Search

Transformer structure, stacked by a sequence of encoder and decoder network layers, achieves significant development in neural machine translation. However, vanilla Transformer mainly exploits the top-layer representation, assuming the lower layers provide trivial or redundant information and thus ignoring the bottom-layer feature that is potentially valuable. In this work, we propose the Group-Transformer model (GTrans) that flexibly divides multi-layer representations of both encoder and decoder into different groups and then fuses these group features to generate target words. To corroborate the effectiveness of the proposed method, extensive experiments and analytic experiments are conducted on three bilingual translation benchmarks and three multilingual translation tasks, including the IWLST-14, IWLST-17, LDC, WMT-14, WMT-21 and OPUS-100 benchmark. Experimental and analytical results demonstrate that our model outperforms its Transformer counterparts by a consistent gain. Furthermore, it can be successfully scaled up to 60 encoder layers and 36 decoder layers.

Knowledge-grounded conversation has led to great progress in producing informative dialog responses by leveraging external knowledge. This work focuses on two affiliated knowledge grounded conversation tasks: Knowledge Selection and Response Generation. Previous work followed the paradigm of selecting the most optimal knowledge piece to guide the conversation towards generating the proper response. However, some knowledge pieces, which are not recognized as optimal, may still benefit response generation. How to effectively leverage these relevant knowledge pieces for response generation still remain a tricky issue. To address this problem, we propose KINet, a Knowledge Incorporation Network, which deals with the problem by boosting both the knowledge selection and the response generation. The proposed model contains a negative enhanced knowledge approximator which improves knowledge selection by enhancing the dense representation of knowledge pieces, and a curriculum knowledge sampler which improves generated responses by incorporating more relevant knowledge pieces in an easy-to-hard manner. We conduct the experiment on two datasets of knowledge-grounded conversations, the results show that the proposed model significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations.

Unsupervised extractive summarization aims to extract salient sentences from documents without labeled corpus. Existing methods are mostly graph-based by computing sentence centrality. These methods have two main problems: facet bias and redundant problems. Facet bias problem leads summarization models tend to select sentences within the same facet, which often leads to the ignoring of other vital facets, especially on long-document and multi-documents. First, to address the facet bias problem, we proposed a novel Facet-Aware centrality-based Ranking model (FAR). We let the model pay more attention to different facets by introducing a sentence-document weight. The weight is added to the sentence centrality score. FAR can alleviate redundancy to some extent. Then, to further reduce redundancy, we proposed a novel Redundancy- and Facet-Aware Ranking model (RFAR) which jointly models facet and redundancy by incorporating Determinantal Point Process (DPP) into the previous proposed FAR. We evaluate our FAR and RFAR on a wide range of summarization tasks that include 8 representative benchmark datasets. Experimental results show that FAR and RFAR consistently outperforms strong baselines, especially in long- and multi-document scenarios, and even perform comparably to some supervised models. Besides, we find that our methods can alleviate the position bias problem.

Application repackaging is a severe threat to Android users and the market. Not only does it infringe on intellectual property, but it is also one of the most common ways of propagating mobile malware. Existing countermeasures mostly detect repackaging based on app similarity measurement, which tends to be imprecise when obfuscations are applied to repackaged apps. Moreover, they rely on a central party, typically the hosting app store, to perform the detection, but many app stores fail to commit proper effort to piracy detection. We consider building the application repackaging detection capability into apps, such that user devices are made use to detect repackaging in a decentralized fashion. The main challenge is how to protect the detection code from being manipulated by attacks. We propose a creative use of logic bombs, which are otherwise regularly used in malware. The trigger conditions of bombs are constructed to exploit the differences between the attacker and users, such that a bomb that lies dormant on the attacker side will be activated on the user side. The detection code, which is part of the bomb payload, is executed only if the bomb is activated. We introduce cryptographically obfuscated logic bomb to enhance the bomb: (1) the detection code is woven into the neighboring original app code, (2) the mixed code gets encrypted using a key, and (3) the key is deleted from the app and can only be derived when the bomb is activated. Thus, attacks that try to modify or delete the detection code will corrupt the app itself, and searching the key in the application will be in vain. Moreover, we propose a bomb spraying technique that allows many bombs to be injected into an app, multiplying the needed adversary effort for bypassing the detection. In addition to repackaging detection, we present application tampering detection to fight attacks that insert malicious code into repackaged apps. We have implemented a prototype, named BombDroid, that builds repackaging and tampering detection into apps through bytecode instrumentation. The evaluation and the security analysis show that the technique is effective, efficient, and resilient to various bomb analysis techniques including fuzzing, symbolic execution, multi-path exploration, and program slicing. Ethical issues due to the use of logic bombs are also discussed.

Visual question answering (VQA) has been proposed as a challenging task and attracted extensive research attention. It aims to learn a joint representation of the question–image pair for answer inference. Most of the existing methods focus on exploring the multi-modal correlation between the question and image to learn the joint representation. However, the answer-related information is not fully captured by these methods, which results that the learned representation is ineffective to reflect the answer of the question. To tackle this problem, we propose a novel model, i.e., adversarial learning with multi-modal attention (ALMA), for VQA. An adversarial learning-based framework is proposed to learn the joint representation to effectively reflect the answer-related information. Specifically, multi-modal attention with the Siamese similarity learning method is designed to build two embedding generators, i.e., question–image embedding and question–answer embedding. Then, adversarial learning is conducted as an interplay between the two embedding generators and an embedding discriminator. The generators have the purpose of generating two modality-invariant representations for the question–image and question–answer pairs, whereas the embedding discriminator aims to discriminate the two representations. Both the multi-modal attention module and the adversarial networks are integrated into an end-to-end unified framework to infer the answer. Experiments performed on three benchmark data sets confirm the favorable performance of ALMA compared with state-of-the-art approaches.

This article describes how recently, many new technologies have been introduced to the web; linked data is probably the most important. Individuals and organizations started emerging and publishing their data on the web adhering to a set of best practices. This data is published mostly in English; hence, only English agents can consume it. Meanwhile, although the number of Arabic users on the web is immense, few Arabic datasets are published. Publication catalogs are one of the primary sources of Arabic data that is not being exploited. Arabic catalogs provide a significant amount of meaningful data and metadata that are commonly stored in excel sheets. In this article, an effort has been made to help publishers easily and efficiently share their catalogs' data as linked data. Marefa is the first tool implemented that automatically extracts RDF triples from Arabic catalogs, aligns them to the BIBO ontology and links them with the Arabic chapter of DBpedia. An evaluation of the framework was conducted, and some statistical measures were generated during the different phases of the extraction process.

Previous work on the one-class collaborative filtering (OCCF) problem can be roughly categorized into pointwise methods, pairwise methods, and content-based methods. A fundamental assumption of these approaches is that all missing values in the user-item rating matrix are considered negative. However, this assumption may not hold because the missing values may contain negative and positive examples. For example, a user who fails to give positive feedback about an item may not necessarily dislike it; he may simply be unfamiliar with it. Meanwhile, content-based methods, e.g. collaborative topic regression (CTR), usually require textual content information of the items, and thus their applicability is largely limited when the text information is not available. In this paper, we propose to apply the latent Dirichlet allocation (LDA) model on OCCF to address the above-mentioned problems. The basic idea of this approach is that items are regarded as words, users are considered as documents, and the user-item feedback matrix constitutes the corpus. Our model drops the strong assumption that missing values are all negative and only utilizes the observed data to predict a user’s interest. Additionally, the proposed model does not need content information of the items. Experimental results indicate that the proposed method outperforms previous methods on various ranking-oriented evaluation metrics. We further combine this method with a matrix factorization-based method to tackle the multi-class collaborative filtering (MCCF) problem, which also achieves better performance on predicting user ratings.

Scientific literature ranking is essential to help researchers find valuable publications from a large literature collection. Recently, with the prevalence of webpage ranking algorithms such as PageRank and HITS, graph-based algorithms have been widely used to iteratively rank papers and researchers through the networks formed by citation and coauthor relationships. However, existing graph-based ranking algorithms mostly focus on ranking the current importance of literature. For researchers who enter an emerging research area, they might be more interested in new papers and young researchers that are likely to become influential in the future, since such papers and researchers are more helpful in letting them quickly catch up on the most recent advances and find valuable research directions. Meanwhile, although some works have been proposed to rank the prestige of a certain type of objects with the help of multiple networks formed of multiobjects, there still lacks a unified framework to rank multiple types of objects in the bibliographic network simultaneously. In this article, we propose a unified ranking framework MRCoRankto corank the future popularity of four types of objects: papers, authors, terms, and venues through mutual reinforcement. Specifically, because the citation data of new publications are sparse and not efficient to characterize their innovativeness, we make the first attempt to extract the text features to help characterize innovative papers and authors. With the observation that the current trend is more indicative of the future trend of citation and coauthor relationships, we then construct time-aware weighted graphs to quantify the importance of links established at different times on both citation and coauthor graphs. By leveraging both the constructed text features and time-aware graphs, we finally fuse the rich information in a mutual reinforcement ranking framework to rank the future importance of multiobjects simultaneously. We evaluate the proposed model through extensive experiments on the ArnetMiner dataset containing more than 1,500,000 papers. Experimental results verify the effectiveness of MRCoRankin coranking the future influence of multiobjects in a bibliographic network.

In this paper, we present a context-sensitive approach to re-ranking retrieved documents for further improving the effectiveness of high-performance biomedical literature retrieval systems. For each topic, a two-dimensional positive context is learnt from the top N retrieved documents and a group of negative contexts are learnt from the last N′ documents in initial retrieval ranked list. The contextual space contains lexical context and conceptual context. The probabilities that retrieved documents are generated within the contextual space are then computed for document re-ranking. Empirical evaluation on the TREC Genomics full-text collection and three high-performance biomedical literature retrieval runs demonstrates that the context-sensitive re-ranking approach yields better retrieval performance.

Many bioinformatics data sets come from DNA microarray experiments. Biclustering of gene expression data can identify genes with similar behaviour with respect to different conditions. Ant Colony Optimisation (ACO) algorithms have been shown to be effective problem solving strategies for a wide range of problem domains. Multiple Objective Ant Colony Optimisation (MOACO) mainly focuses on solving the multiple objective combinatorial optimisation problems. This paper incorporates crowding update technology into MOACOB and proposes crowding MOACO biclustering algorithm to mine biclusters from gene expression data. Experimental results are shown for biclustering algorithm on two real gene expression data.

Abstract: Client-to-client password authenticated key exchange (C2C-PAKE) protocol enables two clients who only share their passwords with their own servers to establish a shared key for their secure communications. Recently, Byun et al. and Yin-Li respectively proposed first provably secure C2C-PAKE protocols. However, both protocols are found to be vulnerable to undetectable online dictionary attacks and other attacks. In this paper, we present an efficient generic construction for cross-realm C2C-PAKE protocols and prove its security in the Random-or-Real model due to Abdalla et al., without making use of the Random Oracle model. [Copyright &y& Elsevier]

Abstract: This paper researches the characteristic of time sensitive protocols and presents a method with simple operations to verify protocols with time stamps and avoid false attacks. Firstly, an extension of π calculus is given to model a time sensitive security protocol. And then, by appending linear arithmetic constraints to the Horn logic model, the extended Horn logic model of security protocols and the modified-version verification method with time constraints are represented. All operations and the strategy of verification are defined for our constraints system. Thirdly, a method is given to determine whether the constraints has a solution or not. Finally, as a result of an experiment, Denning-Sacco protocol with time stamps is verified. The experiment shows that our approach is an innovative and effective method on verifying time sensitive security protocols. [Copyright &y& Elsevier]

Abstract: Is a closed atom derivable from a definite logic progam? This derivation problem is undecidable. Focused on this problem there exist two categories approaches: the accurate approach that does not guarantee termination, and the terminated abstract approaches. Both approaches have its advantages and disadvantages. We present a novel derivation framework for the definite logic program. A dynamic approach to characterizing termination of fixpoint is presented, then which is used to approximately predict termination of fixpoint in advance. If the fixpoint is predicted termination, we use the non-terminational approach to the derivation problem, otherwise,the terminated abstract approach is used. With this termination predicting approach, we combine the non-termination accurate approaches and the termination abstract approaches together for solving the derivation problem more efficiently. And the experiment results demonstrates the effectiveness of our approach. [Copyright &y& Elsevier]

Refutation methods based on the resolution principle are generally applied to a (finite) set of sentences, which must have a series of pre-transformations (prenex normalization, Skolemization and conjunction normalization) before starting the refutation. In this paper, the authors first generalize the concept to abstract consistency class to the most general form—universal abstract consistency class, and prove its universal unifying principle. Then, based on theR-refutation, a universal refutation method is proposed and its soundness and completeness are proved by means of the universal unifying principle. This method can be applied directly to any finite set of wffs without preprocessing the wffs at all so that the refutation procedure is more natural.