Incorporating copying mechanism in sequence to sequence learning Gu et al. 2016, with a side-helping of Neural machine translation by jointly learning to align and translate Bahdanau et al. ICLR 2015 Today’s paper shows how the sequence-to-sequence conversational model we looked at yesterday can be made to seem more natural by including a “copying mechanism” … Continue reading Incorporating (a) copying mechanism in sequence to sequence learning
Month: June 2016
A neural conversation model
A Neural Conversation Model Vinyals & Le, ICML 2015 What happens if you build a bot that is trained on conversational data, and only conversational data: no programmed understanding of the domain at all, just lots and lots of sample conversations…? Building on the sequence to sequence technique that we looked at previously, this is … Continue reading A neural conversation model
A survey of available corpora for building data-driven dialogue systems
A survey of available corpora for building data-driven dialogue systems Serban et al. 2015 Bear with me, it’s more interesting than it sounds :). Yes, this (46-page) paper does include a catalogue of data sets with dialogues from different domains, but it also includes a high level survey of techniques that are used in building … Continue reading A survey of available corpora for building data-driven dialogue systems
On chatbots
No paper today, instead a short piece to tee-up the next mini-series of papers I'll be covering... There’s a lot of excitement around chatbots in the startup community. You can divide this into two broad classes: Consumer-oriented services that want to reach an audience which increasingly spends most of its time in messaging applications. Here … Continue reading On chatbots
Transactional data structure libraries
Transactional Data Structure Libraries Spiegelman et al. PLDI 2016 Today’s choice won a distinguished paper award at the recent PLDI 2016 conference. Spiegelman et al. show how to add transactional support to in-memory concurrent data structure libraries in a way that doesn’t sacrifice performance. Since the advent of the multi-core revolution, many efforts have been … Continue reading Transactional data structure libraries
AI^2: Training a big data machine to defend
AI2: Training a big data machine to defend Veeramachaneni et al. IEEE International conference on Big Data Security, 2016 Will machines take over? The lesson of today’s paper is that we’re better off together. Combining AI with HI (human intelligence, I felt like we deserved an acronym of our own ;) ) yields much better … Continue reading AI^2: Training a big data machine to defend
Hacking Blind
Hacking Blind Bittau et al. IEEE Symposium on Security and Privacy, 2014 (With thanks to Chris Swan for pointing this paper out to me a few months ago…) The ingenuity of attackers continues to amaze. Today’s paper presents an interesting trade-off: security or availability, pick one! (*) The work you put in to make sure … Continue reading Hacking Blind
