ACL 2019, held in Florence, Italy, was the largest ACL to date. The event was spread out over 8 halls, with simultaneous talks (up to 6 simultaneous tracks) and a poster session in every slot. ACL was also co-located with several (almost too many) excellent workshops, each of which could warrant several days of attendance in their own right. In this post, we'll attempt to condense the conference into a quick description of interesting posters and talks that we (Vinit and Daniel) had the chance to see. »

In this post, we offer an introduction to vector-based sentence representations, which have proven to be extremely useful for various NLP tasks in recent years. We'll dive a bit into the history of sentence representation learning and follow this up with a survey of recent methods - both supervised and unsupervised. We'll also attempt to consolidate the results reported for all of our surveyed approaches and discuss recently-proposed sentence representation evaluation frameworks. »

This year’s EMNLP was bigger than any ACL conference ever before. With around 2500 attendees, a couple of hundred talks, and a few hundred posters, it was unthinkable to try and keep track of everything. Nevertheless, in this day-after-the-conference blog, bubbling over with ideas, we will do just that. Starting from the first workshop and concluding with Johan Bos’ Moment of Meaning, we will attempt to offer a convincing account of what happened in Brussels and what it meant for the future of NLP. »