March 23, 2021 Conference paper Open Access

Yitagesu, Sofonias; Zhang, Xiaowang; Feng, Zhiyong; Li, Xiaohong; Xing, Zhenchang

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.4632063</identifier>
  <creators>
    <creator>
      <creatorName>Yitagesu, Sofonias</creatorName>
      <givenName>Sofonias</givenName>
      <familyName>Yitagesu</familyName>
      <affiliation>Tianjin University, China</affiliation>
    </creator>
    <creator>
      <creatorName>Zhang, Xiaowang</creatorName>
      <givenName>Xiaowang</givenName>
      <familyName>Zhang</familyName>
      <affiliation>Tianjin University, China</affiliation>
    </creator>
    <creator>
      <creatorName>Feng, Zhiyong</creatorName>
      <givenName>Zhiyong</givenName>
      <familyName>Feng</familyName>
      <affiliation>Tianjin University, China</affiliation>
    </creator>
    <creator>
      <creatorName>Li, Xiaohong</creatorName>
      <givenName>Xiaohong</givenName>
      <familyName>Li</familyName>
      <affiliation>Tianjin University, China</affiliation>
    </creator>
    <creator>
      <creatorName>Xing, Zhenchang</creatorName>
      <givenName>Zhenchang</givenName>
      <familyName>Xing</familyName>
      <affiliation>Australian National University, Australia</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Automatic Part-of-Speech Tagging for Security Vulnerability Descriptions</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2021</publicationYear>
  <subjects>
    <subject>Fine-Tuning, Part-of-Speech tagging, Unsupervised word embedding, Security vulnerability descriptions</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2021-03-23</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="ConferencePaper"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/4632063</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.4632062</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Abstract&amp;mdash;In this paper, we study the problem of part-of-speech (POS) tagging for security vulnerability descriptions (SVD). In&lt;br&gt;
contrast to newswire articles, SVD often contains a high-level natural language description of the text composed of mixed&lt;br&gt;
language studded with codes, domain-specific jargon, vague language, and abbreviations. Moreover, training data dedicated&lt;br&gt;
to security vulnerability research is not widely available. Existing neural network-based POS tagging has often relied on manually&lt;br&gt;
annotated training data or applying natural language processing (NLP) techniques, suffering from two significant drawbacks. The&lt;br&gt;
former is extremely time-consuming and requires labor-intensive feature engineering and expertise. The latter is inadequate to&lt;br&gt;
identify linguistically-informed words specific to the SVD domain. In this paper, we propose an automatic approach to assign POS&lt;br&gt;
tags to tokens in SVD. Our approach uses the character-level representation to automatically extract orthographic features and&lt;br&gt;
unsupervised word embeddings to capture meaningful syntactic and semantic regularities from SVD. The character level representations are then concatenated with the word embedding as a combined feature, which is then learned and used to predict&lt;br&gt;
the POS tagging. To deal with the issue of the poor availability of annotated security vulnerability data, we implement a finetuning approach. Our approach provides public access to a POS annotated corpus of &amp;sim;8M tokens, which serves as a training dataset in this domain. Our evaluation results show a significant improvement in accuracy (17.72%-28.22%) of POS tagging in SVD over the current approaches.&lt;/p&gt;</description>
  </descriptions>
</resource>