Ambry: LinkedIn’s scalable geo-distributed object store

Ambry: LinkedIn’s scalable geo-distributed object store Noghabi et al. SIGMOD ’16 Ambry is LinkedIn’s blob store, designed to handle the demands of a modern social network: Hundreds of millions of users continually upload and view billions of diverse massive media objects, from photos and videos to documents. These large media objects, called blobs, are uploaded … Continue reading Ambry: LinkedIn’s scalable geo-distributed object store

Ten challenges in highly-interactive dialog systems

Ten challenges in highly-interactive dialog systems Ward &De Vault AAAI 2015 It’s time to end our look into the technology behind chatbots and dialog systems - there’s a huge crop of SIGMOD 2016 papers waiting to be explored for starters! To end the mini-series, today I’ve chosen a 2015 position paper from Ward and De … Continue reading Ten challenges in highly-interactive dialog systems

Multi-domain dialog state tracking using recurrent neural networks

Multi-domain dialog state tracking using recurrent neural networks a Mrksic et al. 2015 Suppose you want to build a chatbot for a domain in which you don’t have much data yet. What can you do to bootstrap your dialog state tracking system? In today’s paper the authors show how to transfer knowledge across domains, and … Continue reading Multi-domain dialog state tracking using recurrent neural networks

Machine learning for dialog state tracking: a review

Machine learning for dialog state tracking: a review Henderson MLSLP 2015 Today we turn our attention to the task of figuring out, potentially over multiple interactions with a bot, what it is the user is requesting the bot to do. This task goes by the name of Dialog State Tracking, and it’s something that Matthew … Continue reading Machine learning for dialog state tracking: a review

End-to-end learning of semantic role labeling using recurrent neural networks

End-to-end learning of semantic role labeling using recurrent neural networks Zhou & Xu International joint conference on Natural Language Processing, 2015 Collobert’s 2011 paper that we looked at yesterday represented a turning point in NLP in which they achieved state of the art performance on part-of-speech tagging (POS), chunking, and named entity recognition (NER) using … Continue reading End-to-end learning of semantic role labeling using recurrent neural networks