Building end-to-end dialogue systems using generative hierarchical neural network models

Building end-to-end dialogue systems using generative hierarchical neural network models Serban et al. AAAI 2016 After reading a few of these papers on generative non-goal driven dialogue systems, I’ve ended up both impressed at the early results and the direction they point in, as well as somewhat underwhelmed at the potential for this technology to ... Continue Reading

Incorporating (a) copying mechanism in sequence to sequence learning

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

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

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

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

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