Ambiguous Queries Research Articles

Personalized and Diversified: Ranking Search Results in an Integrated Way

Ambiguity in queries is a common problem in information retrieval. There are currently two solutions: search result personalization and diversification. The former aims to tailor results for different users based on their preferences, but the limitations are redundant results and incomplete capture of user intents. The goal of the latter is to return results that cover as many aspects related to the query as possible. It improves diversity yet loses personality and cannot return the exact results the user wants. Intuitively, such two solutions can complement each other and bring more satisfactory reranking results. In this article, we propose a novel framework, namely, PnD , to integrate personalization and diversification reasonably. We employ the degree of refinding to determine the weight of personalization dynamically. Moreover, to improve the diversity and relevance of reranked results simultaneously, we design a reset RNN structure (RRNN) with the “reset gate” to measure the influence of the newly selected document on novelty. Besides, we devise a “subtopic learning layer” to learn the virtual subtopics, which can yield fine-grained representations of queries, documents, and user profiles. Experimental results illustrate that our model can significantly outperform existing search result personalization and diversification methods.

Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions Over Knowledge Graphs

Query graph construction aims to construct the correct executable SPARQL on the KG to answer natural language questions. Although recent methods have achieved good results using neural network-based query graph ranking, they suffer from three new challenges when handling more complex questions: 1) complicated SPARQL syntax, 2) huge search space, and 3) locally ambiguous query graphs. In this paper, we provide a new solution. As a preparation, we extend the query graph by treating each SPARQL clause as a subgraph consisting of vertices and edges and define a unified graph grammar called AQG to describe the structure of query graphs. Based on these concepts, we propose a novel end-to-end model that performs hierarchical autoregressive decoding to generate query graphs. The high-level decoding generates an AQG as a constraint to prune the search space and reduce the locally ambiguous query graph. The bottom-level decoding accomplishes the query graph construction by selecting appropriate instances from the preprepared candidates to fill the slots in the AQG. The experimental results show that our method greatly improves the SOTA performance on complex KGQA benchmarks. Equipped with pre-trained models, the performance of our method is further improved, achieving SOTA for all three datasets used.

A Hybrid Text Generation-Based Query Expansion Method for Open-Domain Question Answering

In the two-stage open-domain question answering (OpenQA) systems, the retriever identifies a subset of relevant passages, which the reader then uses to extract or generate answers. However, the performance of OpenQA systems is often hindered by issues such as short and semantically ambiguous queries, making it challenging for the retriever to find relevant passages quickly. This paper introduces Hybrid Text Generation-Based Query Expansion (HTGQE), an effective method to improve retrieval efficiency. HTGQE combines large language models with Pseudo-Relevance Feedback techniques to enhance the input for generative models, improving text generation speed and quality. Building on this foundation, HTGQE employs multiple query expansion generators, each trained to provide query expansion contexts from distinct perspectives. This enables the retriever to explore relevant passages from various angles for complementary retrieval results. As a result, under an extractive and generative QA setup, HTGQE achieves promising results on both Natural Questions (NQ) and TriviaQA (Trivia) datasets for passage retrieval and reading tasks.

How to Approach Ambiguous Queries in Conversational Search: A Survey of Techniques, Approaches, Tools, and Challenges

The advent of recent Natural Language Processing technology has led human and machine interactions more toward conversation. In Conversational Search Systems (CSS) like chatbots and Virtual Personal Assistants such as Apple’s Siri, Amazon Alexa, Microsoft’s Cortana, and Google Assistant, both user and device have a limited platform to communicate through chatting or voice. In the information-seeking process, often users do not know how to properly describe their information need in a machine understandable language. Consequently, it is hard for the assistant agent to predict the user’s intent and yield relevant results by only relying on the original query. Studies have shown many unsatisfactory results can be enhanced with the benefit of CSS, which can dig deeper into the user’s query to reveal the real need. This survey intends to provide a comprehensive and comparative overview of ambiguous query clarification task in the context of conversational search technology. We investigate different approaches, their evaluation methods, and future work. We also address the importance of understanding a query for retrieving the most relevant document(s) and satisfying user’s need by predicting their potential request. This work provides an overview of characteristics of ambiguous queries and contributes to better understanding of the existing technologies and challenges in CSS focus on disambiguation of unclear queries from various dimensions.

A Fuzzy Query Method Oriented to Knowledge Graph

With the widespread application of Knowledge Graphs, Knowledge Graph query technology has received widespread attention. The daily use of natural language usually contains fuzzy terms. The use of fuzzy terms in queries is more in line with natural language habits. Therefore, fuzzy questions have been widely discussed and applied in relational data models, and their use in NoSQL data models has also begun to be affected in recent years. RDF (Resource Description Framework) is a representative model of the knowledge graph, and SPARQL is the standard query language of RDF. To realize the fuzzy query of the knowledge graph, this paper introduces the unclear expansion syntax of aggregate function based on summarizing and analyzing the existing SPARQL fuzzy expansion. Supplements the qualitative preference analysis method then proposes and SPARQL1. 1 Corresponding fuzzy SPARQL1.1 (f-SPARQL1.1) simultaneously provides strategies and techniques for rewriting ambiguous queries into classic SPARQL queries. In addition, this article also provides a visual interface for defining the membership functions of fuzzy terms and provides three interactive methods for setting fuzzy membership functions. Compared with the previous fuzzy query methods for RDF models, the method proposed in this paper has more vital fuzzy query ability and more flexible universality. The experimental results show the usability of the method proposed in this paper.

Interactive Re-ranking via Object Entropy-Guided Question Answering for Cross-Modal Image Retrieval

Cross-modal image-retrieval methods retrieve desired images from a query text by learning relationships between texts and images. Such a retrieval approach is one of the most effective ways of achieving the easiness of query preparation. Recent cross-modal image-retrieval methods are convenient and accurate when users input a query text that can be used to uniquely identify the desired image. However, in reality, users frequently input ambiguous query texts, and these ambiguous queries make it difficult to obtain desired images. To overcome these difficulties, in this study, we propose a novel interactive cross-modal image-retrieval method based on question answering. The proposed method analyzes candidate images and asks users questions to obtain information that can narrow down retrieval candidates. By only answering questions generated by the proposed method, users can reach their desired images, even when using an ambiguous query text. Experimental results show the proposed method’s effectiveness.

Systematic Literature Review of Web Search Personalization

The existing studies have already revealed that the information on the web is increasing rapidly. Ambiguous queries and users’ ability to express their intention through queries have been one of the key challenges in retrieving accurate search results from the search engine. This paper in response explored different methodologies proposed during 2005-2019 by the eminent researchers for obtaining better search results. Some of these methodologies are based on the users’ geographical location while others rely on re-ranking the web results and refinement of the users’ queries. Fellow researchers can use this literature to define the fundamental literature of their work. Furthermore, a brief case study of major search engines like Google, Yahoo, Bing, etc. along with the techniques used by these search engines for personalization is also discussed. Finally, the paper discusses some current issues and challenges related to personalization which further defines the future research directions.

Query bot for retrieving patients’ clinical history: A COVID-19 use-case

ObjectiveWith increasing patient complexity whose data are stored in fragmented health information systems, automated and time-efficient ways of gathering important information from the patients' medical history are needed for effective clinical decision making. Using COVID-19 as a case study, we developed a query-bot information retrieval system with user-feedback to allow clinicians to ask natural questions to retrieve data from patient notes. Materials and methodsWe applied clinicalBERT, a pre-trained contextual language model, to our dataset of patient notes to obtain sentence embeddings, using K-Means to reduce computation time for real-time interaction. Rocchio algorithm was then employed to incorporate user-feedback and improve retrieval performance. ResultsIn an iterative feedback loop experiment, MAP for final iteration was 0.93/0.94 as compared to initial MAP of 0.66/0.52 for generic and 1./1. compared to 0.79/0.83 for COVID-19 specific queries confirming that contextual model handles the ambiguity in natural language queries and feedback helps to improve retrieval performance. User-in-loop experiment also outperformed the automated pseudo relevance feedback method. Moreover, the null hypothesis which assumes identical precision between initial retrieval and relevance feedback was rejected with high statistical significance (p ≪ 0.05). Compared to Word2Vec, TF-IDF and bioBERT models, clinicalBERT works optimally considering the balance between response precision and user-feedback. DiscussionOur model works well for generic as well as COVID-19 specific queries. However, some generic queries are not answered as well as others because clustering reduces query performance and vague relations between queries and sentences are considered non-relevant. We also tested our model for queries with the same meaning but different expressions and demonstrated that these query variations yielded similar performance after incorporation of user-feedback. ConclusionIn conclusion, we develop an NLP-based query-bot that handles synonyms and natural language ambiguity in order to retrieve relevant information from the patient chart. User-feedback is critical to improve model performance.

Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting

Conversational search plays a vital role in conversational information seeking. As queries in information seeking dialogues are ambiguous for traditional ad hoc information retrieval (IR) systems due to the coreference and omission resolution problems inherent in natural language dialogue, resolving these ambiguities is crucial. In this article, we tackle conversational passage retrieval, an important component of conversational search, by addressing query ambiguities with query reformulation integrated into a multi-stage ad hoc IR system. Specifically, we propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting. For the former, we expand conversational queries using important terms extracted from the conversational context with frequency-based signals. For the latter, we reformulate conversational queries into natural, stand-alone, human-understandable queries with a pretrained sequence-to-sequence model. Detailed analyses of the two CQR methods are provided quantitatively and qualitatively, explaining their advantages, disadvantages, and distinct behaviors. Moreover, to leverage the strengths of both CQR methods, we propose combining their output with reciprocal rank fusion, yielding state-of-the-art retrieval effectiveness, 30% improvement in terms of NDCG@3 compared to the best submission of Text REtrieval Conference (TREC) Conversational Assistant Track (CAsT) 2019.

A fuzzy logic‐based approach for fuzzy queries over NoSQL graph database

AbstractThe massive production of data in the web environment increases the need for efficient and effective solutions to store and manage data. NoSQL databases with the capability of storing various types of data were introduced to be used in the management of big data. Besides, supporting flexible querying has significant impacts on data management usability and users prefer to ask their requests using fuzzy terms and get crisp results to make efficient decisions. In this paper, a fuzzy‐based approach is presented which adopts fuzzy queries and delivers crisp recommendations to the users. For this purpose, a counselor, which acts as a fuzzy agent and has knowledge about the data, defines fuzzy terms, membership functions and fuzzy rule tables in a way that each user can ask queries through fuzzy terms. The evaluation results show the efficiency of the proposed approach which removes the need for high‐level programming skills for users. As a result, our approach's efficiency and user acceptance are increased as well and made it an appropriate solution for using ambiguous queries in big graph databases.

Word sense induction using leader-follower clustering of automatically generated lexical substitutes

Word Sense Induction (WSI) concerns the automatic identification of the various senses of polysemous words. Any improvement in this process can directly affect the quality of the applications in which knowing the word’s senses is important. For example, word sense disambiguation, information retrieval, and clustering of web search result in lexically ambiguous queries. In this paper, we propose a novel WSI model that makes use of automatically generated lexical substitutes for a target word to construct a graph and data preparation for the next steps. Following the data preparation step, we make use of Leader–Follower graph clustering to find the basic senses of the target word. The senses of the target word inside the remaining or new upcoming instances will be decided according to their contextual embedding’s similarities with the basic sense. Besides, to make the number of found sense groups of a target word much closer to the reality, we apply post-processing at the end. The results of experiments on SemEval2010 dataset confirm that the proposed method outperforms all the state-of-the-art solutions in terms of both harmonic and geometric v-measure and f-score with a lower average number of sense groups.

Personalized Search Engine Using Binary Tree Traversal (BTT) - A Survey

Web pages have an increasing number of been used because thepatron interface of many software programsoftwarestructures. The simplicity of interplay with internet pages is an idealbenefit of the usage of them. However, the character interface also can get extracomplicatedwhilegreatercomplexnet pages are used to construct it. Understanding the complexity of net pages as perceived subjectively with the resource of clients is thereforecrucial to betterlayout this sort ofconsumer interface. Searching is one of thenot unusual placeassignmentachievedon the Internet. Search engines are the essentialtool of the net, from whereinyou willcollectassociatedstatistics and searched in keeping with the favoredkey-word given by the character. The recordson theinternet is developing dramatically. The consumer has to spend extra time with inside theinternetin case youneed to find outthe correctfactsthey may befascinated in. Existing net engines like Google do now no longerundergo in thoughtsuniqueneeds of character and serve eachpatron similarly. For this ambiguous query, some offiles on wonderfulsubjects are decreaselower backby engines like Google. Hence it will becomedifficult for the consumer to get the requiredcontent materialfabric. Moreover it additionally takes extra time in searching a pertinent content materialfabric. In this paper, we are able to survey the numerous algorithms for decreasing complexity in internetweb page navigations.

AN EFFICIENT NOVEL APPROACH FOR SOCIETAL COMMUNICATION OF Q&A COMMUNITY SYSTEM USING TOPIC MODELING TECHNIQUES

The emerging trend in technical research is to use customer-generated data collected by community media to probe community opinion and scientific communication on employment and care issues. This review of the collected data, the launch of a question-and-answer social website, is a separate stack for exploring the key factors that influence public preferences for technical knowledge and opinions. by means of a web search engine, topic modeling, and regression data modeling, this study quantified the effect of the response textual and auxiliary functions on the number of votes received with the response. Compared to previous studies based on open estimates, the model results show that Quora users are more likely to only talk about technology. It can fail when the keywords in the query do not match the text content of large documents that contain relevant questions of existing methods, ie. CNNMF and NMF, as well as some restrictions are not enough. Also, users are often not experts and provide ambiguous queries leading to mixed results and encountering problems with existing methods. To address this problem, in this article we propose a Hadoop model, distributed using semantics, non-negative matrix factorization (HDiSANNMF), to find topics for short texts. It effectively incorporates the semantic correlations of the word context into the model, where the semantic connections between words and their context are learned by omitting the grammatical view of the corpus. The researchers are trying to reorganize the main results and present modern techniques for modeling distributed themes to address technologies and platforms with increasing attributes, as well as how much time and space it takes to generate the model. This document briefly describes the structure of public questions and answers around the world and tracks the development of the main topics Housing and employment opportunities for next generation technologies in the world in real time.

A new Query Reformulation Approach using Web Result Clustering and User Profile

Query reformulation techniques are essential for information retrieval systems. These techniques eliminate the bad queries (short and ambiguous queries) and minimize users search time. There are two kinds of techniques in literature; the first uses the query logs with the click-through data to identify relevant queries and propose them to the user. The second group uses relevant terms extracted from different sources such as Wikipedia, Wordnet, and pseudo-relevant documents to expand the initial query and increase the likelihood with relevant documents. Both groups generate false queries because they do not consider the user interests and due to the assumption that the user clicks only on relevant results (first group) and that the top-k retrieved documents (top 5 to 15) are relevant (second group).In this paper, we propose a novel approach to reformulate the user queries using his profile (which contains the user interests). The approach retrieves documents related to the query from four different data sources (≈ 1000 doc). Then, it extracts the topics of these documents using the Lingo clustering algorithm (cluster the document with the same topic) and Text razor API (extract the potential topics of each cluster). Finally, it generates queries based on these topics and the user profile. The results show that the proposed approach outperforms the existing solution in P@10, P@20, and MAP.

Querying multi-source heterogeneous fuzzy spatiotemporal data

With the rapid development of the environmental, meteorological and marine data management, fuzzy spatiotemporal data has received considerable attention. Even though some achievements in querying aspect have been made, there are still some unsolved problems. Semantic and structural heterogeneity may exist among different data sources, which will lead to incomplete results. In addition, there are ambiguous query intentions and conditions when the user queries the data. This paper proposes a fuzzy spatiotemporal data semantic model. Based on this model, the RDF local semantic models are converted into a RDF global semantic model after mapping relational data and XML data to RDF local semantic models. The existing methods mainly convert relational data to RDF Schema directly. But our approach converts relational data to XML Schema and then converts it to RDF, which utilizes the semi-structured feature of XML schema to solve the structural heterogeneity between different data sources. The integration process enables us to perform global queries against different data sources. In the proposed query algorithms, the query conditions inputted are converted into exact queries before the results are returned. Finally, this paper has carried out extensive experiments, calculated the recall, precision and F-Score of the experimental results, and compared with other state-of-the-art query methods. It shows the importance of the data integration method and the effectiveness of the query method proposed in this paper.

Visual Grounding Via Accumulated Attention.

Visual grounding (VG) aims to locate the most relevant object or region in an image, based on a natural language query. Generally, it requires the machine to first understand the query, identify the key concepts in the image, and then locate the target object by specifying its bounding box. However, in many real-world visual grounding applications, we have to face with ambiguous queries and images with complicated scene structures. Identifying the target based on highly redundant and correlated information can be very challenging, and often leading to unsatisfactory performance. To tackle this, in this paper, we exploit an attention module for each kind of information to reduce internal redundancies. We then propose an accumulated attention (A-ATT) mechanism to reason among all the attention modules jointly. In this way, the relation among different kinds of information can be explicitly captured. Moreover, to improve the performance and robustness of our VG models, we additionally introduce some noises into the training procedure to bridge the distribution gap between the human-labeled training data and the real-world poor quality data. With this "noised" training strategy, we can further learn a bounding box regressor, which can be used to refine the bounding box of the target object. We evaluate the proposed methods on four popular datasets (namely ReferCOCO, ReferCOCO+, ReferCOCOg, and GuessWhat?!). The experimental results show that our methods significantly outperform all previous works on every dataset in terms of accuracy.

Time-aware query suggestion diversification for temporally ambiguous queries

PurposeThe purpose of this study is to generate diversified results for temporally ambiguous queries and the candidate queries are ensured to have a high coverage of subtopics, which are derived from different temporal periods.Design/methodology/approachTwo novel time-aware query suggestion diversification models are developed by integrating semantics and temporality information involved in queries into two state-of-the-art explicit diversification algorithms (i.e. IA-select and xQuaD), respectively, and then specifying the components on which these two models rely on. Most importantly, first explored is how to explicitly determine query subtopics for each unique query from the query log or clicked documents and then modeling the subtopics into query suggestion diversification. The discussion on how to mine temporal intent behind a query from query log is also followed. Finally, to verify the effectiveness of the proposal, experiments on a real-world query log are conducted.FindingsPreliminary experiments demonstrate that the proposed method can significantly outperform the existing state-of-the-art methods in terms of producing the candidate query suggestion for temporally ambiguous queries.Originality/valueThis study reports the first attempt to generate query suggestions indicating diverse interested time points to the temporally ambiguous (input) queries. The research will be useful in enhancing users’ search experience through helping them to formulate accurate queries for their search tasks. In addition, the approaches investigated in the paper are general enough to be used in many domains; that is, experimental information retrieval systems, Web search engines, document archives and digital libraries.

Interactive Natural Language Grounding via Referring Expression Comprehension and Scene Graph Parsing.

Natural language provides an intuitive and effective interaction interface between human beings and robots. Currently, multiple approaches are presented to address natural language visual grounding for human-robot interaction. However, most of the existing approaches handle the ambiguity of natural language queries and achieve target objects grounding via dialogue systems, which make the interactions cumbersome and time-consuming. In contrast, we address interactive natural language grounding without auxiliary information. Specifically, we first propose a referring expression comprehension network to ground natural referring expressions. The referring expression comprehension network excavates the visual semantics via a visual semantic-aware network, and exploits the rich linguistic contexts in expressions by a language attention network. Furthermore, we combine the referring expression comprehension network with scene graph parsing to achieve unrestricted and complicated natural language grounding. Finally, we validate the performance of the referring expression comprehension network on three public datasets, and we also evaluate the effectiveness of the interactive natural language grounding architecture by conducting extensive natural language query groundings in different household scenarios.

Selective personalization and group profiles for improved web search personalization

Personalization is a common technique used in Web search engines to improve the effectiveness of retrieval. While personalizing some queries yields significant improvements in user experience by providing a ranking in line with the user preferences, it fails to improve or even degrades the effectiveness for less ambiguous queries. A potential personalization metric could improve search engines by selectively applying personalization. One such measure, click entropy uses the query history and the clicked documents for the query, which might be sparse for some queries. In this article, the topic entropy measure is improved by integrating the user distribution into the metric, robust to the sparsity problem. Furthermore, a topic model-based ranking for the personalization method is proposed using grouped user profiles. Experiments reveal that the proposed potential prediction method correlates with human query ambiguity judgments and the group profile-based ranking method improves the mean reciprocal rank by 8%.

Distinct Web Search Engine with Reducing Ambiguity Word Complexity

Searching is one of the common mission accomplished at the Internet. Search engines are the primary tool of the net, from in which you'll be able to acquire associated information and searched in step with the required key-word given by way of the person. The statistics at the internet is developing dramatically. The consumer has to spend more time inside the internet a good way to locate the precise data they may be inquisitive about. Existing internet system do not remember particular needs of user and serve every person similarly. For this ambiguous query, a number of documents on awesome topics are returned by way of engines like Google. Hence it turns into difficult for the consumer to get the specified content material. Moreover it also takes extra time in searching a pertinent content. Privacy based totally Personalized Web Search Engine is considered as a promising answer to address these problems, considering the fact that distinct search outcomes can be furnished depending upon the choice and records needs of users. It exploits consumer records and seek context to learning in which experience a question refer. In order to perform Personalized Web seek it is critical to version User's hobby. User profiles are built to version person's need based on his/her web utilization information. This Enhanced User Profile will help the person to retrieve concentrated information. This paper proposes structure for constructing consumer profile and enhances the person profile the usage of historical past know-how. It can be used for suggesting suitable net pages to the person based totally on his search question and background expertise. And also put into effect the pruning set of rules to put off the consumer info from anonymous person for maintain the important thing phrase privacy. On other side we want to hide the privacy contents present in the person profile to place the privateness hazard under manage. User privateness may be provided in form of safety like without compromising the customized seek satisfactory.