Domain-specific Information Retrieval Research Articles

Natural Language Processing-Assisted Literature Retrieval and Analysis for Combination Therapy in Cancer.

Despite advances in molecular therapeutics, few anticancer agents achieve durable responses. Rational combinations using two or more anticancer drugs have the potential to achieve a synergistic effect and overcome drug resistance, enhancing antitumor efficacy. A publicly accessible biomedical literature search engine dedicated to this domain will facilitate knowledge discovery and reduce manual search and review. We developed RetriLite, an information retrieval and extraction framework that leverages natural language processing and domain-specific knowledgebase to computationally identify highly relevant papers and extract key information. The modular architecture enables RetriLite to benefit from synergizing information retrieval and natural language processing techniques while remaining flexible to customization. We customized the application and created an informatics pipeline that strategically identifies papers that describe efficacy of using combination therapies in clinical or preclinical studies. In a small pilot study, RetriLite achieved an F1 score of 0.93. A more extensive validation experiment was conducted to determine agents that have enhanced antitumor efficacy in vitro or in vivo with poly (ADP-ribose) polymerase inhibitors: 95.9% of the papers determined to be relevant by our application were true positive and the application's feature of distinguishing a clinical paper from a preclinical paper achieved an accuracy of 97.6%. Interobserver assessment was conducted, which resulted in a 100% concordance. The data derived from the informatics pipeline have also been made accessible to the public via a dedicated online search engine with an intuitive user interface. RetriLite is a framework that can be applied to establish domain-specific information retrieval and extraction systems. The extensive and high-quality metadata tags along with keyword highlighting facilitate information seekers to more effectively and efficiently discover knowledge in the combination therapy domain.

Transferrable Framework Based on Knowledge Graphs for Generating Explainable Results in Domain-Specific, Intelligent Information Retrieval

In modern industrial systems, collected textual data accumulates over time, offering an important source of information for enhancing present and future industrial practices. Although many AI-based solutions have been developed in the literature for a domain-specific information retrieval (IR) from this data, the explainability of these systems was rarely investigated in such domain-specific environments. In addition to considering the domain requirements within an explainable intelligent IR, transferring the explainable IR algorithm to other domains remains an open-ended challenge. This is due to the high costs, which are associated with intensive customization and required knowledge modelling, when developing new explainable solutions for each industrial domain. In this article, we present a transferable framework for generating domain-specific explanations for intelligent IR systems. The aim of our work is to provide a comprehensive approach for constructing explainable IR and recommendation algorithms, which are capable of adopting to domain requirements and are usable in multiple domains at the same time. Our method utilizes knowledge graphs (KG) for modeling the domain knowledge. The KG provides a solid foundation for developing intelligent IR solutions. Utilizing the same KG, we develop graph-based components for generating textual and visual explanations of the retrieved information, taking into account the domain requirements and supporting the transferability to other domain-specific environments, through the structured approach. The use of the KG resulted in minimum-to-zero adjustments when creating explanations for multiple intelligent IR algorithms in multiple domains. We test our method within two different use cases, a semiconductor manufacturing centered use case and a job-to-applicant matching one. Our quantitative results show a high capability of our approach to generate high-level explanations for the end users. In addition, the developed explanation components were highly adaptable to both industrial domains without sacrificing the overall accuracy of the intelligent IR algorithm. Furthermore, a qualitative user-study was conducted. We recorded a high level of acceptance from the users, who reported an enhanced overall experience with the explainable IR system.

Semantics-based key concepts identification for documents indexing and retrieval on the web

Bridging the semantic gap on the web remains one of the crucial challenges for current horizontal and domain-specific information retrieval systems. This challenge becomes even more pronounced when users express their information needs using short queries that are formulated using a few number of keywords, therefore relying on keywords for indexing web documents results in degrading the quality of the returned results. In this article, we introduce an approach that employs knowledge captured by large-scale knowledge resources to identify key query terms and retrieve semantically-relevant documents. In this context, key terms are mapped to their semantic correspondences and variable term weights are assigned based on the semantic and taxonomic relations for each term. To demonstrate the effectiveness of the proposed approach, we have conducted experimental evaluation using Glasgow's NPL test collections. Findings indicate that the effectiveness has improved against four conventional similarity metrics that are based on the bag-of-words similarity model.

Research on We—Media Information Retrieval Technology of Knowledge Map

As the development direction of information retrieval technology gradually evolves toward the relationship of search entities, traditional relational databases are difficult to satisfy, and graph databases are specifically created to handle the relationships between data. This article explains the basic concept of graph database, and takes the example of domain-specific database information retrieval as an example, analyzes its advantages and disadvantages, and analyzes the challenges faced by the graph database in full-text information retrieval.

Domain specific concept ontologies and text summarization as hierarchical fuzzy logic ranking indicator on malay text corpus

<span>Ranking function is a predictive algorithm that is used to establish a simple ordering of documents according to its relevance. This step is critical because the results’ quality of a Domain Specific Information Retrieval (IR) such as Hadith Information Retrieval is fundamentally dependent of the ranking function. A Hierarchical Fuzzy Logic Controller of <em>Mamdani</em>-type Fuzzy Inference System has been built to define the ranking function, based on the Malay Information retrieval’s BM25 Model. The model examines three-inputs (Ontology BM25 Score, Fabrication Rate of Hadith and Shia Rate of Hadith) and four-output values of Final Ranking Score which consist of three triangular membership functions. The proposed system has outperformed the BM25 original score and the Vector Space Model (VM) on 16 queries, while the BM25 original score and Vector Space Model only yield better result in 9 and 2 queries respectively on the P@10, %no measures and MAP. P@10 represent the values of Precision at Rank 10 P@10), %no measures represent the percentage of queries with no relevant documents in the top ten retrieved and MAP represents Mean Average Precision of the queries. The results show the proposed system have capability to demote negative documents and move up the relevant documents in the ranking list and its capability to recall unseen document with the application of ontology in text retrieval. For the future works, the researcher would like to apply the usage of other Malay Semantic elements and another corpus for positive ranking indicator.</span>

Enhanced Explicit Semantic Analysis for Product Model Retrieval in Construction Industry

With the rapidly growing number of online product models in construction industry, there is an urgent need for developing effective domain-specific information retrieval methods. Explicit semantic analysis (ESA) is a method that automatically extracts concept-based features from human knowledge repositories for semantic retrieval. This avoids the requirement of constructing and maintaining an explicitly formalized ontology. However, since domain-specific knowledge repositories are relatively small, the available terminologies are insufficient and concepts have coarse granularity. In this paper, we propose an enhanced ESA method for product model retrieval in construction industry. The major enhancements for the original ESA method consist of two parts. First, a novel concept expansion algorithm is proposed to solve the problem caused by insufficient terminologies. Second, a reranking algorithm is developed to solve the problem caused by coarse granularity of concepts. Experimental results show that our method significantly improves the performance of product model retrieval and outperforms the state-of-the-art methods. Our method is also applicable to product retrieval in other engineering domain if a specific knowledge repository is provided in that domain.

Design and development of semantic web-based system for computer science domain-specific information retrieval

Summary In semantic web-based system, the concept of ontology is used to search results by contextual meaning of input query instead of keyword matching. From the research literature, there seems to be a need for a tool which can provide an easy interface for complex queries in natural language that can retrieve the domain-specific information from the ontology. This research paper proposes an IRSCSD system (Information retrieval system for computer science domain) as a solution. This system offers advanced querying and browsing of structured data with search results automatically aggregated and rendered directly in a consistent user-interface, thus reducing the manual effort of users. So, the main objective of this research is design and development of semantic web-based system for integrating ontology towards domain-specific retrieval support. Methodology followed is a piecemeal research which involves the following stages. First Stage involves the designing of framework for semantic web-based system. Second stage builds the prototype for the framework using Protege tool. Third Stage deals with the natural language query conversion into SPARQL query language using Python-based QUEPY framework. Fourth Stage involves firing of converted SPARQL queries to the ontology through Apache's Jena API to fetch the results. Lastly, evaluation of the prototype has been done in order to ensure its efficiency and usability. Thus, this research paper throws light on framework development for semantic web-based system that assists in efficient retrieval of domain-specific information, natural language query interpretation into semantic web language, creation of domain-specific ontology and its mapping with related ontology. This research paper also provides approaches and metrics for ontology evaluation on prototype ontology developed to study the performance based on accessibility of required domain-related information.

Clustering-Based Topical Web Crawling for Topic-Specific Information Retrieval Guided by Incremental Classifier

Today more and more information on the Web makes it difficult to get domain-specific information due to the huge amount of data sources and the keywords that have few features. Anchor texts, which contain a few features of a specific topic, play an important role in domain-specific information retrieval, especially in Web page classification. However, the features contained in anchor texts are not informative enough. This paper presents a novel incremental method for Web page classification enhanced by link-contexts and clustering. Directly applying the vector of anchor text to a classifier might not get a good result because of the limited amount of features. Link-context is used first to obtain the contextual information of the anchor text. Then, a hierarchical clustering method is introduced to cluster feature vectors and content unit, which increases the length of a feature vector belonging to one specific class. Finally, incremental SVM is proposed to get the final classifier and increase the accuracy and efficiency of a classifier. Experimental results show that the performance of our proposed method outperforms the conventional topical Web crawler in Harvest rate and Target recall.

A hybrid approach to finding relevant social media content for complex domain specific information needs

While contemporary semantic search systems offer to improve classical keyword-based search, they are not always adequate for complex domain specific information needs. The domain of prescription drug abuse, for example, requires knowledge of both ontological concepts and “intelligible constructs” not typically modeled in ontologies. These intelligible constructs convey essential information that include notions of intensity, frequency, interval, dosage, and sentiments, which could be important to the holistic needs of the information seeker. In this paper, we present a hybrid approach to domain specific information retrieval (or knowledge-aware search) that integrates ontology-driven query interpretation with synonym-based query expansion, and domain specific rules, to facilitate search. Our framework is based on a context-free grammar (CFG) that defines the query language of constructs interpretable by the search system. The grammar provides two levels of semantic interpretation: (1) a top-level CFG that facilitates retrieval of diverse textual patterns, which belong to broad templates and (2) a low-level CFG that enables interpretation of specific expressions that belong to such patterns. These low-level expressions occur as concepts from four different categories of data: (1) ontological concepts, (2) concepts in lexicons (such as emotions and sentiments), (3) concepts in lexicons with only partial ontology representation, called lexico-ontology concepts (such as side effects and routes of administration (ROA)), and (4) domain specific expressions (such as date, time, interval, frequency, and dosage) derived solely through rules. Our approach is embodied in a novel Semantic Web platform called PREDOSE, which provides search support for complex domain specific information needs in prescription drug abuse epidemiology. When applied to a corpus of over 1 million drug abuse-related web forum posts, our search framework proved effective in retrieving relevant documents when compared with three existing search systems.

Clustering-based topical Web crawling using CFu-tree guided by link-context

Topical Web crawling is an established technique for domain-specific information retrieval. However, almost all the conventional topical Web crawlers focus on building crawlers using different classifiers, which needs a lot of labeled training data that is very difficult to labelmanually. This paper presents a novel approach called clustering-based topical Web crawling which is utilized to retrieve information on a specific domain based on link-context and does not require any labeled training data. In order to collect domain-specific content units, a novel hierarchical clustering method called bottom-up approach is used to illustrate the process of clustering where a new data structure, a linked list in combination with CFu-tree, is implemented to store cluster label, feature vector and content unit. During clustering, four metrics are presented. First, comparison variation (CV) is defined to judge whether the closest pair of clusters can be merged. Second, cluster impurity (CIP) evaluates the cluster error. Then, the precision and recall of clustering are also presented to evaluate the accuracy and comprehensive degree of the whole clustering process. Link-context extraction technique is used to expand the feature vector of anchor text which improves the clustering accuracy greatly. Experimental results show that the performance of our proposed method overcomes conventional focused Web crawlers both in Harvest rate and Target recall.

A Hybrid Approach to Finding Relevant Social Media Content for Complex Domain Specific Information Needs

While contemporary semantic search systems offer to improve classical keyword-based search, they are not always adequate for complex domain specific information needs. The domain of prescription drug abuse, for example, requires knowledge of both ontological concepts and “intelligible constructs” not typically modeled in ontologies. These intelligible constructs convey essential information that include notions of intensity, frequency, interval, dosage and sentiments, which could be important to the holistic needs of the information seeker. In this paper, we present a hybrid approach to domain specific information retrieval that integrates ontology-driven query interpretation with synonym-based query expansion and domain specific rules, to facilitate search in social media on prescription drug abuse. Our framework is based on a context-free grammar (CFG) that defines the query language of constructs interpretable by the search system. The grammar provides two levels of semantic interpretation: 1) a top-level CFG that facilitates retrieval of diverse textual patterns, which belong to broad templates and 2) a low-level CFG that enables interpretation of specific expressions belonging to such textual patterns. These low-level expressions occur as concepts from four different categories of data: 1) ontological concepts, 2) concepts in lexicons (such as emotions and sentiments), 3) concepts in lexicons with only partial ontology representation, called lexico-ontology concepts (such as side effects and routes of administration (ROA)), and 4) domain specific expressions (such as date, time, interval, frequency and dosage) derived solely through rules. Our approach is embodied in a novel Semantic Web platform called PREDOSE, which provides search support for complex domain specific information needs in prescription drug abuse epidemiology. When applied to a corpus of over 1 million drug abuse-related web forum posts, our search framework proved effective in retrieving relevant documents when compared with three existing search systems.

A quantitative evaluation of query expansion in domain specific information retrieval

AbstractThis paper describes our different retrieval approaches conducted on a cultural heritage (CH) content test‐collection. In our study, our main objective is to measure the relative merit of various query expansion and semantic enrichment techniques. To do so we considered different strategies based on blind‐query expansion as well as using external resource, namely Wikipedia. In using external knowledge bases we consider different strategies in order to select the most appropriate concepts to be added to the initial query. Our results show that expansion with both pseudo‐relevant documents and external resources improve the retrieval. While the impact of expansion using an external resource is more significant.

BioinQA: metadata-based multi-document QA system for addressing the issues in biomedical domain

Despite the availability of large amount of biomedical literature; extracting relevant information catering to the exact need of the user has been difficult in the absence of efficient domain specific information retrieval tools. Biomedical question answering (QA) systems require special techniques to address domain-specific issues, since a wide variety of user-groups having different information needs; terminology and level of understanding, etc., may access the information. While specialised information retrieval tools are not suitable for beginners, general purpose search engines are not intelligent enough to respond to domain specific questions. This paper presents an intelligent QA system that answers natural language questions while adapting itself to the level of user. The system constructs answers from multiple documents for complex comparison seeking questions. The system utilises metadata knowledge for addressing specific biomedical domain concerns like heterogeneity, acronyms, etc. Experiments ...

Toward a semantic granularity model for domain-specific information retrieval

Both similarity-based and popularity-based document ranking functions have been successfully applied to information retrieval (IR) in general. However, the dimension of semantic granularity also should be considered for effective retrieval. In this article, we propose a semantic granularity-based IR model that takes into account the three dimensions, namely similarity, popularity, and semantic granularity, to improve domain-specific search. In particular, a concept-based computational model is developed to estimate the semantic granularity of documents with reference to a domain ontology. Semantic granularity refers to the levels of semantic detail carried by an information item. The results of our benchmark experiments confirm that the proposed semantic granularity based IR model performs significantly better than the similarity-based baseline in both a bio-medical and an agricultural domain. In addition, a series of user-oriented studies reveal that the proposed document ranking functions resemble the implicit ranking functions exercised by humans. The perceived relevance of the documents delivered by the granularity-based IR system is significantly higher than that produced by a popular search engine for a number of domain-specific search tasks. To the best of our knowledge, this is the first study regarding the application of semantic granularity to enhance domain-specific IR.

Q&A 커뮤니티 기반 전문영역 검색을 위한 프레임워크

본 연구는 Q&A(question and answer:질문-답변) 커뮤니티 사이트에서 집단지성의 특성을 추출하고, 이를 이용한 전문지식이나 정보 검색을 위한 전문영역 검색(vertical search) 을 위한 프레임워크를 제안한다, 많은 Q&A 사이트로부터 얻은 정보는 하나의 집단지성의 형태로 볼 수 있으며, 전문영역 검색은 특정 전문 분야 검색에 초점을 맞춘 검색 방법이다. 제안된 프레임워크는 사용자가 검색하고자 하는 질의어와 연관되어 있는 질문(question)과 답변(answer) 정보를 이용하여 관련어를 확장한 후, 이를 기반으로 전문지식을 요구하는 특정 도메인분야에 적용하게 된다. 이를 통해 일반 검색 엔진을 통해 검색된 검색 결과보다 유용한 정보와 전문적인 상세정보까지 제공해 줄 수 있다. This study suggests a framework which extracts features of collective intelligence from social Q&A community sites and takes advantage of those features upon vertical search for domain specific knowledge or information retrieval. One source of collective intelligence on the internet is the question and answer(Q&A) data available from many Q&A sites. Vertical search is focused on searching special areas or specific domains. This paper proposes a framework for extending the relevant terms by using Q&A information connected with query that the user wants to retrieve, and then applies them to specific domain field that requires professional and detailed knowledge.

Quantifying the impact of concept recognition on biomedical information retrieval

In ad hoc querying of document collections, current approaches to ranking primarily rely on identifying the documents that contain the query terms. Methods such as query expansion, based on thesaural information or automatic feedback, are used to add further terms, and can yield significant though usually small gains in effectiveness. Another approach to adding terms, which we investigate in this paper, is to use natural language technology to annotate – and thus disambiguate – key terms by the concept they represent. Using biomedical research documents, we quantify the potential benefits of tagging users’ targeted concepts in queries and documents in domain-specific information retrieval. Our experiments, based on the TREC Genomics track data, both on passage and full-text retrieval, found no evidence that automatic concept recognition in general is of significant value for this task. Moreover, the issues raised by these results suggest that it is difficult for such disambiguation to be effective.

TREC-CHEM

Over the past decades, significant progress has been made in Information Retrieval (IR), ranging from efficiency and scalability to theoretical modeling and evaluation. However, many grand challenges remain. Recently, more and more attention has been paid to the research in domain specific IR applications, as evidenced by the organization of Genomics and Legal tracks in the Text REtrieval Conference (TREC). Now it is the right time to carry out large scale evaluations on chemical datasets in order to promote the research in chemical IR in general and chemical Patent IR in particular. Accordingly, we organize a chemical IR track in TREC (TREC-CHEM) in order to address the challenges in chemical and patent IR. This paper describes these challenges and the accomplishments of the first year and opens up the discussions for the next year.

Domain specific Information retrieval system with a correspondence graph applied to car diagnosis

Domain specific Information retrieval system with a correspondence graph applied to car diagnosis

A decision-theoretic approach to the evaluation of information retrieval systems

Evaluation research on information retrieval (IR) systems has thus far been narrowly focused and disjointed. This research attempts to narrow the gap by providing a comprehensive and integrated multiple criteria decision-theoretic approach for the evaluation of IR systems. The approach, which is based on the Analytic Hierarchy Process (AHP), is illustrated in the context of a domain-specific IR system. The novelty of this approach lies in the focus on the user aspect and the application of decision-making theories in the IR field.

A decision-theoretic approach to the evaluation of information retrieval systems

Evaluation research on information retrieval (IR) systems has thus far been narrowly focused and disjointed. This research attempts to narrow the gap by providing a comprehensive and integrated multiple criteria decision-theoretic approach for the evaluation of IR systems. The approach, which is based on the Analytic Hierarchy Process (AHP), is illustrated in the context of a domain-specific IR system. The novelty of this approach lies in the focus on the user aspect and the application of decision-making theories in the IR field.