipedia, to verify the given claims. Existing methods only consider the sentence-level semantics for evidence representations, which typically neglect the importance of fine-grained features in the evidence-related sentences. In addition, the interpretability of the reasoning process has not been well studied in the field of fact verification. To address such issues, we propose an entity-graph based reasoning method for fact verification abbreviated as RoEG, which generates the fine-grained features of evidence at the entity-level and models the human reasoning paths based on an entity graph. In detail, to capture the semantic relations of retrieved evidence, RoEG introduces the entities as nodes and constructs the edges in the graph based on three linking strategies. Then, RoEG utilizes a selection gate to constrain the information propagation in the sub-graph of relevant entities and applies a graph neural network to propagate the entity-features for reasoning. Finally, RoEG employs an attention aggregator to gather the information of entities for label prediction. Experimental results on a large-scale benchmark dataset FEVER demonstrate the effectiveness of our proposal by beating the competitive baselines in terms of label accuracy and FEVER Score. In particular, for a task of multiple-evidence fact verification, RoEG produces 5.48% and 4.35% improvements in terms of label accuracy and FEVER Score against the state-of-the-art baseline. In addition, RoEG shows a better performance when more entities are involved for fact verification.

Incorporating topic information can help response generation models to produce informative responses for chat-bots. Previous work only considers the individual semantic of each topic, ignoring its specific dialog context, which may result in inaccurate topic representation and hurt response coherence. Besides, as an important feature of multi-turn conversation, dynamic topic transitions have not been well-studied. We propose a Context-Controlled Topic-Aware neural response generation model, i.e., CCTA, which makes dialog context interact with the process of topic representing and transiting to achieve balanced improvements on response informativeness and contextual coherence. CCTA focuses on capturing the semantical relations within topics as well as their corresponding contextual information in conversation, to produce context-dependent topic representations at the word-level and turn-level. Besides, CCTA introduces a context-controlled topic transition strategy, utilizing contextual topics to yield relevant transition words. Extensive experimental results on two benchmark multi-turn conversation datasets validate the superiority of our proposal on generating coherent and informative responses against the state-of-the-art baselines. We also find that topic transition modeling can work as an auxiliary learning task to boost the response generation.

In previous work on text summarization, encoder-decoder architectures and attention mechanisms have both been widely used. Attention-based encoder-decoder approaches typically focus on taking the sentences preceding a given sentence in a document into account for document representation, failing to capture the relationships between a sentence and sentences that follow it in a document in the encoder. We propose an attentive encoder-based summarization (AES) model to generate article summaries. AES can generate a rich document representation by considering both the global information of a document and the relationships of sentences in the document. A unidirectional recurrent neural network (RNN) and a bidirectional RNN are considered to construct the encoders, giving rise to unidirectional attentive encoder-based summarization (Uni-AES) and bidirectional attentive encoder-based summarization (Bi-AES), respectively. Our experimental results show that Bi-AES outperforms Uni-AES. We obtain substantial improvements over a relevant start-of-the-art baseline.

Query auto-completion (QAC) is one of the most visible features in modern search engines. It helps users complete their queries by presenting a list of possible completions while they are typing in the search box. Existing works on QAC focus on employing learning-to-rank algorithms over handcrafted features. However, those manually designed features are unable to capture non-linear relationships between users and their submitted queries. Meanwhile, although Recurrent Neural Networks (RNNs) show significant advances in various areas, little attention is paid to its application to QAC. To bridge this gap, we propose three RNN-based models for QAC ranking: a simple session-based RNN model, a personalized RNN model and an attentive RNN model. Extensive experiments are conducted on a real-world query log. The significant improvement over the compared baseline verifies the effectiveness of the personalized RNN model and the attentive RNN model.

Users are strongly influenced by their friends or other users with similar interest. In this paper, we first provide a friends cluster identification approach based on the analysis of social features. Secondly, we propose our static recommendation approach based on an unbiased random walk strategy which simultaneously considers traditional recommendation approach and social relationship. Then, we further identify the change of both friendship and interest over time and propose our extended recommendation algorithm. Finally, we evaluate our approach on CiteULike and Last.fm dataset. Our experimental results demonstrate that the proposed algorithms can be very effective in recommending unknown items.

Document classification has a broad application in the field of sentiment classification, document ranking and topic labeling, etc. Previous neural network-based work has mainly focused on investigating a so-called forward implication, i.e., the preceding text segments are taken as the context of the following text segments when generating the text representation. Such a scenario typically ignores the fact that the semantics of a document are a product of the mutual implication of all text segments in a document. Thus, in this paper, we introduce a concept of interaction and propose a text representation model with Self-interaction Attention Mechanism (TextSAM) for document classification. In particular, we design three aggregated strategies to integrate the interaction into a hierarchical architecture for document classification, i.e., averaging the interaction, maximizing the interaction and adding one more attention layer on the interaction, which leads to three models, i.e., TextSAMAVE, TextSAMMAX and TextSAMATT, respectively. Our comprehensive experimental results on two public datasets, i.e., Yelp 2016 and Amazon Reviews (Electronics), show that our proposals can significantly outperform the state-of-the-art neural-based baselines for document classification, presenting a general improvement in terms of accuracy ranging from 5.97% to 14.05% against the best baseline. Furthermore, we find that our proposals with a self-interaction attention mechanism can obviously alleviate the impact brought by the increase of sentence number as the relative improvement of our proposals against the baselines are enlarged when the sentence number increases.

Document representation is widely used in practical application, for example, sentiment classification, text retrieval, and text classification. Previous work is mainly based on the statistics and the neural networks, which suffer from data sparsity and model interpretability, respectively. In this paper, we propose a general framework for document representation with a hierarchical architecture. In particular, we incorporate the hierarchical architecture into three traditional neural-network models for document representation, resulting in three hierarchical neural representation models for document classification, that is, TextHFT, TextHRNN, and TextHCNN. Our comprehensive experimental results on two public datasets, that is, Yelp 2016 and Amazon Reviews (Electronics), show that our proposals with hierarchical architecture outperform the corresponding neural-network models for document classification, resulting in a significant improvement ranging from 4.65% to 35.08% in terms of accuracy with a comparable (or substantially less) expense of time consumption. In addition, we find that the long documents benefit more from the hierarchical architecture than the short ones as the improvement in terms of accuracy on long documents is greater than that on short documents.

Query suggestions help users refine their queries after they input an initial query. We consider the task of generating query suggestions that are personalized and diversified. We propose a personalized query suggestion diversification model (PQSD), where a user's long-term search behavior is injected into a basic greedy query suggestion diversification model (G-QSD) that considers a user's search context in their current session. Query aspects are identified through clicked documents based on the Open Directory Project (ODP). We quantify the improvement of PQSD over a state-of-the-art baseline using the AOL query log and show that it beats the baseline in terms of metrics used in query suggestion ranking and diversification. The experimental results show that PQSD achieves the best performance when only queries with clicked documents are taken as search context rather than all queries.

Query autocompletion (QAC) is a common interactive feature of web search engines. It aims at assisting users to formulate queries and avoiding spelling mistakes by presenting them with a list of query completions as soon as they start typing in the search box. Existing QAC models mostly rank the query completions by their past popularity collected in the query logs. For some queries, their popularity exhibits relatively stable or periodic behavior while others may experience a sudden rise in their query popularity. Current time-sensitive QAC models focus on either periodicity or recency and are unable to respond swiftly to such sudden rise, resulting in a less optimal QAC performance. In this paper, we propose a hybrid QAC model that considers two temporal patterns of query’s popularity, that is, periodicity and burst trend. In detail, we first employ the Discrete Fourier Transform (DFT) to identify the periodicity of a query’s popularity, by which we forecast its future popularity. Then the burst trend of query’s popularity is detected and incorporated into the hybrid model with its cyclic behavior. Extensive experiments on a large, real-world query log dataset infer that modeling the temporal patterns of query popularity in the form of its periodicity and its burst trend can significantly improve the effectiveness of ranking query completions.

创新点 本文提出一种贪婪算法, 解决信息检索系统中查询推荐多样化问题, 算法目的旨在返回给用户的查询推荐列表既能准确包含用户的潜在查询, 又能使得查询列表涵盖尽可能多的主题, 这样提高不同类型用户查询推荐满意度。 在本算法中, 用户的查询意图不仅体现在当前查询热度上, 同时我们从用户的检索查询历史中挖掘有用信息预测用户意图, 生成用户的查询意图在各个主题上的概率分布, 并依此计算每个查询词被提交的概率并进行排序。 提出的算法在公共测试集上取得了较好地性能, 能把初始查询推荐列表中相似的查询词移除, 达到查询词多样化的目的。

This article uses intraday data for the year 1992 to investigate the effect of trading halts on price discovery for stocks traded on the New York Stock Exchange. The results show that the degree of benefits from trading halts depends on the types of halts and significance of the news items. It is found that trading halts reduce price dispersion when trading is halted due to imbalance in order flows. Such a positive effect is robust to the significance of news items. Trading halts can help price discovery when trading is halted due to the fact that some significant news items already hit the market and investors need more time to digest the impacts on price. In contrast, when officials call for the halt due to the pending news release with little significance, trading halts actually inject more noise into the prices and undermine the price discovery process. Overall, the results are consistent with the argument by exchanges that trading halts help dissipate information and facilitate the price discovery pr...

Information retrieval applications have to publish their output in the form of ranked lists. Such a requirement motivates researchers to develop methods that can automatically learn effective ranking models. Many existing methods usually perform analysis on multidimensional features of query-document pairs directly and don't take users' interactive feedback information into account. They thus incur the high computation overhead and low retrieval performance due to an indefinite query expression. In this paper, we propose a Virtual Feature based Logistic Regression (VFLR) ranking method that conducts the logistic regression on a set of essential but independent variables, called virtual features (VF). They are extracted via the principal component analysis (PCA) method with the user's relevance feedback. We then predict the ranking score of each queried document to produce a ranked list. We systematically evaluate our method using the LETOR 4.0 benchmark datasets. The experimental results demonstrate that the proposal outperforms the state-of-the-art methods in terms of the Mean Average Precision (MAP), the Precision at position k (P@k), and the Normalized Discounted Cumulative Gain at position k (NDCG@k).

Aiming at grid nets under the environment of mass, heterogeneous information task, distribution and dynamic characteristics, this paper discusses the principles to be followed firstly, then creates the operational missions information quality evaluation index system and the utility measure mode. The results can provide an authentication method for sharing and using the operational mission information based on grid nets.

With an increasing use of services sustaining the resources which people need has become more important. In this paper, we propose an effective reservation method, called “BPSR” (Business Process Service Reservation), which aims for the process reservation which to the best of our knowledge has not been studied before. In particular we address for major jobs: service differentiation; service reservation; process reservation and QoS Control. We also describe a flexible policy-based reservation method which aims to increase the success rate of reservation and utilization of service resources. Experimental analysis shows that the BPSR reservation system achieves better results than other reservation methods.

A key challenge in composite web processes is that the quality of participating services changes during the life time of the process. It is necessary to find an available equivalent service to substitute the failed component which has been made unavailable. In this paper different from the previous method based on recompositing the web process, we present an approach of discovering the “same skill” web services to replace the expired one by using the service expiration times.

In contrast to a typical pyramid information system, resources and services in a networked information system are often distributed, published, accessed and updated by multiple service providers. The networked information systems need to support the logistical aspects of business processes at hand. How to invoke these services to satisfy the users’ requirement? A lot of research work has been done in the fields of service discovery and service composition. A feasible method is making use of service API schema classification to inquire suitable service, and then designing a workflow mechanism to consume a serial of services on the fly. But this method cannot guarantee the high service recall and precision rate. And up to now there is no appropriate method to realize the dynamic service composition. Object Petri Nets (OPN) are a well-founded process modeling technique which have been used to model and analyze several types of processes including protocols, manufacturing systems, and business processes. This paper brings forward dynamic service composition based on OPN for networked information system. A service behavior is basically a partial ordered set of operations, which can interact with each other by standard network protocol and interface. The paper brings forward the mapping rules from service to Object Petri Net, based on which the eight tuple description is presented. Secondly the five basic service composition models of sequence, alternative, parallel, arbitrary sequence, iteration are determined, and the mathematical characteristics are studied. Finally the paper brings forward service dynamic composition flow chart. Through the research on dynamic service composition based on OPN, it is adaptable to model and simulate for the networked information system.

Web document ranking arises in many information retrieval (IR) applications, such as the search engine, recommendation system and online advertising. A challenging issue is how to select the representative query-document pairs and informative features as well for better learning and exploring new ranking models to produce an acceptable ranking list of candidate documents of each query. In this study, we propose an active sampling (AS) plus kernel principal component analysis (KPCA) based ranking model, viz. AS-KPCA Regression, to study the document ranking for a retrieval system, i.e. how to choose the representative query-document pairs and features for learning. More precisely, we fill those documents gradually into the training set by AS such that each of which will incur the highest expected DCG loss if unselected. Then, the KPCA is performed via projecting the selected query-document pairs onto p-principal components in the feature space to complete the regression. Hence, we can cut down the computational overhead and depress the impact incurred by noise simultaneously. To the best of our knowledge, we are the first to perform the document ranking via dimension reductions in two dimensions, namely, the number of documents and features simultaneously. Our experiments demonstrate that the performance of our approach is better than that of the baseline methods on the public LETOR 4.0 datasets. Our approach brings an improvement against RankBoost as well as other baselines near 20% in terms of MAP metric and less improvements using P@K and NDCG@K, respectively. Moreover, our approach is particularly suitable for document ranking on the noisy dataset in practice.

Knowledge services technology is becoming the important means to realize Business Intelligence and Knowledge-Based Systems. Based on the development of Grid and Web Services technologies, using Service-Oriented Architecture to build knowledge services is mentioned by many researchers. In this paper, a multi-perspective Knowledge Service Description Model (KSDM) for overall knowledge service modeling is proposed. The model pays attention to the executable part such as the dynamics, process, functionality and context of knowledge within knowledge service, which have not been addressed in existing knowledge service methods. Besides the basic configuration part, the model emphasizes definition of the knowledge contents part from four main perspectives that are Domain Knowledge, Inference Knowledge, Task Knowledge and Context Knowledge. For the application in real systems, a task-oriented architecture based on KSDM is proposed. And an implementation of mine resources evaluation knowledge service on Spatial Information Grid is introduced.

This paper focuses on how to model grid resource and locate grid resource using efficient and scaleable protocol under a grid environment. A mathematic model of grid physical resource space and logical resource space is built based concept of virtual organization. Then, a mathematical method based the binary equivalent relation is presented to divide grid physical resource space. Then, this paper proposes the concept of grid resource domain, and introduce a fully decentralized grid resource locating protocol based it from aspects of the overlay network of grid resource domains and query routing protocol among different grid resource domains. On the other hand, in order to propagate query among information nodes within given grid resource domain, this paper presents informed search protocol based bloom filters. Our resource locating protocol can enhance the query success rate and recall rate, and avoid too much unnecessary query messages.

As the increasing development of application technology and infrastructure, many kinds of application and resources can be encapsulated as Web service and its variations, and service-oriented computing become research hot. But, we believe service-oriented computing should establish on virtualized service rather than concrete service instance directly. In this paper, we present formalized model of virtualized service and service instance, and define the concept of service virtualization. Then, we propose the implementation solution of virtualized service-oriented application from perspective of global and local instantiation process.