Natural Language Techniques Research Articles

Text Mining Approach for Discovering Useful Knowledge from Information Sources of E-Waste

Proposed method introduces a K-Nearest Neighbor method by using relevance vector machine which finds the entities and related information on waste materials to make processing of waste materials more domain friendly. A corpus analysis was incorporated to support the extraction of accurate information through elimination of unrelated tokens. The distribution of weights to terms was determined through a vector space model. Parallel verification on various entities was carried out while testing. This reduces the time taken for mapping and discovering useful information from documents (dataset) of e-waste management. Recent computer aided tools cannot check for consistency and correctness of faulty requirement definition, this paper introduces text processing method using natural language technique; this enables effective maintenance and utilization of waste materials by presenting task specific information through computer-assisted text mining and analysis process.

Application of Natural Language Processing for Information Retrieval

Through a comprehensive analysis of using natural language processing in information retrieval, we compared the effects with the various natural language techniques for information retrieval precision in this paper. This is for the tasks of more suitable as well as accurate results of natural language processing.

Classification of cancer-related death certificates using machine learning

Cancer monitoring and prevention relies on the critical aspect of timely notification of cancer cases. However, the abstraction and classification of cancer from the free-text of pathology reports and other relevant documents, such as death certificates, exist as complex and time-consuming activities. In this paper, approaches for the automatic detection of notifiable cancer cases as the cause of death from free-text death certificates supplied to Cancer Registries are investigated. A number of machine learning classifiers were studied. Features were extracted using natural language techniques and the Medtex toolkit. The numerous features encompassed stemmed words, bi-grams, and concepts from the SNOMED CT medical terminology. The baseline consisted of a keyword spotter using keywords extracted from the long description of ICD-10 cancer related codes. Death certificates with notifiable cancer listed as the cause of death can be effectively identified with the methods studied in this paper. A Support Vector Machine (SVM) classifier achieved best performance with an overall Fmeasure of 0.9866 when evaluated on a set of 5,000 freetext death certificates using the token stem feature set. The SNOMED CT concept plus token stem feature set reached the lowest variance (0.0032) and false negative rate (0.0297) while achieving an F-measure of 0.9864. The SVM classifier accounts for the first 18 of the top 40 evaluated runs, and entails the most robust classifier with a variance of 0.001141, half the variance of the other classifiers. The selection of features significantly produced the most influences on the performance of the classifiers, although the type of classifier employed also affects performance. In contrast, the feature weighting schema created a negligible effect on performance. Specifically, it is found that stemmed tokens with or without SNOMED CT concepts create the most effective feature when combined with an SVM classifier.

"Analyzing gossip in workplace email" by Tanushree Mitra and Eric Gilbert, with Ching-man Au Yeung as coordinator

We spend a significant part of our lives chatting about other people. In other words, we all gossip. Although sometimes a contentious topic, various researchers have shown gossip to be fundamental to social life---from small groups to large, formal organizations. Adopting the Enron email dataset and natural language techniques, we present the first study of gossip in a large CMC corpus. We find that workplace gossip is common at all levels of the organizational hierarchy, with people most likely to gossip with their peers and that it is more likely for an email to contain gossip if targeted to a smaller audience. Also, gossip appears as often in personal exchanges as it does in formal business communication. Exploring the sentiment of gossip, we observe that gossip is in fact quite often negative. Our study provides empirical evidence of an under-researched yet important societal phenomenon and provides empirical insights by testing existing gossip theories originating from anthropology, on a real world large email dataset.

Exploring the use of new technologies in participation practices in legislation

The use of information technology in governance generally, and in legislative processes specifically, has emerged as a significant trend over the last decade. The design and mobilization of such technologies in diverse settings have shown significant progress over time; however, such technologies and related practices continue to reflect limitations and difficulties. This study seeks to address a number of existing limitations in the use of technology in e-legislation. Using an applied research design combined with rapid applications development, the project examines avenues for e-participation in the current investigation-legislative practices of the Blue Ribbon Committee of the Philippine Senate. The project's applications development phase uses Web 2.0 as a platform, and combines it with electronic document and natural language techniques, thus enabling a shift from dominantly information dissemination approaches to multi-directional exchanges supported by new techniques like the automatic categorization of comments. The study explores the potential and the limitations of new technologies, and highlights the need for new institutional policies and capacity building to ensure the success and sustainability of e-participation initiatives. The technologies created can be considered as possible future directions by lawmakers in countries that are seeking to move beyond e-legislation practices that focus primarily on uni-directional information dissemination, into more participatory approaches.

정보검색에서 자연어처리 응용효과 분석

In this paper, some applications of natural language processing techniques for information retrieval have been introduced, but the results are known not to be satisfied. In order to find the roles of some classical natural language processing techniques in information retrieval and to find which one is better we compared the effects with the various natural language techniques for information retrieval precision, and the experiment results show that basic natural language processing techniques with small calculated consumption and simple implementation help a small for information retrieval. Senior high complexity of natural language processing techniques with high calculated consumption and low precision can not help the information retrieval precision even harmful to it, so the role of natural language understanding may be larger in the question answering system, automatic abstract and information extraction.

Natural language-based user interface for mobile devices with limited resources

In this paper, we propose a natural language-based interface model to enable a user to articulate a request without having any specific knowledge about a mobile device. In consideration of the very limited computing and memory capacity of the mobile device and to keep the development cost low, the proposed model does not depend on typical natural language techniques, but on a ranking technique, that is simplified based on the mathematical derivation process with the following assumptions. One assumption is that a device control command consists of a function and its parameters. The other assumption is that the parameter is represented as few predictable patterns, whereas the function can be represented as various sentence patterns. To deal with these various sentence patterns, the proposed model selects the top ranked command candidate with the highest score after generating all possible candidates with their scores. Furthermore, the ranking score function is designed to achieve a high discriminative capability by the simulation of the process of generating every candidate. Experimental results show that the proposed model with 2.9 megabytes performs at 96.27% accuracy, which is slightly lower than 97.06% of the baseline model with 135.2 megabytes.

Biomedical question answering: A survey

Objectives In this survey, we reviewed the current state of the art in biomedical QA (Question Answering), within a broader framework of semantic knowledge-based QA approaches, and projected directions for the future research development in this critical area of intersection between Artificial Intelligence, Information Retrieval, and Biomedical Informatics. Materials and methods We devised a conceptual framework within which to categorize current QA approaches. In particular, we used “semantic knowledge-based QA” as a category under which to subsume QA techniques and approaches, both corpus-based and knowledge base (KB)-based, that utilize semantic knowledge-informed techniques in the QA process, and we further classified those approaches into three subcategories: (1) semantics-based, (2) inference-based, and (3) logic-based. Based on the framework, we first conducted a survey of open-domain or non-biomedical-domain QA approaches that belong to each of the three subcategories. We then conducted an in-depth review of biomedical QA, by first noting the characteristics of, and resources available for, biomedical QA and then reviewing medical QA approaches and biological QA approaches, in turn. The research articles reviewed in this paper were found and selected through online searches. Results Our review suggested the following tasks ahead for the future research development in this area: (1) Construction of domain-specific typology and taxonomy of questions (biological QA), (2) Development of more sophisticated techniques for natural language (NL) question analysis and classification, (3) Development of effective methods for answer generation from potentially conflicting evidences, (4) More extensive and integrated utilization of semantic knowledge throughout the QA process, and (5) Incorporation of logic and reasoning mechanisms for answer inference. Conclusion Corresponding to the growth of biomedical information, there is a growing need for QA systems that can help users better utilize the ever-accumulating information. Continued research toward development of more sophisticated techniques for processing NL text, for utilizing semantic knowledge, and for incorporating logic and reasoning mechanisms, will lead to more useful QA systems.

Natural Language Processing for Foreign Languages Learning as Computer-based Learning Tools

This paper outlines a framework to use computer and natural language techniques for various levels of learners to learn foreign languages in Computer-based Learning environment. We propose some ideas for using the computer as a practical tool for learning foreign language where the most of courseware is generated automatically. We then describe how to build Computer Based Learning tools, discuss its effectiveness, and conclude with some possibilities using on-line resources.

Automated Analysis and Codification of Free Text Pathology Reports

Introduction: Epidemiologic research in hematologic malignancies has been dependent on three sources of data; SEER data, patients accrued to large clinical trials, and databases generated by individual providers or departments. Each of these sets of data have major limitations. In theory the adoption of computerized databases by pathology departments and the adoption of electronic medical records should have greatly expanded the ability to identify patients with particular types of malignancies. In practice the need to manually classify tens of thousands of free text pathology reports has made this resource unavailable. We have developed a computer program to extract and codify the final diagnoses described in free text pathology reports according to the World Health Organization (WHO) classification of hematologic malignancies. This enables us to identify sets of cases of desired pathologies for further study.Methods: A medical records review protocol was approved by the Dana Farber Harvard Cancer Center Institutional Review Board. Using our clinical lymphoma database we collected records of patients at Massachusetts General Hospital (MGH) Cancer Center who carried a diagnosis of follicular lymphoma (FL) and diffuse large B-cell lymphoma (DLBCL).The program is modified from one developed to extract diagnoses from discharge summaries in a different context [Long, AMIA 2007]. The approach is to use punctuation and a few words (conjunctions and some common verbs) to divide the text into phrases and then use a search procedure to find the most specific matching concepts in the UMLS (Unified Medical Language System). The search uses all of the alternate phrases for each concept as included in the UMLS normalized string table, matched against normalized subphrases from the text. We mapped UMLS concepts to the desired WHO concepts. To ensure a complete list of UMLS concepts we used the hierarchical relations in the UMLS and examined both more specific and more general concepts for possible inclusion in the search. Since not all diseases in a report are part of the diagnosis, we developed pattern matching procedures to identify the parts of the pathology report containing the final diagnosis (as opposed to “note” or “clinical data” that might have patient specific clinical information that are not diagnosed in the current pathology report). The program also uses a strategy for identifying modifiers that change the sense of the diagnosis (“suggestive of”, “rule out”, “no”, etc.) to exclude diseases that are absent or only possible.Results: We used the system to identify cases of FL and DLBCL and compared the results to lists of cases generated manually. The current program was 90% accurate in automatically classifying pathology reports as describing follicular lymphoma. Of 150 cases of FL, the program found 133 (eg, MALIGNANT LYMPHOMA, FOLLICLE CENTER) and 3 were in reports not available to the program (133/147 90%). Of 100 DLBCL cases, 76 were available and 63 were found (83%) (eg, HISTIOCYTE-RICH LARGE B-CELL LYMPHOMA). There were several reasons for the missed cases. Most commonly (13) the diagnosis was not in the identified diagnosis section, either because the section was divided by a note or the diagnosis was in an addendum. Only 3 cases had phrases not found in the UMLS. For 2 others, the program missed because the phrase was not contiguous (eg, B-CELL LYMPHOMA, CONSISTENT WITH FOLLICLE CENTER CELL TYPE). In 5 of the DLBCL cases the stated final diagnosis was more general than the desired diagnoses and 2 of the FL cases were listed as “strongly suggestive” which the program concluded was not a definite diagnosis.Discussion: This program is useful for identifying desired cohorts of cases and can be improved with better identification of the sections containing the diagnosis, the addition of a few missing phrases as they are discovered, and the addition of techniques for handling common discontinuities in disease descriptions (eg, allowing “consistent with” in the phrase). We have shown that very simple natural language techniques are sufficient to extract most of the desired disease descriptions from free text reports, enabling automatic selection of cases and greatly enhancing the usefulness of large repositories of pathology reports.

Bio-Ontology and text: bridging the modeling gap.

Natural language processing (NLP) techniques are increasingly being used in biology to automate the capture of new biological discoveries in text, which are being reported at a rapid rate. Yet, information represented in NLP data structures is classically very different from information organized with ontologies as found in model organisms or genetic databases. To facilitate the computational reuse and integration of information buried in unstructured text with that of genetic databases, we propose and evaluate a translational schema that represents a comprehensive set of phenotypic and genetic entities, as well as their closely related biomedical entities and relations as expressed in natural language. In addition, the schema connects different scales of biological information, and provides mappings from the textual information to existing ontologies, which are essential in biology for integration, organization, dissemination and knowledge management of heterogeneous phenotypic information. A common comprehensive representation for otherwise heterogeneous phenotypic and genetic datasets, such as the one proposed, is critical for advancing systems biology because it enables acquisition and reuse of unprecedented volumes of diverse types of knowledge and information from text. A novel representational schema, PGschema, was developed that enables translation of phenotypic, genetic and their closely related information found in textual narratives to a well-defined data structure comprising phenotypic and genetic concepts from established ontologies along with modifiers and relationships. Evaluation for coverage of a selected set of entities showed that 90% of the information could be represented (95% confidence interval: 86-93%; n = 268). Moreover, PGschema can be expressed automatically in an XML format using natural language techniques to process the text. To our knowledge, we are providing the first evaluation of a translational schema for NLP that contains declarative knowledge about genes and their associated biomedical data (e.g. phenotypes). http://zellig.cpmc.columbia.edu/PGschema

A text-mining system for knowledge discovery from biomedical documents

This paper describes the application of IBM TAKMI® for Biomedical Documents to facilitate knowledge discovery from the very large text databases characteristic of life science and healthcare applications. This set of tools, designated MedTAKMI, is an extension of the TAKMI (Text Analysis and Knowledge MIning) system originally developed for text mining in customer-relationship-management applications. MedTAKMI dynamically and interactively mines a collection of documents to obtain characteristic features within them. By using multifaceted mining of these documents together with biomedically motivated categories for term extraction and a series of drill-down queries, users can obtain knowledge about a specific topic after seeing only a few key documents. In addition, the use of natural language techniques makes it possible to extract deeper relationships among biomedical concepts. The MedTAKMI system is capable of mining the entire MEDLINE® database of 11 million biomedical journal abstracts. It is currently running at a customer site.

Extracting information from free-text aircraft repair notes

For every problem mentioned by crew members in an aircraft log book, an associated repair action note is entered in the same log book by a maintenance technician after the problem has been handled. These hand-written repair notes, subsequently transcribed into a database, give an account of the actions undertaken by the technicians to fix the problems. Written in a free-text format with peculiar linguistic characteristics, including many arbitrary abbreviations and missing auxiliaries, they contain valuable information that can be used for decision support methods such as case-based reasoning. We use natural language techniques in our information extraction system to analyze the structure and contents of these notes in order to determine the pieces of equipment involved in a repair and what was done to them. Lexical information and domain knowledge are extracted from an electronic version of the illustrated parts catalog for the particular airplane, and are used at different stages of the process, from the morpholexical analysis to the evaluation of the semantic expression generated by the syntactical analyzer.

The Text REtrieval Conferences (TRECs): Providing a Test‐Bed for Information Retrieval Systems

Les congres de la TREC (Text REtrieval Conferences) ont pour sujet d'etude les methodes de recherche d'information ainsi que l'evaluation de ces methodes. La TREC fournit des collection-test

Using linguistic knowledge in view integration: Toward a third generation of tools

This paper addresses the problem of view integration in a CASE tool environment which is aiming at the elaboration of a conceptual schema of an application. The previous integration tools were mainly based on syntax and structure comparisons. A new generation of intelligent tools is now arising, assuming that view integration algorithms must also capture the deep semantics of the objects represented in the views. Dealing with the semantics of the objects is now a realistic objective, thanks to the research results obtained in the natural language area. This paper presents the definition of a view integration algorithm enhanced by the use of linguistic knowledge. This algorithm mainly consists of a semantic unification of views which are described using an extended entity-relationship model. It is combined with natural language techniques such as Fillmore's semantic cases and Sowa's conceptual graphs, supported by semantic dictionaries.

Overview of the Second Text Retrieval Conference (TREC-2)

The second Text Retrieval Conference (TREC-2) was held in August, 1993, and was attended by about 150 people involved in 31 participating groups. The goal of the conference was to bring research groups together to discuss their work on a new large test collection. There was a large variation of retrieval techniques reported on, including methods using automatic thesaurii, sophisticated term weighting, natural language techniques, relevance feedback, and advanced pattern matching. As results had been run through a common evaluation package, groups were able to compare the effectiveness of different techniques, and discuss how differences between the systems affected performance.

Toward an integral multi-file on-line bibliographic database

The work described represented an attempt to lay the basis for an integral multi-file bibliographic database and, in particular, to derive a common retrieval vocabulary for data bases received from many different sources in a single carrier language. The creation of an experimental database of some 44 000 references with abstracts, as originally announced in NASA STAR during 1973 and 1974, is described. This data base could be searched either by the classical controlled voca bulary technique or by means of an improved natural language technique using terms in the titles and/or abstracts, or any combination of these. This improved technique was based on three discrete aspects: the development of an index file of uniterms from the natural language by means of an iterative, machine-aided procedure; the incorporation of meaningful phrases culled from the same source; and the derivation of an RT-analogue, on the basis of statistical term association, called Associated Concepts. The experimental database was submitted to a comparative evaluation of controlled and natural language retrieval performance by an external group directed by Prof. Cyril Cleverdon and com prising expert documentalists from several large European information centres with long experience of on-line search ing ; the results of this evaluation are reported.