![]() ![]() ![]() The noise was indescribable, he told me, the constant shelling from sea to shore, the bombers and fighters just overhead, pounding the headlands and interior, the ship's own battery firing rapidly. The officer waved to him just as a salvo from a German coastal artillery battery obliterated the bridge. When he was older he told the story of an identical Liberty ship, one with a young officer just like him on its bridge, steaming in the same circle a few hundred yards away. The shells throwing geysers of water high in the sky when they missed, and red, brown, and black explosions when they struck an unlucky target. German shells rained down on them as they circled waiting the signal to go in and offload the cans of gasoline stacked in the hold and all over the decks. Then seeing the beaches wreathed in smoke thick as fog, caused by the constant shelling from hundreds of American, British, and Canadian warships assembled offshore for the invasion: battleships, cruisers, destroyers, mine sweepers, PT boats and on and on. He described the steady roar that night of the C-47s carrying paratroopers who would start the invasion by dropping on key bridges and crossroads before the landings began at dawn. ![]() Filled to capacity with gasoline cans, sailing to Sword Beach to take part in the D-Day landings on June 6th, 1944. These results are useful for understanding humor and also in the design of more engaging conversational agents in text and multimodal (vision+text) systems.Īs part of this work, a large set of cartoons and captions is being made available to the community so that other researchers may experiment further.Seventy-nine years ago tonight, my wonderful father in law, Hayes Tate, just twenty-two, was second officer on a Liberty ship in the English Channel. The researchers were able to show that negative sentiment, human-centeredness, and lexical centrality most strongly match the funniest captions, followed by positive sentiment. Then, they performed Amazon Mechanical Turk experiments in which they asked Turkers to judge which of the selected captions is funnier. They used each of these methods to independently rank all captions from the New Yorker’s corpus of cartoons and selected the top captions for each method. They developed a set of unsupervised methods for ranking captions based on features such as originality, centrality, sentiment, concreteness, grammatically, human-centeredness, etc. In their study, the researchers took a computational approach to studying the contest to gain insights into what differentiates funny captions from the rest. The contest has become a cultural phenomenon and has generated a lot of discussion as to what makes a cartoon funny. They pick the top three submitted captions and ask the readers to pick the weekly winner. Each week, the editors post a cartoon and ask readers to come up with a funny caption for it. ![]() The New Yorker publishes a weekly Cartoon Caption Contest has been running for more than 10 years. Their paper, posted on and entitled “Humor in Collective Discourse: Unsupervised Funniness Detection in the New Yorker Cartoon Caption Contest,” describes their findings. Dragomir Radev and his former student and alumnus Rahul Jha, together with colleagues from Yahoo! Labs and Columbia University, recently teamed up with New Yorker Cartoon Editor Bob Mankoff to take a computational approach to understanding humor. How do we know what’s funny, and can machine learning and big data techniques be used to identify the essence of humor? ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |