Submitted by Irene Nascimento (irene.kessia@ufpe.br) on 2016-08-04T18:54:26Z No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) DissertacaoFinalDominiqueDigital.pdf: 1809626 bytes, checksum: 0394869923ec4dde774f79a5ec5290de (MD5) / Made available in DSpace on 2016-08-04T18:54:26Z (GMT). No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) DissertacaoFinalDominiqueDigital.pdf: 1809626 bytes, checksum: 0394869923ec4dde774f79a5ec5290de (MD5) Previous issue date: 2016-02-29 / Facepe / A presente pesquisa se desenvolveu no âmbito do Observatório Temático e Laboratório – Ensino, Tecnologia, Ciência e Informação (OtletCI) com a intensão de avançar na questão de como extrair informação relevante e de como representá-la para fins de recuperação semântica da informação, em particular no caso de textos de publicações científicas em português. Para tanto, como metodologia, investigou-se a tecnologia da busca semântica quanto aos fundamentos teóricos, sua utilidade no contexto do OtletCI e requisitos para aplicação em textos científicos em português. Como experimento, buscou-se explicitar os requisitos da busca semântica para a aplicação em textos científicos, através da análise da extração de relacionamentos semânticos do tipo “causa e efeito” em 60 resumos, em português, de artigos científicos da área de Ciências Agrárias. O estudo apresentou, por meio de considerações de ordem qualitativa e quantitativa, uma comparação entre o processo manual e automático de extração de sentenças de causa e efeito. Esses documentos foram previamente analisados de forma manual, e as sentenças de causa e efeito foram extraídas através da leitura dos resumos. Para o processo automático, com os dados transferidos do software PALAVRAS para a planilha do Excel, foi possível realizar uma programação para localizar sentenças de causa e efeito automaticamente. O objetivo foi comparar as sentenças identificadas diretamente pelo pesquisador e as sentenças reconstruídas automaticamente a partir do conjunto de células programadas. Conclui-se enfatizando que a possibilidade de usar técnicas automáticas acelera o processo de criação e extração de relações de causa e efeito e pode ser usada como alternativa ao processo custoso de identificação manual de informações semânticas. Porém, mais importante que propor uma estrutura de relações de causa e efeito para a construção de sistemas de busca, o que pode-se apontar como o resultado mais expressivo da presente pesquisa é o estabelecimento preliminar de rotinas para a versão automatizada. / This research is developed within the Thematic Observatory and Laboratory - Education, Technology, Science and Information (OtletCI) with the intention to move forward on the question of how to extract relevant information and how to represent it for purposes of semantic retrieval of information, particularly in the case of texts of scientific publications in Portuguese. Therefore, as a methodology, we investigated the semantic search technology based on the theoretical foundations, its usefulness in the context of OtletCI and requirements for application in scientific texts in Portuguese. As an experiment, we tried to clarify the semantic search requirements for the application of scientific texts by analyzing the extraction of semantic relationships such as "cause and effect" in 60 abstracts, in Portuguese, of scientific articles in the area of Agricultural Sciences. The study shows, through qualitative and quantitative considerations, a comparison between manual and automatic extraction process of cause and effect sentences. These documents were previously analyzed manually, and the sentences of cause and effect were extracted by reading the summaries. For automatic process, with data transferred from PALAVRAS software to the Excel spreadsheet, it was possible to carry out a program to find cause and effect sentences automatically. The goal was to buy the sentences identified directly by the researcher and sentences automatically reconstructed from the set of programmed cells. The research concludes emphasizing that the possibility of using automatic techniques accelerates the process of creating and extracting of cause and effect relationship and may be used as an alternative to costly manual process of identifying semantic information. However, more important than to propose a structure of cause and effect relationships for building search engines, we can point out as the most significant result of this research the preliminary establishment of routines for automated version.

Searching is a fundamental task to support research. Current search engines are keyword-based. Semantic technologies promise a next generation of semantic search engines, which will be able to answer questions. Current approaches either apply natural language processing to unstructured text or they assume the existence of structured statements over which they can reason. This work provides a system for combining the classical keyword-based search engines with semantic annotation. Conventional search results are annotated using a customized annotation algorithm, which takes the textual properties and requirements such as speed and scalability into account. The biomedical background knowledge consists of the GeneOntology and Medical Subject Headings and other related entities, e.g. proteins/gene names and person names. Together they provide the relevant semantic context for a search engine for the life sciences. We develop the system GoWeb for semantic web search and evaluate it using three benchmarks. It is shown that GoWeb is able to aid question answering with success rates up to 79%. Furthermore, the system also includes semantic hyperlinks that enable semantic browsing of the knowledge space. The semantic hyperlinks facilitate the use of the eScience infrastructure, even complex workflows of composed web services. To complement the web search of GoWeb, other data source and more specialized information needs are tested in different prototypes. This includes patents and intranet search. Semantic search is applicable for these usage scenarios, but the developed systems also show limits of the semantic approach. That is the size, applicability and completeness of the integrated ontologies, as well as technical issues of text-extraction and meta-data information gathering. Additionally, semantic indexing as an alternative approach to implement semantic search is implemented and evaluated with a question answering benchmark. A semantic index can help to answer questions and address some limitations of GoWeb. Still the maintenance and optimization of such an index is a challenge, whereas GoWeb provides a straightforward system.

Background: Most of our biomedical knowledge is only accessible through texts. The biomedical literature grows exponentially and PubMed comprises over 18.000.000 literature abstracts. Recently much effort has been put into the creation of biomedical ontologies which capture biomedical facts. The exploitation of ontologies to explore the scientific literature is a new area of research. Motivation: When people search, they have questions in mind. Answering questions in a domain requires the knowledge of the terminology of that domain. Classical search engines do not provide background knowledge for the presentation of search results. Ontology annotated structured databases allow for data-mining. The hypothesis is that ontology annotated literature databases allow for text-mining. The central problem is to associate scientific publications with ontological concepts. This is a prerequisite for ontology-based literature search. The question then is how to answer biomedical questions using ontologies and a literature corpus. Finally the task is to automate bibliometric analyses on an corpus of scientific publications. Approach: Recent joint efforts on automatically extracting information from free text showed that the applied methods are complementary. The idea is to employ the rich terminological and relational information stored in biomedical ontologies to markup biomedical text documents. Based on established semantic links between documents and ontology concepts the goal is to answer biomedical question on a corpus of documents. The entirely annotated literature corpus allows for the first time to automatically generate bibliometric analyses for ontological concepts, authors and institutions. Results: This work includes a novel annotation framework for free texts with ontological concepts. The framework allows to generate recognition patterns rules from the terminological and relational information in an ontology. Maximum entropy models can be trained to distinguish the meaning of ambiguous concept labels. The framework was used to develop a annotation pipeline for PubMed abstracts with 27,863 Gene Ontology concepts. The evaluation of the recognition performance yielded a precision of 79.9% and a recall of 72.7% improving the previously used algorithm by 25,7% f-measure. The evaluation was done on a manually created (by the original authors) curation corpus of 689 PubMed abstracts with 18,356 curations of concepts. Methods to reason over large amounts of documents with ontologies were developed. The ability to answer questions with the online system was shown on a set of biomedical question of the TREC Genomics Track 2006 benchmark. This work includes the first ontology-based, large scale, online available, up-to-date bibliometric analysis for topics in molecular biology represented by GO concepts. The automatic bibliometric analysis is in line with existing, but often out-dated, manual analyses. Outlook: A number of promising continuations starting from this work have been spun off. A freely available online search engine has a growing user community. A spin-off company was funded by the High-Tech Gründerfonds which commercializes the new ontology-based search paradigm. Several off-springs of GoPubMed including GoWeb (general web search), Go3R (search in replacement, reduction, refinement methods for animal experiments), GoGene (search in gene/protein databases) are developed.