code2seq: Generating Sequences from Structured Representations of Code
The ability to generate natural language sequences from source code snippets has a variety of applications such as code summarization, documentation, and retrieval. Sequence-to-sequence (seq2seq) models, adopted from neural machine-translation (NMT), have achieved state-of-the-art performance on these tasks by treating source code as a sequence of tokens. We present CODE2SEQ: an alternative approach that leverages the syntactic structure of programming languages to better encode source code.
Eran Yahav is an associate professor at the Computer Science Department, Technion, Israel. Prior to that, he was a research staff member at the IBM T.J. Watson Research Center (2004-2010). He received his Ph.D. from Tel Aviv University (2005) and his B.Sc. from the Technion in 1996. His research interests include program analysis, program synthesis and program verification. Eran is a recipient of the prestigious Alon Fellowship for Outstanding Young Researchers, the Andre Deloro Career Advancement Chair in Engineering, the ERC Consolidator Grant as well as multiple best paper awards at various conferences.
Sat 6 AprDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
16:00 - 17:00
|Decidable Reasoning for Verification: How Far Can You EPR?|
Oded Padon Stanford University
|code2seq: Generating Sequences from Structured Representations of Code|
Eran Yahav Technion