BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Net2Text: Query-Guided Summarization of Network Forwarding Behavio
 rs
DTSTART:20180517T133000
DTEND:20180517T143000
DTSTAMP:20260502T075603Z
UID:28334b18400d577dfd71f429d77be51c1bd31866419801be0ba881d6
CATEGORIES:Conferences - Seminars
DESCRIPTION:By Dana Drachsler Cohen\n\nAbstract\nToday network operators s
 pend a significant amount of time struggling to understand how their netwo
 rk forwards traffic. Even simple questions such as "How is my network hand
 ling Google traffic?" often require operators to manually bridge large sem
 antic gaps between lowlevel forwarding rules distributed across many route
 rs and the corresponding high-level insights.\n\nIn this talk\, I will int
 roduce Net2Text\, a system which assists network operators in reasoning ab
 out network-wide forwarding behaviors. Out of the raw forwarding state and
  a query expressed in natural language\, Net2Text automatically produces s
 uccinct summaries\, also in natural language\, which efficiently capture n
 etwork-wide semantics. The key insight is to pose the problem of summarizi
 ng the network forwarding state as an optimization problem that aims to ba
 lance coverage\, by describing as many paths as possible\, and explainabil
 ity\, by maximizing the information provided. As this problem is NP-hard\,
  I will show an approximation algorithm which generates summaries based on
  a sample of the forwarding state\, with marginal loss of quality. I will 
 experimentally show that Net2Text generates high-quality interpretable sum
 maries of the entire forwarding state of hundreds of routers with full rou
 ting tables\, in few seconds only.\n\nJoint work with Rüdiger Birkner\, L
 aurent Vanbever\, and Martin Vechev.\n\nBio\nDana is an ETH Postdoctoral F
 ellow in the department of Computer Science at ETH Zurich.\nHer research f
 ocuses on applying programming languages techniques to bring rigor to othe
 r areas including deep learning models\, blockchains\, and computer networ
 ks.\nShe obtained her PhD from the Computer Science Department at the Tech
 nion in 2017.\n\nMore information\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR