Recognizing software bug-specific named entity in software bug repository

Recognizing software bug-specific named entity in software bug repository

主要内容：

1. 考虑在软件bug领域下如何进一步识别bug命名实体
2. 给bug做一个分类，并考虑到叠加关系的情况（通过general，component，special进行区分）
3. 模型并没有多大的创新，使用了CRF+Skip-gram
4. 整体流程如下图：
   

语料库标注

基于B2IO的范式，采用Brat¹工具

标注的范式表格

Reference

@inproceedings{DBLP:conf/iwpc/ZhouLSG18,
author = {Cheng Zhou and
Bin Li and
Xiaobing Sun and
Hongjing Guo},
title = {Recognizing software bug-specific named entity in software bug repository},
booktitle = {Proceedings of the 26th Conference on Program Comprehension, {ICPC}
2018, Gothenburg, Sweden, May 27-28, 2018},
pages = {108–119},
year = {2018},
crossref = {DBLP:conf/iwpc/2018},
url = {https://doi.org/10.1145/3196321.3196335},
doi = {10.1145/3196321.3196335},
timestamp = {Tue, 26 Feb 2019 17:40:20 +0100},
biburl = {https://dblp.org/rec/bib/conf/iwpc/ZhouLSG18},
bibsource = {dblp computer science bibliography, https://dblp.org}
}

---

1. Brat: a Web-based Tool for NLP-Assisted Text Annotation. In EACL 2012 ↩︎