Report Open Access

Natural Language Processing for Scientific Research

Amina Manafli

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="" xmlns="" xsi:schemaLocation="">
  <identifier identifierType="DOI">10.5281/zenodo.2574460</identifier>
      <creatorName>Amina Manafli</creatorName>
      <affiliation>CERN openlab summer student</affiliation>
    <title>Natural Language Processing for Scientific Research</title>
    <subject>CERN openlab</subject>
    <subject>summer student programme</subject>
    <date dateType="Issued">2019-02-21</date>
  <resourceType resourceTypeGeneral="Report"/>
    <alternateIdentifier alternateIdentifierType="url"></alternateIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.2574459</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf"></relatedIdentifier>
    <rights rightsURI="">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
    <description descriptionType="Abstract">&lt;p&gt;The goal of this Openlab project is to create a Smart Data Analytics Platform for Science that will host analytical tools, publish data, share resources, interact with bots, collaborate and build communities of researchers with various backgrounds in a single ecosystem. With this platform we will address solutions of such research problems as finding reliable sources, lack or excess of data, interacting with researchers of different backgrounds and finding partners for research work, creating a set of common definitions and environments. Thus, the underlying goal is the promotion of especially innovative, interdisciplinary research projects, as well as dealing with high entrance barriers of the research field.&lt;/p&gt;

&lt;p&gt;One of the crucial stages of building such platform is creating an intelligent chat bot, able to analyze and answer questions, as accessing and effectively using large amounts of data can be the most challenging and time consuming part of the research work. To do that we need to direct attention to Question Answering models, methods of Natural Language Processing and find a reliable dataset, for their further development and implementation.&lt;/p&gt;</description>
All versions This version
Views 117117
Downloads 8686
Data volume 39.7 MB39.7 MB
Unique views 102102
Unique downloads 7878


Cite as