Tag Archives: Wikipedia

Semantic Search using Wikipedia

Today I gave my master’s thesis talk in the Technion as part of my master’s duties. Actually, the non-buzzword title is “Concept-Based Information Retrieval using Explicit Semantic Analysis”, but that’s not a very click-worthy post title :-)…

The whole thing went far better than I expected – the room was packed, the slides flew smoothly (and quickly too, luckily Shaul convinced me to add some spare slides just in case), and I ended up with over 10 minutes of Q&A (an excellent sign for a talk that went well…)

Click to view on Slideshare

BTW – anybody has an idea how to embed slideshare into a hosted blog? doesn’t seem to work…

In the footsteps of Napoleon

A while back I made a sweep through some old CDs we had at home to rip them, and rediscovered some old favorites. One of these was Al Stewart’s Roads to Moscow, an epic ballad telling the story of Operation Barbarossa in the eyes of a Russian soldier. Al Stewart tells the story in such a beautiful and captivating way, that I could feel the tragedy for both fighting sides, had my own personal existence not depended on the final outcome. I found myself skipping straight to Wikipedia for more reading, chilling stories of Hubris on both sides, endless ‘almost’ moments, the tragic betrayel by Stalin of his own war heroes, and the inevitable comparison with Napoleon’s accounts:

The Germans were nearing exhaustion, they also began to recall Napoleon’s invasion of Russia. General Günther Blumentritt noted in his diary: “They remembered what happened to Napoleon’s Army. Most of them began to re-read Caulaincourt’s grim account of 1812. That had a weighty influence at this critical time in 1941. I can still see Von Kluge trudging through the mud from his sleeping quarters to his office and standing before the map with Caulaincourt’s book in his hand”

Only later did I consider searching, rather than going straight to Wikipedia. Surprisingly, there were quite a few quality articles in the top 10, so I tried to figure what inhibited my strong search habits. Two reasons came up –

  1. Wikipedia’s mass of editors and strict adherence to NPOV, ensures me I’m not wasting my time on someone’s subjective view
  2. Habit – I knew what coverage and scope to expect in Wikipedia

No wonder, then, that Google got concerned about this habit of visiting adsense-less, top search result pages, tried to tackle it with Google Knol, but failed. But then, revisiting my reason #1 above shows very clearly why the individualist knol concept will always fail against Wikipedia as an objective information source, no matter how much weight Google puts behind it. Someone’s hubris at Google followed in the footsteps of another Napoleon, too.