Original Query Research Articles

Semantically-enhanced information retrieval using multiple knowledge sources

Classical or traditional Information Retrieval (IR) approaches rely on the word-based representations of query and documents in the collection. The specification of the user information need is completely based on words figuring in the original query in order to retrieve documents containing those words. Such approaches have been limited due to the absence of relevant keywords as well as the term variation in documents and user’s query. The purpose of this paper is to present a new method to Semantic Information Retrieval (SIR) to solve the limitations of existing approaches. Concretely, we propose a novel method SIRWWO (Semantic Information Retrieval using Wikipedia, WordNet, and domain Ontologies) for SIR by combining multiple knowledge sources Wikipedia, WordNet, and Description Logic (DL) ontologies. In order to illustrate the approach SIRWWO, we first present the notion of Labeled Dynamic Semantic Network (LDSN) by extending the notions of dynamic semantic network and extended semantic net based on WordNet (and DAML ontology library). According to the notion of LDSN, we obtain the notion of Weighted Dynamic Semantic Network (WDSN, intuitively, each edge in WDSN is assigned to a number in the [0, 1] interval) and give the WDSN construction method using Wikipedia, WordNet, and DL ontology. We then propose a novel metric to measure the semantic relatedness between concepts based on WDSN. Lastly, we investigate the approach SIRWWO by using semantic relatedness between users’ query keywords and digital documents. The experimental results show that our proposals obtain comparable and better performance results than other traditional IR system Lucene.

A Query Understanding Framework for Earth Data Discovery

One longstanding complication with Earth data discovery involves understanding a user’s search intent from the input query. Most of the geospatial data portals use keyword-based match to search data. Little attention has focused on the spatial and temporal information from a query or understanding the query with ontology. No research in the geospatial domain has investigated user queries in a systematic way. Here, we propose a query understanding framework and apply it to fill the gap by better interpreting a user’s search intent for Earth data search engines and adopting knowledge that was mined from metadata and user query logs. The proposed query understanding tool contains four components: spatial and temporal parsing; concept recognition; Named Entity Recognition (NER); and, semantic query expansion. Spatial and temporal parsing detects the spatial bounding box and temporal range from a query. Concept recognition isolates clauses from free text and provides the search engine phrases instead of a list of words. Name entity recognition detects entities from the query, which inform the search engine to query the entities detected. The semantic query expansion module expands the original query by adding synonyms and acronyms to phrases in the query that was discovered from Web usage data and metadata. The four modules interact to parse a user’s query from multiple perspectives, with the goal of understanding the consumer’s quest intent for data. As a proof-of-concept, the framework is applied to oceanographic data discovery. It is demonstrated that the proposed framework accurately captures a user’s intent.

이중 주파수 대역 검출기반의 강인한 Audio Fingerprinting 시스템

In this paper, we present a new audio identification system which is robust to various attacks. The types of attacks employed are modification such as changes of tempo, pitch and speed and noise addition also low and high pass filtering. We proposed a two-dimensional representation for the audio signal called FFMAP. This consists of pitch components and frame components. We also employ Pearson’s correlation score to calculate similarity between original audio data and query. Experimental results show that the proposed algorithm has a high performance.

Query Expansion for Improving Web Search

The aim of this paper is to retrieve the most relevant expansion words for expanding the initial query of the user in order to enhance the outcomes of web search results. Query expansion plays a major role in reformulating a user’s initial query to a one more pertinent to the user’s intended meaning. The reformulated query is then used to obtain more appropriate outcomes from a large amount of information on the web. The proposed semantic query expansion technique uses Wikipedia and WordNet as data sources. Wikipedia is taken as a base for all query expansions because it is one of the most diversified and relevant databases available on the web. To further improve the proposed query expansion technique,WordNet—a lexical database—is used as the as another data source because the synonyms (synsets) of the query term provided by it can be quite useful for query expansion. The proposed expansion technique successfully combines the two data sources to retrieve the most relevant expansion terms from the data sources in response to the user’s original query. The proposed work has been divided into four phases: (1) extraction of relevant words from Wikipedia (2) extraction of relevant words from WordNet (3) merging of the expansion terms obtained from Wikipedia and WordNet, and (4) query formulation by combining the expansion terms using Boolean operators. This reformulated query is then fired on the web to find the desired result. The Experimental result shows a significant improvement in information retrieval using query expansion.

Answering Why-Not Group Spatial Keyword Queries

With the proliferation of geo-textual objects on the web, extensive efforts have been devoted to improving the efficiency of top- $k$ k spatial keyword queries in different settings. However, comparatively much less work has been reported on enhancing the quality and usability of such queries. In this context, we propose means of enhancing the usability of a top- $k$ k group spatial keyword query, where a group of users aim to find $k$ k objects that contain given query keywords and are nearest to the users. Specifically, when users receive the result of such a query, they may find that one or more objects that they expect to be in the result are in fact missing, and they may wonder why. To address this situation, we develop a so-called why-not query that is able to minimally modify the original query into a query that returns the expected, but missing, objects, in addition to other objects. Specifically, we formalize the why-not query in relation to the top- $k$ k group spatial keyword query, called the W hy-not G roup S patial K eyword Query ( $\mathsf{WGSK}$ WGSK ) that is able to provide a group of users with a more satisfactory query result. We propose a three-phase framework for efficiently computing the $\mathsf{WGSK}$ WGSK . The first phase substantially reduces the search space for the subsequent phases by retrieving a set of objects that may affect the ranking of the user-expected objects. The second phase provides an incremental sampling algorithm that generates candidate weightings of more promising queries. The third phase determines the penalty of each refined query and returns the query with minimal penalty, i.e., the minimally modified query. Extensive experiments with real and synthetic data offer evidence that the proposed solution excels over baselines with respect to both effectiveness and efficiency.

A supervised term ranking model for diversity enhanced biomedical information retrieval

BackgroundThe number of biomedical research articles have increased exponentially with the advancement of biomedicine in recent years. These articles have thus brought a great difficulty in obtaining the needed information of researchers. Information retrieval technologies seek to tackle the problem. However, information needs cannot be completely satisfied by directly introducing the existing information retrieval techniques. Therefore, biomedical information retrieval not only focuses on the relevance of search results, but also aims to promote the completeness of the results, which is referred as the diversity-oriented retrieval.ResultsWe address the diversity-oriented biomedical retrieval task using a supervised term ranking model. The model is learned through a supervised query expansion process for term refinement. Based on the model, the most relevant and diversified terms are selected to enrich the original query. The expanded query is then fed into a second retrieval to improve the relevance and diversity of search results. To this end, we propose three diversity-oriented optimization strategies in our model, including the diversified term labeling strategy, the biomedical resource-based term features and a diversity-oriented group sampling learning method. Experimental results on TREC Genomics collections demonstrate the effectiveness of the proposed model in improving the relevance and the diversity of search results.ConclusionsThe proposed three strategies jointly contribute to the improvement of biomedical retrieval performance. Our model yields more relevant and diversified results than the state-of-the-art baseline models. Moreover, our method provides a general framework for improving biomedical retrieval performance, and can be used as the basis for future work.

Trends in Crossover of Patients in Phase III Clinical Trials for Hematologic Malignancies

Background: The incorporation of crossover in randomized controlled trials is accepted as an ethical obligation, especially in cancer clinical trials. The more common type of crossover is unidirectional, which allows patients assigned to the control arm (either placebo or standard of care) to switch to the experimental arm. In contrast, bidirectional crossover includes the switching of patients from the experimental arm to the control arm. Integrating crossover into the initial study design may have advantages in patient recruitment, and incorporating crossover after initial positive results fulfills ethical requirements. However, crossover can also contribute to confounding major endpoints of studies, such as overall survival or the second progression-free survival interval. For this reason, it is important to investigate and identify potential trends of crossover in clinical trials testing novel therapies. The development of new treatments for hematologic malignancies is promising, and as such, makes these trials susceptible to crossover. Trends in crossover of clinical trials for hematologic malignancies have not yet been studied. Methods: Data about cancer clinical trials were extracted from clinicaltrials.gov. The search query was limited to completed phase III studies in adult populations. Location was limited to the United States. No date range or funder type was specified. The following search query was used: recruitment status: "completed;" age: "adult (18-64)," "older adult (65+);" sex: "all;" country: "United States;" study phase: "phase 3." These criteria were then applied in individual searches for clinical trials related each hematologic malignancy. The following terms were used in the "disease" search field: "acute lymphoid leukemia," "acute myeloid leukemia," "multiple myeloma," "lymphoma," "chronic myeloid leukemia," and "chronic lymphocytic leukemia." Repeat clinical trials obtained through separate searches were excluded. Studies were then excluded if they were not randomized controlled trials (RCTs) with the primary purpose of treatment, and if they did not test cancer-related interventions. Results: A total of 184 unique clinical trials were identified, of which 156 were RCTs with the primary purpose of treatment. Only 149 trials tested cancer-related drugs, biologicals, or procedures. Of those, 60 trials contained 2 experimental arms, and 89 trials contained 3 or more experimental arms. 6 of the 60 (10%) 2 arm trials permitted crossover, and 4 of the 89 (4.5%) 3+ arm trials permitted crossover, for a total of 10 trials with crossover. The start dates of these trials ranged from 2000-2012. 3 trials (30%) were bidirectional, and 7 (70%) were unidirectional. The identified clinical trials with crossover belonged to only 3 of the original 6 hematologic malignancies included in the original search query: multiple myeloma, lymphoma, and CML (Table 1). Conclusions: The proportion of identified clinical trials with crossover to those without is extremely small. Crossover in clinical trials studying hematologic malignancies does not appear to be a widespread practice. Multiple myeloma contains the most trials with crossover compared to other hematologic malignancies. Even though statistical approaches to mitigate confounding exist, crossover can still skew accurate reporting of the impact of experimental therapies on overall survival. Examining trends among the trials with crossover will hopefully lead to improved correction methods and better estimates of treatment benefit. Disclosures No relevant conflicts of interest to declare.

Explaining Natural Language query results

Multiple lines of research have developed Natural Language (NL) interfaces for formulating database queries. We build upon this work, but focus on presenting a highly detailed form of the answers in NL. The answers that we present are importantly based on the provenance of tuples in the query result, detailing not only the results but also their explanations. We develop a novel method for transforming provenance information to NL, by leveraging the original NL query structure. Furthermore, since provenance information is typically large and complex, we present two solutions for its effective presentation as NL text: one that is based on provenance factorization, with novel desiderata relevant to the NL case, and one that is based on summarization. We have implemented our solution in an end-to-end system supporting questions, answers and provenance, all expressed in NL. Our experiments, including a user study, indicate the quality of our solution and its scalability.

Improving Search Engines by Demoting Non-Relevant Documents

A good search engine aims to have more relevant documents on the top of the list. This paper describes a new technique called ???Improving search engines by demoting non-relevant documents??? (DNR) that improves the precision by detecting and demoting non-relevant documents. DNR generates a new set of queries that are composed of the terms of the original query combined in different ways. The documents retrieved from those new queries are evaluated using a heuristic algorithm to detect the non-relevant ones. These non-relevant documents are moved down the list which will consequently improve the precision. The new technique is tested on WT2g test collection. The testing of the new technique is done using variant retrieval models, which are the vector model based on the TFIDF weighing measure, the probabilistic models based on the BM25, and DFR-BM25 weighing measures. The recall and precision ratios are used to compare the performance of the new technique against the performance of the original query.

Deep learning the semantics of change sequences for query expansion

SummaryThe overexpansion problem negatively affects the quality of query expansion. To improve the quality of queries for searching code, this paper proposed a DBN‐based algorithm for effective query expansion. The deep belief network (DBN) model is trained on the code sequences and their change sequences, which aims to capture the meaningful terms during the evolution of source code. In contrast to previous studies, the proposed model not only extracts relevant terms to expand a query but also excludes irrelevant terms from the query. It addresses two problems in query expansion, including the overexpansion of the original query and the negative influence of the changed terms in the target source code. Experiments on both artificial queries and real queries show that the proposed algorithm outperforms several query expansion algorithms for code search.

Evaluation of word spotting under improper segmentation scenario

Word spotting is an important recognition task in large-scale retrieval of document collections. In most of the cases, methods are developed and evaluated assuming perfect word segmentation. In this paper, we propose an experimental framework to quantify the goodness that word segmentation has on the performance achieved by word spotting methods in identical unbiased conditions. The framework consists of generating systematic distortions on segmentation and retrieving the original queries from the distorted dataset. We have tested our framework on several established and state-of-the-art methods using George Washington and Barcelona Marriage Datasets. The experiments done allow for an estimate of the end-to-end performance of word spotting methods.

Facilitating phenotype transfer using a common data model

Implementing clinical phenotypes across a network is labor intensive and potentially error prone. Use of a common data model may facilitate the process. Electronic Medical Records and Genomics (eMERGE) sites implemented the Observational Health Data Sciences and Informatics (OHDSI) Observational Medical Outcomes Partnership (OMOP) Common Data Model across their electronic health record (EHR)-linked DNA biobanks. Two previously implemented eMERGE phenotypes were converted to OMOP and implemented across the network. It was feasible to implement the common data model across sites, with laboratory data producing the greatest challenge due to local encoding. Sites were then able to execute the OMOP phenotype in less than one day, as opposed to weeks of effort to manually implement an eMERGE phenotype in their bespoke research EHR databases. Of the sites that could compare the current OMOP phenotype implementation with the original eMERGE phenotype implementation, specific agreement ranged from 100% to 43%, with disagreements due to the original phenotype, the OMOP phenotype, changes in data, and issues in the databases. Using the OMOP query as a standard comparison revealed differences in the original implementations despite starting from the same definitions, code lists, flowcharts, and pseudocode. Using a common data model can dramatically speed phenotype implementation at the cost of having to populate that data model, though this will produce a net benefit as the number of phenotype implementations increases. Inconsistencies among the implementations of the original queries point to a potential benefit of using a common data model so that actual phenotype code and logic can be shared, mitigating human error in reinterpretation of a narrative phenotype definition.

Variational BEJG Solvers for Marginal-MAP Inference with Accurate Approximation of B-Conditional Entropy

Previously proposed variational techniques for approximate MMAP inference in complex graphical models of high-order factors relax a dual variational objective function to obtain its tractable approximation, and further perform MMAP inference in the resulting simplified graphical model, where the sub-graph with decision variables is assumed to be a disconnected forest. In contrast, we developed novel variational MMAP inference algorithms and proximal convergent solvers, where we can improve the approximation accuracy while better preserving the original MMAP query by designing such a dual variational objective function that an upper bound approximation is applied only to the entropy of decision variables. We evaluate the proposed algorithms on both simulated synthetic datasets and diagnostic Bayesian networks taken from the UAI inference challenge, and our solvers outperform other variational algorithms in a majority of reported cases. Additionally, we demonstrate the important real-life application of the proposed variational approaches to solve complex tasks of policy optimization by MMAP inference, and performance of the implemented approximation algorithms is compared. Here, we demonstrate that the original task of optimizing POMDP controllers can be approached by its reformulation as the equivalent problem of marginal-MAP inference in a novel single-DBN generative model, which guarantees that the control policies computed by probabilistic inference over this model are optimal in the traditional sense. Our motivation for approaching the planning problem through probabilistic inference in graphical models is explained by the fact that by transforming a Markovian planning problem into the task of probabilistic inference (a marginal MAP problem) and applying belief propagation techniques in generative models, we can achieve a computational complexity reduction from PSPACE-complete or NEXP-complete to NPPP-complete in comparison to solving the POMDP and Dec-POMDP models respectively search vs. dynamic programming).

A qualitative analysis of the Wikipedia N-Substate Algorithm's Enhancement Terms

<p>Automatic Search Query Enhancement (ASQE) is the process of modifying a user submitted search query and identifying terms that can be added or removed to enhance the relevance of documents retrieved from a search engine. ASQE differs from other enhancement approaches as no human interaction is required. ASQE algorithms typically rely on a source of a priori knowledge to aid the process of identifying relevant enhancement terms. This paper describes the results of a qualitative analysis of the enhancement terms generated by the Wikipedia NSubstate Algorithm (WNSSA) for ASQE. The WNSSA utilises Wikipedia as the sole source of a priori knowledge during the query enhancement process. As each Wikipedia article typically represents a single topic, during the enhancement process of the WNSSA, a mapping is performed between the user’s original search query and Wikipedia articles relevant to the query. If this mapping is performed correctly, a collection of potentially relevant terms and acronyms are accessible for ASQE. This paper reviews the results of a qualitative analysis process performed for the individual enhancement term generated for each of the 50 test topics from the TREC-9 Web Topic collection. The contributions of this paper include: (a) a qualitative analysis of generated WNSSA search query enhancement terms and (b) an analysis of the concepts represented in the TREC-9 Web Topics, detailing interpretation issues during query-to-Wikipedia article mapping performed by the WNSSA.</p>

Bayesian approach to incorporating different types of biomedical knowledge bases into information retrieval systems for clinical decision support in precision medicine.

By providing clinicians with information regarding treatment options for molecular sub-types of complex diseases with genetic origin, such as cancer, information retrieval (IR) systems play an important role in precision medicine. In this paper, we propose Bayesian Precision Medicine (BPM), a novel probabilistic framework for query expansion in information retrieval systems for Clinical Decision Support (CDS) in Precision Medicine (PM). Such systems can assist clinicians with selecting personalized treatment of complex diseases based on the patients' genomic data, such as gene mutations. In particular, we focus on a clinical decision support scenario in which clinicians provide two types of information in their queries: (1) short description of a patient's case, which may contain information regarding the type of cancer that a patient has as well as symptoms and demographics, and (2) gene mutations, which may contain gene names, mutation code and type of mutation. The goal of an IR system in this scenario is to rank biomedical articles from a large collection, such as the MEDLINE, based on their relevance to the provided query. One of the main challenges faced by IR systems in this scenario is semantic matching of heterogeneous information (gene names, medical terminology and other query keywords) in queries and relevant biomedical articles. To address this challenge, we propose a probabilistic framework that enables mapping gene mutations provided in a given query onto the biomedical concepts that are related to the entire query and can be effectively utilized for query expansion. The BPM obtains candidate query expansion concepts from biomedical knowledge bases, the Unified Medical Language System (UMLS) and the Drug-Gene Interaction Database (DGIdb), as well as the top-ranked MEDLINE articles retrieved for the original query. The BPM then utilizes information from the Catalog of Somatic Mutations in Cancer (COSMIC) and co-occurrence statistics in MEDLINE to assess the relatedness of candidate query expansion concepts to gene mutations and other information provided in a query. Experimental evaluation of the BPM was conducted on a large subset of MEDLINE articles as well as abstracts from the American Association for Cancer Research (AACR) and American Society of Clinical Oncology (ASCO) proceedings. Experimental results on a publicly available benchmark provided by the 2017 TREC precision medicine track indicate that the proposed probabilistic framework is effective at utilizing both genomic and textual information in queries to improve the accuracy of IR systems for CDS in PM through query expansion.

Similar image search for histopathology: SMILY

The increasing availability of large institutional and public histopathology image datasets is enabling the searching of these datasets for diagnosis, research, and education. Although these datasets typically have associated metadata such as diagnosis or clinical notes, even carefully curated datasets rarely contain annotations of the location of regions of interest on each image. As pathology images are extremely large (up to 100,000 pixels in each dimension), further laborious visual search of each image may be needed to find the feature of interest. In this paper, we introduce a deep-learning-based reverse image search tool for histopathology images: Similar Medical Images Like Yours (SMILY). We assessed SMILY’s ability to retrieve search results in two ways: using pathologist-provided annotations, and via prospective studies where pathologists evaluated the quality of SMILY search results. As a negative control in the second evaluation, pathologists were blinded to whether search results were retrieved by SMILY or randomly. In both types of assessments, SMILY was able to retrieve search results with similar histologic features, organ site, and prostate cancer Gleason grade compared with the original query. SMILY may be a useful general-purpose tool in the pathologist’s arsenal, to improve the efficiency of searching large archives of histopathology images, without the need to develop and implement specific tools for each application.

Answering why-not questions on KNN queries

Being decades of study, the usability of database systems have received more attention in recent years. Now it is especially able to explain missing objects in a query result, which is called “why-not” questions, and is the focus of concern. This paper studies the problem of answering why-not questions on KNN queries. In our real life, many users would like to use KNN queries to investigate the surrounding circumstances. Nevertheless, they often feel disappointed when finding the result not including their expected objects. In this paper, we use the query refinement approach to resolve the problem. Given the original KNN query and a set of missing objects as input, our algorithm offer a refined KNN query that includes the missing objects to the user. The experimental results demonstrate the efficiency of our proposed optimizations and algorithms.

Monitoring Heat-Related Illness through Syndromic Surveillance in Los Angeles County

ObjectiveTo analyze Los Angeles County’s (LAC) extreme heat season in 2018 and evaluate the Council of State and Territorial Epidemiologists’ (CSTE) syndrome query for heat-related-illness (HRI) in Los Angeles County (LAC)IntroductionLAC experienced several days of record-breaking temperatures during the summer of 2018. Downtown Los Angeles temperatures soared to 108°F in July with an average daily maximum of 92°F. Extreme heat events such as these can pose major risks to human health. Syndromic surveillance can be a useful tool in providing near real-time surveillance of HRI. In 2014, a working group was formed within the CSTE Climate Change Subcommittee to define and analyze HRI. The workgroup’s goal was to provide guidance to public health professionals in adapting and implementing an HRI syndrome surveillance query. The Acute Communicable Disease Control Program’s (ACDC) Syndromic Surveillance Unit utilized CSTE’s HRI query to provide surveillance during the extreme heat season in 2018 in LAC. Additional modifications to the CSTE query were evaluated for potential improvements towards characterizing HRI trends.MethodsFrom May 1 to September 30, 2018, Emergency Department (ED) data were queried for cases using the CSTEs definition for HRI. The queries consisted of key word searches within the chief complaint (CC) data field, and, if available, the diagnosis data fields. The query was derived from the CSTE HRI query published in 20161. In addition, ACDC explored the utility of expanding the CSTE syndrome definition to include additional chief complaints commonly associated with HRI such as dehydration and syncope. Both queries were applied on all participating syndromic EDs in LAC alongside daily high temperature data trends. Local temperature data for downtown Los Angeles weather station KCQT were taken from the Weather Underground website. Spearman correlation coefficients were calculated for each query during the heat season. Similarly, both queries were also applied during colder months from October 1, 2017 to April 30, 2018 for comparison. Lastly, results for dehydration and syncope were independently assessed apart from other HRI query terms during both heat seasons and colder months.ResultsThe CSTE HRI query and the query with the added terms yielded 1,258 and 63,332 ED visits, respectively, during the heat season. On July 6, the maximum daily temperature peaked at 108 °F; the HRI and the query with the added terms yielded 136 and 618 ED visits, respectively. The HRI query and the HRI query with the added terms had a correlation coefficient of 0.714 (p <0.0001) and 0.427 (p <0.0001), respectively. During colder months, the CSTE HRI query and the query with the added terms yielded 377 and 86,008, respectively, with correlation coefficients of 0.342 (p < 0.0001) and 0.133 (p < 0.052). The syncope-only query saw no variation in HRI classified encounters throughout the heat season (mean: 328; min: 228; max: 404) or colder months (mean: 328; min: 261; max: 404) with correlation coefficients of 0.238 (p = 0.003) and 0.155 (p = 0.024), respectively. Similarly, the dehydration-only query saw no variation in HRI classified encounters throughout the heat season (mean: 96; min: 58; max: 258) or colder months (mean: 94; min: 60; max: 160) with correlation coefficients of 0.596 (p < 0.0001) and -0.016 (p = 0.822).ConclusionsThe CSTE HRI query proved to be a strong indicator for HRI, and the addition of terms associated with dehydration and syncope to the CSTE HRI query weakened the correlation with temperature. Compared to the original CSTE HRI query, the added terms yielded a 4934% increase in HRI classified encounters during the heat season; however, these were likely due to causes other than HRI -- adding the extra terms resulted in a weaker correlation with temperature. Additionally, the comparative analysis showed that, with the added terms, the volume of HRI encounters was larger during colder months than hotter months suggesting misclassification of non-HRI illnesses. Surveillance of HRI has proven to be difficult because many of the HRI symptoms are too commonly associated with non-HRI conditions which would explain the weaker correlations when adding additional chief complaints associated with HRI. In conclusion, the CSTE syndrome definition for HRI proved to be the most robust query for HRI during the heat season. Case counts of HRI are difficult due to symptom overlap with many other medical conditions. However, syndromic surveillance using the CSTE HRI query is useful for trend analysis in near real-time during heat events.

Mining Implicit Treatment Concepts for Neural Precision Medicine.

Precision medicine (PM) is regarded as an information retrieval (IR) task in which biomedical articles containing treatment information about specific diseases or genetic variants are retrieved in response to patient record for the purpose of providing medical evidence to the point-of-care. In existing PM approaches, manual keywords, such as "treatment" and "therapy," are considered direct indicators of treatment information and are thereby introduced to expand the original query. However, the common medical concepts that are implicitly related to treatment (such as "oncogene" and "tumor"), and differ the relevant documents from the non-relevant ones, are yet to be utilized. To bridge the gap, in this paper, we propose an extension of the state-of-the-art neural IR (NIR) models, including K-NRM and DRMM, to encapsulate the PM solutions within a neural network framework, referred to as NIR PM . Specifically, the proposed approach mines a global list of common medical concepts from documents that are judged pertinent to different queries. Thereafter, the mined implicit concepts are incorporated within an NIR framework to enhance the effectiveness of PM. The experimental results on the standard Text REtrieval Conference (TREC) PM track benchmark confirm the superior performance of the proposed NIRPM model.

Query Expansion for Effective Retrieval Results of Hindi–English Cross-Lingual IR

ABSTRACTInformation retrieval (IR) is the science of identifying documents or sub-documents from a collection of information or database. The collection of information does not necessarily be available in only one language as information does not depend on languages. Monolingual IR is the process of retrieving information in query language whereas cross-lingual information retrieval (CLIR) is the process of retrieving information in a language that differs from query language. In current scenario, there is a strong demand of CLIR system because it allows the user to expand the international scope of searching a relevant document. As compared to monolingual IR, one of the biggest problems of CLIR is poor retrieval performance that occurs due to query mismatching, multiple representations of query terms and untranslated query terms. Query expansion (QE) is the process or technique of adding related terms to the original query for query reformulation. Purpose of QE is to improve the performance and quality of retrieved information in CLIR system. In this paper, QE has been explored for a Hindi–English CLIR in which Hindi queries are used to search English documents. We used Okapi BM25 for documents ranking, and then by using term selection value, translated queries have been expanded. All experiments have been performed using FIRE 2012 dataset. Our result shows that the relevancy of Hindi–English CLIR can be improved by adding the lowest frequency term.