Write a Blog >>
ICPC 2020
Mon 13 - Wed 15 July 2020
co-located with ICSE 2020
Tue 14 Jul 2020 02:00 - 02:15 at ICPC - Session 4: Summalization Chair(s): Venera Arnaoudova

Software developers spend a great deal of time reading and understanding code that is poorly-documented, written by other developers, or developed using differing styles. During the past decade, researchers have investigated techniques for automatically documenting code to improve comprehensibility. In particular, recent advances in deep learning have led to sophisticated summary generation techniques that convert functions or methods to simple English strings that succinctly describe that code’s behavior. However, automatic summarization techniques are assessed using internal metrics such as BLEU scores, which measure natural language properties in translational models, or ROUGE scores, which measure overlap with human-written text. Unfortunately, these metrics do not necessarily capture how machine-generated code summaries actually affect human comprehension or developer productivity. We conducted a human study involving both university students and professional developers (n = 45). Participants reviewed Java methods and summaries and answered established program comprehension questions. In addition, participants completed coding tasks given summaries as specifications. Critically, the experiment controlled the source of the summaries: for a given method, some participants were shown human-written text and some were shown machine-generated text. We found that participants performed significantly better (p = 0.029) using human-written summaries versus machine-generated summaries. However, we found no evidence to support that participants perceive human- and machine-generated summaries to have different qualities. In addition, participants’ performance showed no correlation with the BLEU and ROUGE scores often used to assess the quality of machine-generated summaries. These results suggest a need for revised metrics to assess and guide automatic summarization techniques.

Tue 14 Jul
Times are displayed in time zone: (UTC) Coordinated Universal Time change

01:30 - 02:30: Research - Session 4: Summalization at ICPC
Chair(s): Venera ArnaoudovaWashington State University
icpc-2020-research01:30 - 01:45
Alexander LeClairUniversity Of Notre Dame, Sakib HaqueUniversity of Notre Dame, Lingfei WuIBM Research, Collin McMillanUniversity of Notre Dame
Pre-print Media Attached
icpc-2020-research01:45 - 02:00
Haoran LiuNational University of Defense Technology, Yue YuCollege of Computer, National University of Defense Technology, Changsha 410073, China, Shanshan LiNational University of Defense Technology, Yong GuoNational University of Defense Technology, Deze WangNational University of Defense Technology, Xiaoguang MaoNational University of Defense Technology
Media Attached
icpc-2020-research02:00 - 02:15
Sean StapletonUniversity of Michigan, Yashmeet GambhirUniversity of Michigan, Alexander LeClairUniversity Of Notre Dame, Zachary Eberhart, Westley WeimerUniversity of Michigan, USA, Kevin LeachUniversity of Michigan, Yu HuangUniversity of Michigan
Pre-print Media Attached
icpc-2020-era02:15 - 02:30
Miroslav TushevLouisiana State University, Nash MahmoudLouisiana State University
Media Attached