Information Retrieval Approach Research Articles

Intelligent ontology based semantic information retrieval using feature selection and classification

Semantic information retrieval provides more relevant information to the user query by performing semantic analysis. In such a scenario, knowledge representation using ontology can provide effective semantic retrieval facility which is more efficient than representation using semantic networks and frames. The existing information retrieval systems have been developed to handle very large volume of data and information stored in text format. On the other hand, the information available in the current web based applications such as Facebook and twitter grow very fast and hence the existing information retrieval systems consume large amount of time for relevant information retrieval. Moreover, most of the existing search engines use syntactic approach for information retrieval and use page ranking algorithms to measure the relevancy score. However, such approach is not able to provide more accurate results in terms of relevancy. Therefore, a new semantic information retrieval system is proposed in this paper which uses feature selection and classification for enhancing the relevancy score which is performed in this work by proposing a new intelligent fuzzy rough set based feature selection algorithm and an intelligent ontology and Latent Dirichlet Allocation based semantic information retrieval algorithm. The main advantages of the proposed algorithms are the increase in relevancy, ability to handle big data and fast retrieval.

Semantic Quality Assurance of Heterogeneous Unstructured Repair Reports

Service technicians spend a considerable amount of their working hours in order to search for information regarding a current work order. In case of an IPS² malfunction for example, they can either search for potential failure causes within previously documented repair reports that describe a similar malfunction or manually inspect the IPS². On the one hand the former IT-related information procurement is caused by a large amount of irrelevant search results rendered by current state of the art information retrieval approaches implemented in maintenance-related IT systems. On the other hand many repair reports suffer from missing or ambiguous information and a holistically low data quality, which makes it difficult for the service technicians to derive task-related information from a particular repair report, although this report basically describes the same malfunction. These current difficulties will be amplified once service partners get access to maintenance-related information documented by other service partners (companies) within the IPS² network as the amount of available data will increase drastically and new problems will raise concerning the heterogeneity of the data. The paper on hand presents a semantic quality assurance concept for heterogeneous unstructured repair reports that addresses the low data quality problem by utilizing natural language processing and machine learning methods to automatically analyze the service technician’s inputs during the repair report creation process and by notifying him of potential losses in data quality. The concept’s feasibility has been shown by performing a case study with a prototype that utilizes the developed methods.

Detecting prominent microblog users over crisis events phases

During crisis events such as disasters, the need for real-time information retrieval (IR) from microblogs becomes essential. However, the huge amount and the variety of the shared information in real time during such events over-complicates this task. Unlike existing IR approaches based on content analysis, we propose to tackle this problem by using user-centric IR approaches with identifying and tracking prominent microblog users who are susceptible to share relevant and exclusive information at an early stage of each analyzed event phase. This approach ensures real-time access to the valuable microblogs information required by the emergency teams. In this approach, we propose a phase-aware probabilistic model for predicting and ranking prominent microblog users over time according to their behavior using Mixture of Gaussians Hidden Markov Models (MoG-HMM). The model utilizes a new user representation which takes into account both the user and the event specificities over time. This user representation comprises the following new aspects (1) Modeling microblog users behavior evolution by considering the different event phases (2) Characterizing users activity over time through a temporal sequence representation (3) Time-series-based selection of the most discriminative features (4) prominent users prediction using probabilistic phase-aware models learned a priori. We have conducted experiments during flooding events: we trained our identification models using a dataset relative to the “Alpes-Maritimes floods” and we tested its identification performance using a new dataset relative to another flooding disaster “Herault floods”. The achieved results show that our model significantly outperforms phase-unaware models and identifies most of the prominent users at an early stage of each event phase.

Response selection from unstructured documents for human-computer conversation systems

This paper studies response selection for human-computer conversation systems. Existing retrieval-based human-computer conversation systems are intended to reply to user utterances based on existing utterance-response pairs. However, collecting sufficient utterance-response pairs is intractable in practical situations, especially for many specific domains. We introduce DocChat a novel information retrieval approach for human-computer conversation systems that can use unstructured documents rather than semi-structured utterance-response pairs, to react to user utterances. The key of DocChat is a learning to rank model with features designed at various levels of granularity which is proposed to quantify the relevance between utterances and responses directly. We conduct comprehensive experiments on both sentence selection and real human-computer conversation scenarios. Empirical studies of sentence selection datasets shows reasonable improvements and the strong adaptability of our model. We compare DocChat with Xiaoice, a famous open domain chitchat engine in China. Side-by-side evaluation shows that DocChat is a good complement for human-computer conversation systems using utterance-response pairs as the primary source of responses. Furthermore, we release a large scale open-domain dataset for sentence selection which contains 304,413 query-sentence pairs.

Intelligent rule-based approach for effective information retrieval and dynamic storage in local repositories

Rules in artificial intelligence are able to provide inference facilities for making effective decisions in information retrieval. In such a scenario, a keyword-based information retrieval systems use the keywords as indexes generated by Web crawlers without considering semantics. Moreover, many Web search engines perform re-ranking based on relevance feedback. However, the relevant documents in e-learning applications must be stored in local repositories and must be updated dynamically based on the level of the users. Therefore, it is necessary to have an information retrieval system which performs relevant information extraction and stores such relevant information dynamically in local e-learning repositories. In order to address these issues, a new information retrieval and local storage system is proposed in this paper by applying rules for making effective decisions in the storage and retrieval algorithms which are newly proposed in this paper. For this purpose, two new algorithms called intelligent rule-based relevant information retrieval algorithm with semantics and a secured information storage using semantic knowledge representation are proposed in this paper for effectively retrieving the e-learning contents from the Web on computer science subject and to store them in local repositories with semantic indexing. The major advantages of the proposed information retrieval system include increase in accuracy, reduction in retrieval time and effective storage in local repositories for further use.

Introduction to the special issue on bibliometric-enhanced information retrieval and natural language processing for digital libraries (BIRNDL)

The large scale of scholarly publications poses a challenge for scholars in information seeking and sensemaking. Bibliometric, information retrieval (IR), text mining, and natural language processing techniques can assist to address this challenge, but have yet to be widely used in digital libraries (DL). This special issue on bibliometric-enhanced information retrieval and natural language processing for digital libraries (BIRNDL) was compiled after the first joint BIRNDL workshop that was held at the joint conference on digital libraries (JCDL 2016) in Newark, New Jersey, USA. It brought together IR and DL researchers and professionals to elaborate on new approaches in natural language processing, information retrieval, scientometric, and recommendation techniques that can advance the state of the art in scholarly document understanding, analysis, and retrieval at scale. This special issue includes 14 papers: four extended papers originating from the first BIRNDL workshop 2016 and the BIR workshop at ECIR 2016, four extended system reports of the CL-SciSumm Shared Task 2016 and six original research papers submitted via the open call for papers.

Recommending Education Materials for Diabetic Questions Using Information Retrieval Approaches.

BackgroundSelf-management is crucial to diabetes care and providing expert-vetted content for answering patients’ questions is crucial in facilitating patient self-management.ObjectiveThe aim is to investigate the use of information retrieval techniques in recommending patient education materials for diabetic questions of patients.MethodsWe compared two retrieval algorithms, one based on Latent Dirichlet Allocation topic modeling (topic modeling-based model) and one based on semantic group (semantic group-based model), with the baseline retrieval models, vector space model (VSM), in recommending diabetic patient education materials to diabetic questions posted on the TuDiabetes forum. The evaluation was based on a gold standard dataset consisting of 50 randomly selected diabetic questions where the relevancy of diabetic education materials to the questions was manually assigned by two experts. The performance was assessed using precision of top-ranked documents.ResultsWe retrieved 7510 diabetic questions on the forum and 144 diabetic patient educational materials from the patient education database at Mayo Clinic. The mapping rate of words in each corpus mapped to the Unified Medical Language System (UMLS) was significantly different (P<.001). The topic modeling-based model outperformed the other retrieval algorithms. For example, for the top-retrieved document, the precision of the topic modeling-based, semantic group-based, and VSM models was 67.0%, 62.8%, and 54.3%, respectively.ConclusionsThis study demonstrated that topic modeling can mitigate the vocabulary difference and it achieved the best performance in recommending education materials for answering patients’ questions. One direction for future work is to assess the generalizability of our findings and to extend our study to other disease areas, other patient education material resources, and online forums.

Locating bugs without looking back

Bug localisation is a core program comprehension task in software maintenance: given the observation of a bug, e.g. via a bug report, where is it located in the source code? Information retrieval (IR) approaches see the bug report as the query, and the source code files as the documents to be retrieved, ranked by relevance. Such approaches have the advantage of not requiring expensive static or dynamic analysis of the code. However, current state-of-the-art IR approaches rely on project history, in particular previously fixed bugs or previous versions of the source code. We present a novel approach that directly scores each current file against the given report, thus not requiring past code and reports. The scoring method is based on heuristics identified through manual inspection of a small sample of bug reports. We compare our approach to eight others, using their own five metrics on their own six open source projects. Out of 30 performance indicators, we improve 27 and equal 2. Over the projects analysed, on average we find one or more affected files in the top 10 ranked files for 76% of the bug reports. These results show the applicability of our approach to software projects without history.

Bridging the gap: Incorporating a semantic similarity measure for effectively mapping PubMed queries to documents

The main approach of traditional information retrieval (IR) is to examine how many words from a query appear in a document. A drawback of this approach, however, is that it may fail to detect relevant documents where no or only few words from a query are found. The semantic analysis methods such as LSA (latent semantic analysis) and LDA (latent Dirichlet allocation) have been proposed to address the issue, but their performance is not superior compared to common IR approaches. Here we present a query-document similarity measure motivated by the Word Mover’s Distance. Unlike other similarity measures, the proposed method relies on neural word embeddings to compute the distance between words. This process helps identify related words when no direct matches are found between a query and a document. Our method is efficient and straightforward to implement. The experimental results on TREC Genomics data show that our approach outperforms the BM25 ranking function by an average of 12% in mean average precision. Furthermore, for a real-world dataset collected from the PubMed® search logs, we combine the semantic measure with BM25 using a learning to rank method, which leads to improved ranking scores by up to 25%. This experiment demonstrates that the proposed approach and BM25 nicely complement each other and together produce superior performance.

Retrieving and classifying instances of source code plagiarism

Automatic detection of source code plagiarism is an important research field for both the commercial software industry and within the research community. Existing methods of plagiarism detection primarily involve exhaustive pairwise document comparison, which does not scale well for large software collections. To achieve scalability, we approach the problem from an information retrieval (IR) perspective. We retrieve a ranked list of candidate documents in response to a pseudo-query representation constructed from each source code document in the collection. The challenge in source code document retrieval is that the standard bag-of-words (BoW) representation model for such documents is likely to result in many false positives being retrieved, because of the use of identical programming language specific constructs and keywords. To address this problem, we make use of an abstract syntax tree (AST) representation of the source code documents. While the IR approach is efficient, it is essentially unsupervised in nature. To further improve its effectiveness, we apply a supervised classifier (pre-trained with features extracted from sample plagiarized source code pairs) on the top ranked retrieved documents. We report experiments on the SOCO-2014 dataset comprising 12K Java source files with almost 1M lines of code. Our experiments confirm that the AST based approach produces significantly better retrieval effectiveness than a standard BoW representation, i.e., the AST based approach is able to identify a higher number of plagiarized source code documents at top ranks in response to a query source code document. The supervised classifier, trained on features extracted from sample plagiarized source code pairs, is shown to effectively filter and thus further improve the ranked list of retrieved candidate plagiarized documents.

A Literature Review on Patent Information Retrieval Techniques

Objective: Patents are critical intellectual assets for any competitive business. They can prove to be a gold mine if retrieved, analyzed and utilized appropriately. Patentability search is an important step in the patent process and missing out any relevant patent may cause expensive legal consequences. As worldwide patent collection is growing rapidly, retrieval of this enormous knowledge source has become complex and exhaustive. This paper attempts to review the studies carried out in enhancing the relevance effectiveness of patent information retrieval. Method/Analysis: Literature review presents various research works that have been carried out to yield better results in patent retrieval task by refining existing information retrieval techniques or by using standard approaches at the various stages of the patent retrieval task. This work exclusively looks at literatures dealing with retrieval of patent text. Findings: Patent retrieval is not a completely solved research domain and general information retrieval approaches do not prove effective in this domain as patents are special documents posing various retrieval challenges. The review also highlights future research directions and will help researchers working in the domain of patent retrieval. Application/Improvement: Considering the various techniques and frameworks available and their limitations, there is a lot of scope in the field of patent retrieval techniques which makes room for further research to be taken up in this domain. Keywords: Information Retrieval, Patent Retrieval, Patent Search, Query Expansion, Relevance Feedback, Semantic Analysis

A Composite Natural Language Processing and Information Retrieval Approach to Question Answering Using a Structured Knowledge Base

With the inception of the World Wide Web, the amount of data present on the Internet is tremendous. This makes the task of navigating through this enormous amount of data quite difficult for the user. As users struggle to navigate through this wealth of information, the need for the development of an automated system that can extract the required information becomes urgent. This paper presents a Question Answering system to ease the process of information retrieval. Question Answering systems have been around for quite some time and are a sub-field of information retrieval and natural language processing. The task of any Question Answering system is to seek an answer to a free form factual question. The difficulty of pinpointing and verifying the precise answer makes question answering more challenging than simple information retrieval done by search engines. The research objective of this paper is to develop a novel approach to Question Answering based on a composition of conventional approaches of Information Retrieval (IR) and Natural Language processing (NLP). The focus is on using a structured and annotated knowledge base instead of an unstructured one. The knowledge base used here is DBpedia and the final system is evaluated on the Text REtrieval Conference (TREC) 2004 questions dataset.

Market Reaction to News and Investor Attention in Real Time

This paper develops a new framework to study investor attention in real time at high frequency. Using information retrieval approach, we construct a proxy for attention from the Twitter messages of financial experts, hedge funds and portfolio managers around the release of unscheduled news announcements. We then examine how markets react to new information in the absence and presence of attention. On implementing our methodology with high-frequency data for large-cap U.S. stocks, we find evidence that news events receiving attention on social media lead to large and persistent changes in trading activity, volatility and price jumps. When the attention is limited, however, the news effects on such trading patterns tend to be smaller and vanish quickly. With respect to reaction timing, we find that approximately one fourth of the news stories arrive first on Twitter before being reported by Bloomberg newswire. This result suggests that movements prior to news releases may not be explained only by private information, but could also be related to timestamp delays. We control for such potential biases by incorporating attention and correcting newswire timestamps. This adjustment considerably eliminates the pre-announcement effects in the data.

Extracting semantic knowledge from web context for multimedia IR: a taxonomy, survey and challenges

Since its invention, the Web has evolved into the largest multimedia repository that has ever existed. This evolution is a direct result of the explosion of user-generated content, explained by the wide adoption of social network platforms. The vast amount of multimedia content requires effective management and retrieval techniques. Nevertheless, Web multimedia retrieval is a complex task because users commonly express their information needs in semantic terms, but expect multimedia content in return. This dissociation between semantics and content of multimedia is known as the semantic gap. To solve this, researchers are looking beyond content-based or text-based approaches, integrating novel data sources. New data sources can consist of any type of data extracted from the context of multimedia documents, defined as the data that is not part of the raw content of a multimedia file. The Web is an extraordinary source of context data, which can be found in explicit or implicit relation to multimedia objects, such as surrounding text, tags, hyperlinks, and even in relevance-feedback. Recent advances in Web multimedia retrieval have shown that context data has great potential to bridge the semantic gap. In this article, we present the first comprehensive survey of context-based approaches for multimedia information retrieval on the Web. We introduce a data-driven taxonomy, which we then use in our literature review of the most emblematic and important approaches that use context-based data. In addition, we identify important challenges and opportunities, which had not been previously addressed in this area.

Report on the Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2016)

The large scale of scholarly publications poses a challenge for scholars in information seeking and sensemaking. Bibliometric, information retrieval (IR), text mining, and NLP techniques could help in these activities, but are not yet widely used in digital libraries. The BIRNDL workshop was held at the Joint Conference on Digital Libraries (JCDL 2016) in Newark, NJ. It intended to stimulate IR researchers and digital library professionals to elaborate on new approaches in natural language processing, information retrieval, scientometric, and recommendation techniques that can advance the state-of-the-art in scholarly document understanding, analysis, and retrieval at scale. The workshop incorporated three paper sessions and the 2nd edition of the CL-SciSumm Shared Task.

Keyword spotting in doctor's handwriting on medical prescriptions

In this paper, we propose a word spotting based information retrieval approach for medical prescriptions/reports written by doctors. Sometimes due to almost illegible handwriting, it is difficult to understand the medication reports of doctors. This often confuses the patients about the actual medicine/disease names written by doctors and as a consequence they suffer. A medical prescription is generally partitioned into two parts, a printed letterhead part containing the doctor's name, designation, organization name, etc. and a handwritten part where the doctor writes patient's name and report his/her findings and suggests medicine names. There are many significance impacts of the proposed work. For example, such work can be used (i) to develop expert diagnostic systems (ii) to extract information from patient history that can be obtained by this proposed method (iii) to detect wrong medication (iv) to make different statistical analysis of the medicines prescribed by the doctors etc. To extract the information from such document images, first we extract the domain specific knowledge of doctors by identifying department names from the printed text that appears in letterhead part. From the letterhead text, the specialty/expertise of doctors is understood and this helps us to search only relevant prescription documents for word spotting in handwritten portion. Word spotting in letterhead part as well as in handwritten part has been performed using Hidden Markov Model. An efficient MLP (Multilayer Perceptron) based Tandem feature is proposed to improve the performance. From the experiment with 500 prescriptions, we have obtained encouraging results. Information from printed letterhead part improved the word spotting performance in handwritten part, significantly.

An Information Retrieval Approach for Robust Prediction of Road Surface States.

Recently, due to the increasing importance of reducing severe vehicle accidents on roads (especially on highways), the automatic identification of road surface conditions, and the provisioning of such information to drivers in advance, have recently been gaining significant momentum as a proactive solution to decrease the number of vehicle accidents. In this paper, we firstly propose an information retrieval approach that aims to identify road surface states by combining conventional machine-learning techniques and moving average methods. Specifically, when signal information is received from a radar system, our approach attempts to estimate the current state of the road surface based on the similar instances observed previously based on utilizing a given similarity function. Next, the estimated state is then calibrated by using the recently estimated states to yield both effective and robust prediction results. To validate the performances of the proposed approach, we established a real-world experimental setting on a section of actual highway in South Korea and conducted a comparison with the conventional approaches in terms of accuracy. The experimental results show that the proposed approach successfully outperforms the previously developed methods.

Fuzzy rule based profiling approach for enterprise information seeking and retrieval

With the exponential growth of information available on the Internet and various organisational intranets there is a need for profile based information seeking and retrieval (IS&R) systems. These systems should be able to support users with their context-aware information needs. This paper presents a new approach for enterprise IS&R systems using fuzzy logic to develop task, user and document profiles to model user information seeking behaviour. Relevance feedback was captured from real users engaged in IS&R tasks. The feedback was used to develop a linear regression model for predicting document relevancy based on implicit relevance indicators. Fuzzy relevance profiles were created using Term Frequency and Inverse Document Frequency (TF-IDF) analysis for the successful user queries. Fuzzy rule based summarisation was used to integrate the three profiles into a unified index reflecting the semantic weight of the query terms related to the task, user and document. The unified index was used to select the most relevant documents and experts related to the query topic. The overall performance of the system was evaluated based on standard precision and recall metrics which show significant improvements in retrieving relevant documents in response to user queries.

Combining IR and LDA Topic Modeling for Filtering Microblogs

Twitter is a networking micro-blogging service where users post millions of short messages every day. Building multilingual corpora from these microblogs contents can be useful to perform several computational tasks such as opinion mining. However, Twitter data gathering involves the problem of irrelevant included data. Recent literary works have proved that topic models such as Latent Dirichlet Allocation (LDA) are not consistent when applied to short texts like tweets. In order to prune the irrelevant tweets, we investigate in this paper a novel method to improve topics learned from Twitter content without modifying the basic machinery of LDA. This latter is based on a pooling process which combines Information retrieval (IR) approach and LDA.This is achieved through an aggregation strategy based on IR task to retrieve similar tweets in a same cluster. The result of tweet pooling is then used as an input for a basic LDA to overcome the sparsity problem of Twitter content. Empirical results highlight that tweets aggregation based on IR and LDA leads to an interesting improvement in a variety of measures for topic coherence, in comparison to unmodified LDA baseline and a variety of pooling schemes.

Provider-Driven Knowledge Allocation Concept for Improving Technical Repair Tasks in IPS2 Networks

Availability-oriented business models in IPS2 networks obligate providers to cooperate with several service partners that provide maintenance, repair and overhaul (MRO) services in case of a machine malfunction. Currently, these partners, as well as customers, who operate the IPS2, barely have access to technical documents from the product development phase or to the knowledge of other parties within the IPS2 network. Additionally, traditional information retrieval approaches, which are currently state-of-the-art within MRO-related IT systems, render too many irrelevant results and are not suitable for efficient usage in heterogeneous data that differ in wording and structure because of the diverse nature of IPS2 partners. This causes long machine downtimes, as the service technician needs to inspect the machine locally by himself to find the cause(s) for the malfunction. The paper on hand presents a provider-driven knowledge allocation approach to overcome the aforementioned issues by a semantic repair assistant as the gateway to knowledge from all parties within the IPS2 network.