Query Intent Research Articles

A Novel IR for Relational Database using Optimize Query Building

The different type search engine like Google, binge, AltaVista is used to fetch the information from the database by easy language. The non-technical employee they don’t understand the database and query cannot access the database. The proposed system is performing work as a search engine where users can fetch the information from the database by natural human sounding language. The previous existing system doesn’t able to solve queries in one easy statement. The structured query approach, while expressive and powerful, is not easy for naive users. The keyword-based approach is very friendly to use, but cannot express complex query intent accurately. This paper emphasis on Natural Language based query processor. We have proposed the use of query optimization approach to convert complex NLP query to SQL query, SPAM word removal, POS tagger applied over NL query and concluded that execution time lesser when query size increases.

FANDA: A Novel Approach to Perform Follow-Up Query Analysis

Recent work on Natural Language Interfaces to Databases (NLIDB) has attracted considerable attention. NLIDB allow users to search databases using natural language instead of SQL-like query languages. While saving the users from having to learn query languages, multi-turn interaction with NLIDB usually involves multiple queries where contextual information is vital to understand the users’ query intents. In this paper, we address a typical contextual understanding problem, termed as follow-up query analysis. In spite of its ubiquity, follow-up query analysis has not been well studied due to two primary obstacles: the multifarious nature of follow-up query scenarios and the lack of high-quality datasets. Our work summarizes typical follow-up query scenarios and provides a new FollowUp dataset with 1000 query triples on 120 tables. Moreover, we propose a novel approach FANDA, which takes into account the structures of queries and employs a ranking model with weakly supervised max-margin learning. The experimental results on FollowUp demonstrate the superiority of FANDA over multiple baselines across multiple metrics.

A Hybrid Spoken Language Processing System for Smart Device Troubleshooting

The purpose of this work is to develop a spoken language processing system for smart device troubleshooting using human-machine interaction. This system combines a software Bidirectional Long Short Term Memory Cell (BLSTM)-based speech recognizer and a hardware LSTM-based language processor for Natural Language Processing (NLP) using the serial RS232 interface. Mel Frequency Cepstral Coefficient (MFCC)-based feature vectors from the speech signal are directly input into a BLSTM network. A dropout layer is added to the BLSTM layer to reduce over-fitting and improve robustness. The speech recognition component is a combination of an acoustic modeler, pronunciation dictionary, and a BLSTM network for generating query text, and executes in real time with an 81.5% Word Error Rate (WER) and average training time of 45 s. The language processor comprises a vectorizer, lookup dictionary, key encoder, Long Short Term Memory Cell (LSTM)-based training and prediction network, and dialogue manager, and transforms query intent to generate response text with a processing time of 0.59 s, 5% hardware utilization, and an F1 score of 95.2%. The proposed system has a 4.17% decrease in accuracy compared with existing systems. The existing systems use parallel processing and high-speed cache memories to perform additional training, which improves the accuracy. However, the performance of the language processor has a 36.7% decrease in processing time and 50% decrease in hardware utilization, making it suitable for troubleshooting smart devices.

A hybrid deep neural network model for query intent classification

A hybrid deep neural network model for query intent classification

Semantic locality‐based approximate knowledge graph query

SummaryRDF knowledge graphs (KG) usually contain billions of labeled entities, and how to obtain the desired results efficiently on RDF KG for given SPARQL queries have attracted increasing attentions recently. However, it is difficult for users to write a complex SPARQL query without full knowledge of the underlying KG schema due to the “schema‐free” feature of RDF KG. In this paper, we study the problem of acquiring semantic approximate results for a simple SPARQL query instead of the complex expression. The basic idea behind is to use the real knowledge semantics to extend the query intention of given simplified SPARQL query, and then a semantic based greedy search over is designed to return top‐k similar results. To obtain the knowledge semantics efficiently, we define type similarity to reorganize the original KG as a corpus with semantic locality and then a context aware text embedding model is adopted to achieve the semantic vectors of existing knowledge. Afterwards, an approximate query method over RDF KG is designed to obtain top‐k similar results based on the knowledge semantics above. Extensive experiments over DBpedia dataset and QALD‐4 benchmark confirm our solution's superiority on both effectiveness and efficiency.

Saliency Inside: Learning Attentive CNNs for Content-based Image Retrieval.

In content-based image retrieval (CBIR), one of the most challenging and ambiguous tasks are to correctly understand the human query intention and measure its semantic relevance with images in the database. Due to the impressive capability of visual saliency in predicting human visual attention that is closely related to the query intention, this paper attempts to explicitly discover the essential effect of visual saliency in CBIR via qualitative and quantitative experiments. Toward this end, we first generate the fixation density maps of images from a widely used CBIR dataset by using an eye-tracking apparatus. These ground-truth saliency maps are then used to measure the influence of visual saliency to the task of CBIR by exploring several probable ways of incorporating such saliency cues into the retrieval process. We find that visual saliency is indeed beneficial to the CBIR task, and the best saliency involving scheme is possibly different for different image retrieval models. Inspired by the findings, this paper presents two-stream attentive CNNs with saliency embedded inside for CBIR. The proposed network has two streams that simultaneously handle two tasks. The main stream focuses on extracting discriminative visual features that are tightly related to semantic attributes. Meanwhile, the auxiliary stream aims to facilitate the main stream by redirecting the feature extraction to the salient image content that human may pay attention to. By fusing these two streams into the Main and Auxiliary CNNs (MAC), image similarity can be computed as the human being does by reserving conspicuous content and suppressing irrelevant regions. Extensive experiments show that the proposed model achieves impressive performance in image retrieval on four public datasets.

An Efficient Top-$K$ Spatial Keyword Typicality and Semantic Query

Existing spatial keyword query processing models mainly consider the spatial proximity and text relevancy between spatial objects and spatial keyword query, which usually makes the top- k answer objects are similar to each other. However, the user hopes to obtain the top- k results that are typical and semantically related to his/her query intention. This paper proposes a top- k spatial keyword typicality and sematic querying approach which can expeditiously provide top- k typical and semantically related objects to the given query. The approach consists of two processing steps. During the offline step, we first analyze the location-semantic relationships between spatial objects by considering both the location similarity and document semantic relevancy between them. For measuring the semantic similarity between documents associated to the spatial objects, we propose two methods, the keyword coupling relationship-based document similarity measure and the Word2Vec-CNN-based document similarity measure. Then, the Gaussian probabilistic density-based estimation method is leveraged to find a few representative objects from the dataset and then the order/permutation of remaining objects in the dataset can be generated corresponding to each representative object. The objects in the permutation are ranked in descending order according to their location-semantic relationships to the representative object. When a spatial keyword query coming, the online processing step first computes the spatial proximity and semantic relevancy between the query and each representative object, and then a small number of orders generated in the offline step can be selected and used at querying time to facilitate top- k typical and semantically related object selection by using the threshold algorithm (TA). Results of a preliminary user study demonstrate our location-semantic relationship measuring method can capture the location similarity and semantic relevancy between spatial objects accurately. The efficiency of typicality analysis and TA-based top- k selection algorithm is also demonstrated.

Query Recommendation Using Hybrid Query Relevance

With the explosion of web information, search engines have become main tools in information retrieval. However, most queries submitted in web search are ambiguous and multifaceted. Understanding the queries and mining query intention is critical for search engines. In this paper, we present a novel query recommendation algorithm by combining query information and URL information which can get wide and accurate query relevance. The calculation of query relevance is based on query information by query co-concurrence and query embedding vector. Adding the ranking to query-URL pairs can calculate the strength between query and URL more precisely. Empirical experiments are performed based on AOL log. The results demonstrate the effectiveness of our proposed query recommendation algorithm, which achieves superior performance compared to other algorithms.

A view-based 3D CAD model reuse framework enabling product lifecycle reuse

3D CAD models have great significances for product lifecycle reuse as each model aggregates abundant knowledge in a vivid 3D CAD model and enables engineers to reuse the existing mature designs from a high-level perspective. The effective reuse of the pre-existing 3D CAD models could greatly save time and cost in new product development. Consequently, this paper proposes a novel view-based 3D CAD model reuse framework, which supports the effective reuse of 3D CAD models throughout the new product lifecycle by a deep learning approach. In this framework, each 3D CAD model is first represented by a series of orthogonal two-dimensional views, which contain rich spatial information for differentiating 3D CAD models. Then, we define the problem of model retrieval as a view recognition problem, where a deep residual network (ResNet) is successfully trained to facilitate the view-based 3D CAD model retrieval. With the learned ResNet, engineers could take the understandable views of a model that represent their query intents as input and acquire the relevant 3D CAD models for product lifecycle reuse. Finally, the typical application scenario demonstrates the feasibility of the proposed framework, and the evaluation experiments show the superiorities of ResNet used in this framework.

Query-aware sparse coding for web multi-video summarization

Given the explosive growth of online videos, it is becoming increasingly important to relieve the tedious work of browsing and managing the video content of interest. Video summarization aims at providing such a technique by transforming one or multiple videos into a compact one. However, conventional multi-video summarization methods often fail to produce satisfying results as they ignore the users’ search intents. To this end, this paper proposes a novel query-aware approach by formulating the multi-video summarization in a sparse coding framework, where the web images searched by a query are taken as the important preference information to reveal the query intent. To provide a user-friendly summarization, this paper also develops an event-keyframe presentation structure to present keyframes in groups of specific events related to the query by using an unsupervised multi-graph fusion method. Moreover, we release a new public dataset named MVS1K, which contains about 1000 videos from 10 queries and their video tags, manual annotations, and associated web images. Extensive experiments on the MVS1K and TVSum datasets demonstrate that our approaches produce competitively objective and subjective results.

Semantic composition of distributed representations for query subtopic mining

Inferring query intent is significant in information retrieval tasks. Query subtopic mining aims to find possible subtopics for a given query to represent potential intents. Subtopic mining is challenging due to the nature of short queries. Learning distributed representations or sequences of words has been developed recently and quickly, making great impacts on many fields. It is still not clear whether distributed representations are effective in alleviating the challenges of query subtopic mining. In this paper, we exploit and compare the main semantic composition of distributed representations for query subtopic mining. Specifically, we focus on two types of distributed representations: paragraph vector which represents word sequences with an arbitrary length directly, and word vector composition. We thoroughly investigate the impacts of semantic composition strategies and the types of data for learning distributed representations. Experiments were conducted on a public dataset offered by the National Institute of Informatics Testbeds and Community for Information Access Research. The empirical results show that distributed semantic representations can achieve outstanding performance for query subtopic mining, compared with traditional semantic representations. More insights are reported as well.

Supervised Search Result Diversification via Subtopic Attention

Search result diversification aims to retrieve diverse results to satisfy as many different information needs as possible. Supervised methods have been proposed recently to learn ranking functions and they have been shown to produce superior results to unsupervised methods. However, these methods use implicit approaches based on the principle of Maximal Marginal Relevance (MMR). In this paper, we propose a learning framework for explicit result diversification where subtopics are explicitly modeled. Based on the information contained in the sequence of selected documents, we use the attention mechanism to capture the subtopics to be focused on while selecting the next document, which naturally fits our task of document selection for diversification. As a preliminary attempt, we employ recurrent neural networks and max pooling to instantiate the framework. We use both distributed representations and traditional relevance features to model documents in the implementation. The framework is flexible to model query intent in either a flat list or a hierarchy. Experimental results show that the proposed method significantly outperforms all the existing search result diversification approaches.

Search result diversification on attributed networks via nonnegative matrix factorization

Search result diversification is an effective way to tackle query ambiguity and enhance result novelty. In the context of large information networks, diversifying search result is also critical for further design of applications such as link prediction and citation recommendation. In previous work, this problem has mainly been tackled in a way of implicit query intent. To further enhance the performance on attributed networks, we propose a novel search result diversification approach via nonnegative matrix factorization. Our approach encodes latent query intents as well as nodes as representation vectors by a novel nonnegative matrix factorization model, and the diversity of the results accounts for the query relevance and the novelty w.r.t. these vectors. To learn the representation vectors of nodes, we derive the multiplicative updating rules to train the nonnegative matrix factorization model. We perform a comprehensive evaluation on our approach with various baselines. The results show the effectiveness of our proposed solution, and verify that attributes do help improve diversification performance.

Answering Natural Language Questions by Subgraph Matching over Knowledge Graphs

RDF question/answering (Q/A) allows users to ask questions in natural languages over a knowledge base represented by RDF. To answer a natural language question, the existing work takes a two-stage approach: question understanding and query evaluation. Their focus is on question understanding to deal with the disambiguation of the natural language phrases. The most common technique is the joint disambiguation, which has the exponential search space. In this paper, we propose a systematic framework to answer natural language questions over RDF repository (RDF Q/A) from a graph data-driven perspective. We propose a semantic query graph to model the query intention in the natural language question in a structural way, based on which, RDF Q/A is reduced to subgraph matching problem. More importantly, we resolve the ambiguity of natural language questions at the time when matches of query are found. The cost of disambiguation is saved if there are no matching found. More specifically, we propose two different frameworks to build the semantic query graph, one is relation (edge)-first and the other one is node-first. We compare our method with some state-of-the-art RDF Q/A systems in the benchmark dataset. Extensive experiments confirm that our method not only improves the precision but also speeds up query performance greatly.

Natural language aggregate query over RDF data

Natural language question/answering over RDF (Resource Description Framework) data has received widespread attention. Although several studies can address a small number of aggregate queries, these studies have many restrictions (e.g., interactive information, controlled questions or query templates). Thus far, there has been no natural language querying mechanism that can process general aggregate queries over RDF data. Therefore, we propose a framework called NLAQ (Natural Language Aggregate Query). First, we propose a novel algorithm to automatically understand a user's query intention, which primarily contains semantic relations and aggregations. Second, to build a better bridge between the query intention and RDF data, we propose an extended paraphrase dictionary ED to obtain more candidate mappings for semantic relations, and we introduce a predicate-type adjacent set PT to filter out inappropriate candidate mapping combinations in semantic relations and basic graph patterns. Third, we design a suitable translation plan for each aggregate category and effectively distinguish whether an aggregate item is numeric, which will greatly affect the aggregate result. Finally, we conduct extensive experiments over real datasets (QALD benchmark and DBpedia). The experimental results demonstrate that our solution is effective.

Query Auto-Completion Based on Word2vec Semantic Similarity

Query auto-completion (QAC) is the first step of information retrieval, which helps users formulate the entire query after inputting only a few prefixes. Regarding the models of QAC, the traditional method ignores the contribution from the semantic relevance between queries. However, similar queries always express extremely similar search intention. In this paper, we propose a hybrid model FS-QAC based on query semantic similarity as well as the query frequency. We choose word2vec method to measure the semantic similarity between intended queries and pre-submitted queries. By combining both features, our experiments show that FS-QAC model improves the performance when predicting the user’s query intention and helping formulate the right query. Our experimental results show that the optimal hybrid model contributes to a 7.54% improvement in terms of MRR against a state-of-the-art baseline using the public AOL query logs.

Query Intent Recognition Based on Multi-Class Features

In order to enhance the user search experience of the search engine, an intent recognition search based on natural language input is proposed. By using reality mining technology to obtain the potential consciousness information from the query expression, search engines can better predict the query results that meet users’ requirements. With the development of conventional machine learning and deep learning, it is possible to further improve the accuracy of prediction results. This paper adopts a similarity calculation method based on long short-term memory (LSTM) and a traditional machine learning method based on multi-feature extraction. It is found that entity features can significantly improve the accuracy of intention classification. Second, the accuracy of intention classification based on the feature sequence constructed by key entities is up to 94.16% in the field of manual labeling by using the BiLSTM classification model.

Scalable Aspects Learning for Intent-Aware Diversified Search on Social Networks

Search result diversification on networks aims at selecting a set of representative nodes in response to a given query node so that the result is able to meet users’ ambiguous query intents. Previous work mainly tackles this problem based on global diversity metrics, such as the expansion ratio and the expanded relevance, according to which the potential diversity needs of different query are interpreted as an unchanged criterion. While with various side information in real-world social networks, the intents of users often have more than one interpretation underlying the same query. In this paper, we therefore adopt an intent-aware perspective on this problem, based on network representation learning. With the hypothesis that a search result being aware of multiple intents of query is more likely to satisfy the information needs of users, we propose an intent-aware method that first encodes the possible query aspects and nodes as vectors, and then diversifies the search result based on these vectors. In particular, we present aspect2vec , a scalable and flexible network representation learning model, which maps nodes into low-dimensional vector spaces while preserving the network structure, the node attribute, and the query-oriented proximity. An attribute augmented sampling approach is proposed to sample corpus for the three contexts to train the model. Finally, we perform a comprehensive evaluation on our method with various baselines. The results show that our proposed method outperforms the state-of-the-art diversification algorithms.

Deep Bi-Directional LSTM Network for Query Intent Detection

Detecting the user intentions encoded in text queries is a pivotal task in many natural language processing application like search engines, personal assistants, smart agents, and robots. Previous works have explored the use of various machine learning algorithms for the task of intent detection from user queries. In this work, we are proposing a deep learning based framework using Bi-Directional Long Short-Term Memory (BLSTM) Networks for intent identification. The proposed model takes word embeddings as input and learns useful features for identifying the possible intentions of a user query. Instead of directly using word embeddings generated using GloVe Model for training the model, a semantically enriched set of embeddings are used to ensure semantic correctness of word embeddings. The evaluation results on ATIS dataset shows that semantic enrichment and proposed deep learning model improves the results of intent detection.

Semantic query graph based SPARQL generation from natural language questions

In order to precisely represent natural language questions (NLQs) in question answering system (QAS) and provide a more naturally interactive mode, we require SPARQL, a formalized query patterns, instead of search expression to express the user’s semantic query intention. However, how to generate and evaluate SPARQL query from NLQ is a mostly open research question. In this paper, we propose a framework that can help users translating NLQ into well-formed queries for knowledge based systems. We define a new graph structure, semantic query graph, and vocabulary to match all kinds of complex and compound questions without using domain ontology. Through query expansion and semantic query graph generation, the framework resembles subgraphs of the knowledge base and can be directly mapped to a logical form. Extensive experiments over NLQ in real RDF QASs verify the feasibility and efficiency of semantic query graph and our proposed framework with average F-measure of 0.825.