NIPS 2006 -- NLP Tutorial -- 3 [Read-Only]

„„„„„„„„„„„„„„„„„„„„NOTEMachine Learning for NLP:New Developments and ChallengesThese slides are still incompleteA more complete version will be posted at a later date at:http://www.cs.berkeley.edu/~klein/nips-tutorialDan KleinComputer Science DivisionUniversity of California at BerkeleyWhat is NLP? Speech SystemsAutomatic Speech Recognition (ASR)Audio in, text outSOTA: 0.3% for digit strings, 5% dictation, 50%+ TVFundamental goal: deep understand of broad language “Speech Lab”End systems that we want to build:Ambitious: speech recognition, machine translation, information Text to Speech (TTS)extraction, dialog interfaces, question answering… Text in, audio outModest: spelling correction, text categorization… SOTA: totally intelligible (if sometimes unnatural)Sometimes we’re also doing computational linguisticsMachine Translation Information ExtractionInformation Extraction (IE)Unstructured text to database entriesNew York Times Co. named Russell T. Lewis, 45, president and general manager of its flagship New York Times newspaper, responsible for all business-side activities. He was executive vice president and deputy general manager. He succeeds Lance R. Primis, who in September was named president and chief operating officer of the parent. Person Company Post StateRussell T. Lewis New York Times president and general startnewspaper managerRussell T. Lewis New York Times executive vice president endnewspaperLance R. ...