Query Sentence Research Articles

SQL Injection Attacks Prevention System Technology: Review

The vulnerabilities in most web applications enable hackers to gain access to confidential and private information. Structured query injection poses a significant threat to web applications and is one of the most common and widely used information theft mechanisms. Where hackers benefit from errors in the design of systems or existing gaps by not filtering the user's input for some special characters and symbols contained within the structural query sentences or the quality of the information is not checked, whether it is text or numerical, which causes unpredictability of the outcome of its implementation. In this paper, we review PHP techniques and other techniques for protecting SQL from the injection, methods for detecting SQL attacks, types of SQL injection, causes of SQL injection via getting and Post, and prevention technology for SQL vulnerabilities.

Text-Guided Graph Neural Networks for Referring 3D Instance Segmentation

This paper addresses a new task called referring 3D instance segmentation, which aims to segment out the target instance in a 3D scene given a query sentence. Previous work on scene understanding has explored visual grounding with natural language guidance, yet the emphasis is mostly constrained on images and videos. We propose a Text-guided Graph Neural Network (TGNN) for referring 3D instance segmentation on point clouds. Given a query sentence and the point cloud of a 3D scene, our method learns to extract per-point features and predicts an offset to shift each point toward its object center. Based on the point features and the offsets, we cluster the points to produce fused features and coordinates for the candidate objects. The resulting clusters are modeled as nodes in a Graph Neural Network to learn the representations that encompass the relation structure for each candidate object. The GNN layers leverage each object's features and its relations with neighbors to generate an attention heatmap for the input sentence expression. Finally, the attention heatmap is used to "guide" the aggregation of information from neighborhood nodes. Our method achieves state-of-the-art performance on referring 3D instance segmentation and 3D localization on ScanRefer, Nr3D, and Sr3D benchmarks, respectively.

Natural language query handling using extended knowledge provider system

Extraction of knowledge data from knowledge database using natural language query is a difficult task. Different types of natural language processing (NLP) techniques have been developed to handle this knowledge data extraction task. This paper proposes an automated query-response model termed Extended Automated Knowledge Provider System (EAKPS) that can manage various types of natural language queries from user. The EAKPS uses combination based technique and it can handle assertive, interrogative, imperative, compound and complex type query sentences. The algorithm of EAKPS generates structure query language (SQL) for each natural language query to extract knowledge data from the knowledge database resident within the EAKPS. Extraction of noun or noun phrases is another issue in natural language query processing. Most of the times, determiner, preposition and conjunction are prefixed to a noun or noun phrase and it is difficult to identify the noun/noun phrase with prefix during query processing. The proposed system is able to identify these prefixes and extract exact noun or noun phrases from natural language queries without any manual intervention.

Knowledge Graph Question and Answer System for Mechanical Intelligent Manufacturing Based on Deep Learning

With the development of deep learning and its wide application in the field of natural language, the question and answer research of knowledge graph based on deep learning has gradually become the focus of attention. After that, the natural language query is converted into a structured query sentence to identify the entities and attributes in the user’s natural language query and the specified entities and attributes are used to retrieve answers to the knowledge graph. Using the advantage of deep learning in capturing sentence information, it incorporates the attention mechanism to obtain the semantic vector of the relevant attributes in the query and uses the parameter sharing mechanism to insert candidate attributes into the triple in the same model to obtain the semantic vector of typical candidates. The experiment measured that under the 100,000 RDF dataset, the single entity query of the MIQE model does not exceed 3 seconds, and the connection query does not exceed 5 seconds. Under the one-million RDF dataset, the single entity query of the MIQE model does not exceed 8 seconds, and the connection query will not be more than 10 seconds. Experimental data show that the system of knowledge-answering questions of engineering of intelligent construction based on deep learning has good horizontal scalability.

Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding.

In this paper, we are tackling the weakly-supervised referring expression grounding task, for the localization of a referent object in an image according to a query sentence, where the mapping between image regions and queries are not available during the training stage. In traditional methods, an object region that best matches the referring expression is picked out, and then the query sentence is reconstructed from the selected region, where the reconstruction difference serves as the loss for back-propagation. The existing methods, however, conduct both the matching and the reconstruction approximately as they ignore the fact that the matching correctness is unknown. To overcome this limitation, a discriminative triad is designed here as the basis to the solution, through which a query can be converted into one or multiple discriminative triads in a very scalable way. Based on the discriminative triad, we further propose the triad-level matching and reconstruction modules which are lightweight yet effective for the weakly-supervised training, making it three times lighter and faster than the previous state-of-the-art methods. One important merit of our work is its superior performance despite the simple and neat design. Specifically, the proposed method achieves a new state-of-the-art accuracy when evaluated on RefCOCO (39.21 percent), RefCOCO+ (39.18 percent) and RefCOCOg (43.24 percent) datasets, that is 4.17, 4.08 and 7.8 percent higher than the previous one, respectively. The code is available at https://github.com/insomnia94/DTWREG.

*Improving Natural Language Queries Search and Retrieval through Semantic Image Annotation Understanding

Retrieving images using detailed natural language queries remains a difficult challenge. Traditional annotation-based image retrieval systems using word matching techniques cannot efficiently support such query types. Significant improvements for this problem can be achieved with a semantic understanding for those query sentences and image annotations. This paper presents a two-stage semantic understanding approach for natural language query sentences. At the first stage, the Stanford parser and a designed rule-based relation extraction tool are used in triple extraction process to efficiently extract the objects attributes, instances and natural language annotations relationships involving these objects. The second stage integrates the extracted relations with external commonsense knowledge source in a mapping process to provide high-level semantic meanings to the extracted triples. Experiments are conducted for evaluating the benefit of the proposed semantic understanding against a testing set of natural language sentences from the Flickr8k dataset. The results show that the proposed approach succeeds to extract relational triples with average accuracy value of 97% for the different types of annotations relationships: attributes and instance relations, multiword dependence relations, and semantic relations.

Coarse-to-Fine Spatial-Temporal Relationship Inference for Temporal Sentence Grounding

Temporal sentence grounding aims to ground a query sentence into a specific segment of the video. Previous methods follow the common equally-spaced frame selection mechanism for appearance and motion modeling, which fails to consider redundant and distracting visual information. There is also no guarantee that all meaningful frames can be obtained. Moreover, this task needs to detect the location clues precisely from both spatial and temporal dimensions, but the relationship between spatial-temporal semantic information and query sentence is still unexplored in existing methods. Inspired by human thinking patterns, we propose a Coarse-to-Fine Spatial-Temporal Relationship Inference (CFSTRI) network to progressively localize fine-grained activity segments. Firstly, we present a coarse-grained crucial frame selection module, where the query-guided local difference context modeling from adjacent frames helps discriminate all the coarse boundary locations relevant to the sentence semantics, and the soft assignment vector of locally aggregated descriptors are employed to enhance the representation of selected frames. Then, we develop a fine-grained spatial-temporal relationship matching module to refine the coarse boundaries, which disentangles the spatial and temporal semantic information from query sentence to guide the excavation of visual grounding clues of corresponding dimensions. Furthermore, we devise a gated graph convolution network to incorporate the spatial-temporal semantic information by leveraging a gate operation to highlight frames referred to by the query sentence from spatial and temporal dimensions, and propagate fused information on the graph. Extensive experiments on two benchmark datasets demonstrate that our CFSTRI significantly outperforms most state-of-the-art methods.

Text-Based Localization of Moments in a Video Corpus.

Prior works on text-based video moment localization focus on temporally grounding the textual query in an untrimmed video. These works assume that the relevant video is already known and attempt to localize the moment on that relevant video only. Different from such works, we relax this assumption and address the task of localizing moments in a corpus of videos for a given sentence query. This task poses a unique challenge as the system is required to perform: 2) retrieval of the relevant video where only a segment of the video corresponds with the queried sentence, 2) temporal localization of moment in the relevant video based on sentence query. Towards overcoming this challenge, we propose Hierarchical Moment Alignment Network (HMAN) which learns an effective joint embedding space for moments and sentences. In addition to learning subtle differences between intra-video moments, HMAN focuses on distinguishing inter-video global semantic concepts based on sentence queries. Qualitative and quantitative results on three benchmark text-based video moment retrieval datasets - Charades-STA, DiDeMo, and ActivityNet Captions - demonstrate that our method achieves promising performance on the proposed task of temporal localization of moments in a corpus of videos.

Multi-Modal Interaction Graph Convolutional Network for Temporal Language Localization in Videos.

This paper focuses on tackling the problem of temporal language localization in videos, which aims to identify the start and end points of a moment described by a natural language sentence in an untrimmed video. However, it is non-trivial since it requires not only the comprehensive understanding of the video and sentence query, but also the accurate semantic correspondence capture between them. Existing efforts are mainly centered on exploring the sequential relation among video clips and query words to reason the video and sentence query, neglecting the other intra-modal relations (e.g., semantic similarity among video clips and syntactic dependency among the query words). Towards this end, in this work, we propose a Multi-modal Interaction Graph Convolutional Network (MIGCN), which jointly explores the complex intra-modal relations and inter-modal interactions residing in the video and sentence query to facilitate the understanding and semantic correspondence capture of the video and sentence query. In addition, we devise an adaptive context-aware localization method, where the context information is taken into the candidate moments and the multi-scale fully connected layers are designed to rank and adjust the boundary of the generated coarse candidate moments with different lengths. Extensive experiments on Charades-STA and ActivityNet datasets demonstrate the promising performance and superior efficiency of our model.

Interaction-Integrated Network for Natural Language Moment Localization.

Natural language moment localization aims at localizing video clips according to a natural language description. The key to this challenging task lies in modeling the relationship between verbal descriptions and visual contents. Existing approaches often sample a number of clips from the video, and individually determine how each of them is related to the query sentence. However, this strategy can fail dramatically, in particular when the query sentence refers to some visual elements that appear outside of, or even are distant from, the target clip. In this paper, we address this issue by designing an Interaction-Integrated Network (I2N), which contains a few Interaction-Integrated Cells (I2Cs). The idea lies in the observation that the query sentence not only provides a description to the video clip, but also contains semantic cues on the structure of the entire video. Based on this, I2Cs go one step beyond modeling short-term contexts in the time domain by encoding long-term video content into every frame feature. By stacking a few I2Cs, the obtained network, I2N, enjoys an improved ability of inference, brought by both (I) multi-level correspondence between vision and language and (II) more accurate cross-modal alignment. When evaluated on a challenging video moment localization dataset named DiDeMo, I2N outperforms the state-of-the-art approach by a clear margin of 1.98%. On other two challenging datasets, Charades-STA and TACoS, I2N also reports competitive performance.

Multi-Perspective Attention Network for Fast Temporal Moment Localization

Temporal moment localization (TML) aims to retrieve the temporal interval for a moment semantically relevant to a sentence query. This is challenging because it requires understanding a video, a sentence, and the relationship between them. Existing TML methods have shown impressive performances by modeling interactions between videos and sentences using fine-grained techniques. However, these fine-grained techniques require a high computational overhead, making them impractical. This work proposes an effective and efficient multi-perspective attention network for temporal moment localization. Inspired by the way humans understand an image from multiple perspectives and different contexts, we devise a novel multi-perspective attention mechanism consisting of perspective attention and multi-perspective modal interactions. Specifically, a perspective attention layer based on multi-head attention takes two memory sequences, one as the base and the other as the reference memory, as inputs. Perspective attention assesses the two different memories, models the relationship, and encourages the base memory to focus on features related to the reference memory, providing an understanding of the base memory from the perspective of the reference memory. Furthermore, multi-perspective modal interactions model the complex relationship between a video and sentence query, and obtain the modal-interacted memory, consisting of a visual feature that selectively learned query-related information. Similar to the heavyweight fine-grained TML methods, the proposed network obtains the accurate complex relationship while being lightweight like coarse-grained TML methods. We also adopt a fast action recognition network to efficiently extract visual features, which reduce the computational overhead. Through experiments on three TML benchmark datasets, we demonstrate the effectiveness and efficiency of the proposed network.

SEA: Sentence Encoder Assembly for Video Retrieval by Textual Queries

Retrieving unlabeled videos by textual queries, known as Ad-hoc Video Search (AVS), is a core theme in multimedia data management and retrieval. The success of AVS counts on cross-modal representation learning that encodes both query sentences and videos into common spaces for semantic similarity computation. Inspired by the initial success of previously few works in combining multiple sentence encoders, this paper takes a step forward by developing a new and general method for effectively exploiting diverse sentence encoders. The novelty of the proposed method, which we term <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sentence Encoder Assembly</i> (SEA), is two-fold. First, different from prior art that uses only a single common space, SEA supports text-video matching in multiple encoder-specific common spaces. Such a property prevents the matching from being dominated by a specific encoder that produces an encoding vector much longer than other encoders. Second, in order to explore complementarities among the individual common spaces, we propose multi-space multi-loss learning. As extensive experiments on four benchmarks (MSR-VTT, TRECVID AVS 2016-2019, TGIF and MSVD) show, SEA surpasses the state-of-the-art. In addition, SEA is extremely ease to implement. All this makes SEA an appealing solution for AVS and promising for continuously advancing the task by harvesting new sentence encoders.

Story-driven Video Editing

This paper proposes a novel multimedia task: story-driven video editing. Given a story paragraph, this task aims to retrieve related video segments from a gallery of collected video segments and compose them into a video sequence by the storyline order. Our proposed baseline solution consists of three modules: a retrieval module, which returns lists of candidate segments for all query sentences in the story paragraph using an object-aware sentence-segment matching method; a sequence candidate proposal module, which aggregates the retrieved segment sets into a sequence proposal by the submodular optimization method; a sorting module, which arranges the candidates according to the storyline of the paragraph using the Sinkhorn network. We build a benchmark for this task including a reorganized version of the ActivityNet Captions dataset, a well-defined quantitative metric called Evaluation of Segment-to-Sequence Matching (ESSM) for measuring the difference between the generated video segment sequence and the ground truth. Quantitative results of the proposed baseline solution are reported. We hope this new task and benchmark will bring broad research attention and push forward a lot of novel online short video editing applications.

Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language

We address the problem of retrieving a specific moment from an untrimmed video by a query sentence. This is a challenging problem because a target moment may take place in relations to other temporal moments in the untrimmed video. Existing methods cannot tackle this challenge well since they consider temporal moments individually and neglect the temporal dependencies. In this paper, we model the temporal relations between video moments by a two-dimensional map, where one dimension indicates the starting time of a moment and the other indicates the end time. This 2D temporal map can cover diverse video moments with different lengths, while representing their adjacent relations. Based on the 2D map, we propose a Temporal Adjacent Network (2D-TAN), a single-shot framework for moment localization. It is capable of encoding the adjacent temporal relation, while learning discriminative features for matching video moments with referring expressions. We evaluate the proposed 2D-TAN on three challenging benchmarks, i.e., Charades-STA, ActivityNet Captions, and TACoS, where our 2D-TAN outperforms the state-of-the-art.

Scalable Attentive Sentence Pair Modeling via Distilled Sentence Embedding

Recent state-of-the-art natural language understanding models, such as BERT and XLNet, score a pair of sentences (A and B) using multiple cross-attention operations – a process in which each word in sentence A attends to all words in sentence B and vice versa. As a result, computing the similarity between a query sentence and a set of candidate sentences, requires the propagation of all query-candidate sentence-pairs throughout a stack of cross-attention layers. This exhaustive process becomes computationally prohibitive when the number of candidate sentences is large. In contrast, sentence embedding techniques learn a sentence-to-vector mapping and compute the similarity between the sentence vectors via simple elementary operations. In this paper, we introduce Distilled Sentence Embedding (DSE) – a model that is based on knowledge distillation from cross-attentive models, focusing on sentence-pair tasks. The outline of DSE is as follows: Given a cross-attentive teacher model (e.g. a fine-tuned BERT), we train a sentence embedding based student model to reconstruct the sentence-pair scores obtained by the teacher model. We empirically demonstrate the effectiveness of DSE on five GLUE sentence-pair tasks. DSE significantly outperforms several ELMO variants and other sentence embedding methods, while accelerating computation of the query-candidate sentence-pairs similarities by several orders of magnitude, with an average relative degradation of 4.6% compared to BERT. Furthermore, we show that DSE produces sentence embeddings that reach state-of-the-art performance on universal sentence representation benchmarks. Our code is made publicly available at https://github.com/microsoft/Distilled-Sentence-Embedding.

Probabilistic sentence satisfiability: An approach to PSAT

Information analysis often involves heterogeneous sources expressed as logical sentences, numerical models, sensor data, etc. Each of these has its own way to describe uncertainty or error; e.g., frequency analysis, algorithmic truncation, floating point roundoff, Gaussian distributions, etc. A unifying framework is proposed here to represent this information as logical sentences with associated probabilities in order to allow the inference of the probability of a query sentence.Given such a knowledge base in Conjunctive Normal Form (CNF) for use by an intelligent agent, with probabilities assigned to the conjuncts, the probability of any new query sentence can be determined by solving the Probabilistic Satisfiability Problem (PSAT). This involves finding a consistent probability distribution over the atoms (if they are independent) or complete conjunction set of the atoms. For each sentence in the knowledge base, we propose to produce an equation in terms of atoms and conditional probabilities. This system of equations is then solved numerically to get a solution consistent with the sentence probabilities. Finding such a solution is called the Probabilistic Sentence Satisfiability (PS-SAT) problem. In particular, findings include:1.For independent logical variables:(a)atom probabilities which solve PS-SAT also provide a PSAT solution.(b)numerical experiments demonstrate a q-superlinear convergence rate for most test cases.(c)problems with up to 1,000 variables and 300 sentences are solved.2.For general knowledge bases (i.e., variables not independent):(a)both atom and a subset of conditional probabilities must be found,(b)a solution to PS-SAT does not guarantee a solution to PSAT, but most empirical results provide such a solution.(c)The convergence rate for equations with non-independent variables also appears q-superlinear.

Indonesian Text Translator into Database Structured Query Language with Multi Parameters using Natural Language Processing

In this paper, we present the results of our research on SQL (Structured Query Language) Translator in Indonesian which aims to measure how accurate the designed system in understanding query sentences in Indonesian into SQL query languages. The methods used include pre-processing sentences, stemming, identifying keywords, until the final evaluation of sentences. We prepared 18 sentences divided into several categories as test data. The test results show that the system successfully evaluates all sentences with a total accuracy of 72.22% to 83.87%. Accuracy values were obtained by comparing similarities between systems generated queries and key answers query. In general, the system has been able to translate most of the Indonesian sentences into SQL queries.

Sugarcane ORF finder: the web-application for mining genes from sugarcane genome

Sugarcane is one of the most important multi-purpose crops that are native to tropical regions. As commercial sugarcane is an interspecific hybrid between Saccharum officianarum and Saccharum spontaneum, the genome size of sugarcane has been reported around 10 Gbase. From this reason, it has been hard to build the reference level assembly resulting in partial contigs. With the advance of third generation sequencers and assembly strategies, recently, two sugarcane genome assemblies were published representing monoploidy of sugarcane cultivar and whole genome of S. spontaneum. Synergetically, the genome-editing technology is advanced that can eventually facilitate the sugarcane breeding and the necessity of utilizing genome sequence is also arising for sugarcane researchers to find guide-RNA binding site by the machine learning algorithms or human inspection. Here, we built web-application for the researchers to find the open reading frame (ORF) of sugarcane genes easily with a query gene ID and catalog candidate gene list by query sentences (http://pgl.gnu.ac.kr/sugarcane_orf_finder/). This enables the researchers to find their genes of interest and directly observe the ORF structure of the query gene and design precise guide RNA for genome editing.

SLTFNet: A spatial and language-temporal tensor fusion network for video moment retrieval

This paper focuses on temporal retrieval of activities in videos via sentence queries. Given a sentence query describing an activity, temporal moment retrieval aims at localizing the temporal segment within the video that best describes the textual query. This is a general yet challenging task as it requires the comprehending of both video and language. Existing research predominantly employ coarse frame-level features as the visual representation, obfuscating the specific details (e.g., the desired objects “girl”, “cup” and action “pour”) within the video which may provide critical cues for localizing the desired moment. In this paper, we propose a novel Spatial and Language-Temporal Tensor Fusion (SLTF) approach to resolve those issues. Specifically, the SLTF method first takes advantage of object-level local features and attends to the most relevant local features (e.g., the local features “girl”, “cup”) by spatial attention. Then we encode the sequence of the local features on consecutive frames by employing LSTM network, which can capture the motion information and interactions among these objects (e.g., the interaction “pour” involving these two objects). Meanwhile, language-temporal attention is utilized to emphasize the keywords based on moment context information. Thereafter, a tensor fusion network learns both the intra-modality and inter-modality dynamics, which can enhance the learning of moment-query representation. Therefore, our proposed two attention sub-networks can adaptively recognize the most relevant objects and interactions in the video, and simultaneously highlight the keywords in the query for retrieving the desired moment. Experimental results on three public benchmark datasets (obtained from TACOS, Charades-STA, and DiDeMo) show that the SLTF model significantly outperforms current state-of-the-art approaches, and demonstrate the benefits produced by new technologies incorporated into SLTF.

Semantic Proposal for Activity Localization in Videos via Sentence Query

This paper presents an efficient algorithm to tackle temporal localization of activities in videos via sentence queries. The task differs from traditional action localization in three aspects: (1) Activities are combinations of various kinds of actions and may span a long period of time. (2) Sentence queries are not limited to a predefined list of classes. (3) The videos usually contain multiple different activity instances. Traditional proposal-based approaches for action localization that only consider the class-agnostic “actionness” of video snippets are insufficient to tackle this task. We propose a novel Semantic Activity Proposal (SAP) which integrates the semantic information of sentence queries into the proposal generation process to get discriminative activity proposals. Visual and semantic information are jointly utilized for proposal ranking and refinement. We evaluate our algorithm on the TACoS dataset and the Charades-STA dataset. Experimental results show that our algorithm outperforms existing methods on both datasets, and at the same time reduces the number of proposals by a factor of at least 10.