Language Log: Remembering 9/11/2001

Like almost everyone else, I was happy to learn that Osama bin Laden is now an ex-terrorist; and I was mildly surprised to learn that he had been holed up in a large and luxurious compound located less than a mile by road from PMA Kakul, Pakistan's equivalent of West Point. And last night's announcement made me think about where I was on September 11, 2001. By coincidence, I happened to be on a train entering the outskirts of Washington D.C. just as American Airlines Flight 77 hit the Pentagon. Along with Martha Palmer and Chris Cieri, I was headed for a meeting in Arlington VA about plans for a DARPA project called TIDES ("Translingual Information Detection, Extraction, and Summarization"), whose stated goal was to "to revolutionize the way that information is obtained from human language by enabling people to find and interpret needed information, quickly and effectively, regardless of language or medium". Our train was held up for a while just outside Union Station, and then we were let off and told to evacuate the station immediately. Among the thousands of people milling around outside, all sorts of rumors were circulating: truck bombs at the State Department, gas attacks in the Metro. The crowd carried us along towards the U.S. Capitol building, which is visible from the area outside the station, but it occurred to us that the capitol area might not be the wisest choice of destination at that particular moment. And anyhow, we were supposed to get to Arlington for our meeting. Obviously there were no cabs available, and the Metro station was closed, and it wasn't clear what public transit might be available when, so we started walking west towards our destination. After a while, we found a station from which the Orange line was running towards Virginia — I think it might have been the Foggy Bottom station — and at some point we'd managed to get through to George Doddington or someone else at DARPA by phone, so we made it to the meeting location only somewhat late. The morning's events changed the agenda of our discussions that day, and also charged our work over the next weeks and months, just as they did for many other people. In researching this post, I stumbled across a document that I wrote in March of 2000, summarizing the resources then available for the first year of the TIDES project — and you'll notice that the featured languages are Mandarin, Korean, and Spanish. After our all-day meeting on 9/11/2001, we began working seriously on resources for Arabic-language technology development, including Arabic news text, Arabic/English parallel text, Arabic lexicons and morph analyzers, Arabic broadcast and conversational speech,  Arabic "treebanks", and so on.