All posts tagged: discovery

Drinker’s Digest II. Weekly flux: space-wine, mimicry and ships

You can’t step into the same river twice they say. Most experience is like that. You can’t taste the same wine twice. Circumstances change: wines get older, palates soften. Here we stick WineQuant’s wine-word taster into some promising parts of the world-wide-web of wine and take two snapshots in time. So what can happen in a week? In the first picture, which is from last week, a set of Decanter articles on China features prominently as a cluster of points at the top right hand corner: Cabernet Sauvignon, Merlot and Pinot Noir vines were launched as cargo on the Tiangong-2 Rocket in September 2016. Space-wine enthusiasts hope that the stressful conditions will trigger mutations that will make the vines hardier, better able to cope with the weather in places like Ningxia. Farthest away in space from the articles on China and at the top left of last week’s map, we pick out a cluster centered on the changing fortunes of winery investor Charles Banks. A bit of history: Banks became known to the wine world …

Drinker’s Digest: Intro & Decanter on 23/06

The internet of wine is vast: tasting notes, news, gossip, prices, analysis and buying advice. I feel that I can’t read as much of it as I’d like to. Like you I have habits and filters to cope with the quantity: bookmarks, favorites, online networks and communities. And so I am part of the tangled world-wide web of words. The internet of wine is rich, yet we are creatures of habit. It takes time to discover a source of knowledge, to feel and become familiar with its grooves. It’s easier to roam well-known territory, to tend my bookmarks, look out for trusted ‘likes’, like the one above. When I do venture out into unfamiliar undergrowth, the journeys are tangled and haphazard. Tabs accumulate with trails followed and abandoned. It would be easier with a map. I could scan its features in seconds and plan my route. I could focus my journeys and I’d be able to see more in less time. In previous posts we visualized tasting notes. We ran wine-reviews through algorithms that look for …

Tasting Algos, Spring I.

You shall know a word by the company it keeps (Firth, J. R.) It’s reasonable to believe that wine words which occur in similar contexts have related meanings for the tasters who wrote them down. Join us on our machine assisted journey to explore the unplumbed depths of wine writing with natural language processing (NLP) techniques. As machine learning meets human taste, let’s strive to make the symbiosis fruitful: with NLP algorithms and computing power at our fingertips, here’s an opportunity to discover more about how we record sensory impressions with words. We’ve trained neural network models on a large corpus of wine notes to recognize words by the company they keep. The results are fascinating. It’s spring-time, so let’s start by investigating a couple of fresh, uplifting, seasonal descriptors that come to mind naturally. Each word comes with its top 10 contextual associates picked out by our machine assistant.  The score (cosine similarity) indicates how close the association is. Blossoms ‘peaches’, 0.64 ‘wax’, 0.64 ‘poached’, 0.62, ‘bursts’, 0.61 ‘hazelnuts’, 0.61 ‘apples’, 0.61 ‘buttered’, 0.60 ‘apricots’, 0.60 ‘candle’, …