Slide 1AnnouncementsWhat’s Next?Natural Language for the WebCS 4706: Spoken Language ProcessingSlide 6Slide 7Stop by and visitWhat is Computational Linguistics? (NLP)Form of Final ExamSemanticsSlide 12Sample questionsSlide 14Word RelationsWordsEyeSlide 17Word Sense DisambiguationRobust semanticsIE QuestionReferenceSlide 22MTMT QuestionsSlide 25GenerationAn example grammarA simple inputDiscourseDiscourse Structure for Generation and SummarizationSlide 31Another take: What is Computational Linguistics?Final Review and Wrap UpCS4705Natural Language ProcessingFinal: December 17th 1:10-4, 1024 Mudd◦Closed book, notes, electronicsDon’t forget courseworks evaluation: only 4% so far have done it.Office hours as usual next weekAnnouncementsNatural Language for the Web (Spring 10)◦TIME CHANGE: Thursdays 6-8pmSpoken Language Processing (Spring 10)Statistical natural language (Spring 10)Machine translation (Fall 10)What’s Next?Seminar style classReading original papers◦Presentation and discussionSemester long projectThe web contains huge amounts of unstructured documents, both written and spoken, in many languages. This class will study applications of natural language processing to the web. We will study search techniques that incorporate language, cross-lingual search, advanced summarization and question answering particularly for new media such as blogs, social networking, sentiment analysis and entailment. For many of these, we will look at multi-lingual approaches.Natural Language for the WebSpeech phenomena◦Acoustics, intonation, disfluencies, laughter◦Tools for speech annotation and analysisSpeech technologies◦Text-to-Speech◦Automatic Speech Recognition◦Speaker Identification◦Dialogue SystemsCS 4706: Spoken Language ProcessingChallenges for speech technologies◦Pronunciation modeling◦Modeling accent, phrasing and contour◦Spoken cues to Discourse segmentationInformation statusTopic detectionSpeech actsTurn-takingFun stuff: emotional speech, charismatic speech, deceptive speech….Stop by and visitCS AdvisingRecommendation lettersResearch projectAdvice on applying to graduate schoolAn experiment done by outgoing ACL President Bonnie Dorrhttp://www.youtube.com/v/k4cyBuIsdy4http://www.youtube.com/v/CUSxWsj7y0whttp://www.youtube.com/v/Nz_sSvXBdfkWhat is Computational Linguistics? (NLP)Fill-in-the-blank/multiple choiceShort answerProblem solvingEssayComprehensive (Will cover the full semester)Form of Final ExamMeaning Representations◦Predicate/argument structure and FOPCThematic roles and selectional restrictionsAgent/ Patient: George hit Bill. Bill was hit by GeorgeGeorge assassinated the senator. *The spider assassinated the flySemantics)}(),(),()({, yCarxyHadThingxSHaverxHavingyx Compositional semantics◦Rule 2 rule hypothesis◦E.g. x y E(e) (Isa(e,Serving) ^ Server(e,y) ^ Served(e,x))◦Lambda notationλ x P(x): λ + variable(s) + FOPC expression in those variablesNon-compositional semantics◦Metaphor: You’re the cream in my coffee. ◦Idiom: The old man finally kicked the bucket. ◦Deferred reference: The ham sandwich wants his check.Give the FOPC meaning representation for:◦John showed each girl an apple. ◦All students at Columbia University are tall. Given a sentence and a syntactic grammar, give the semantic representation for each word and the semantic annotations for the grammar. Derive the meaning representation for the sentence.Sample questionsRepresenting time: ◦Reichenbach ’47Utterance time (U): when the utterance occursReference time (R): the temporal point-of-view of the utteranceEvent time (E): when events described in the utterance occurGeorge is eating a sandwich.-- E,R,U George will eat a sandwich?Verb aspect◦Statives, activities, accomplishments, achievementsWordnet: pros and consTypes of word relations◦Homonymy: bank/bank◦Homophones: red/read◦Homographs: bass/bass◦Polysemy: Citibank/ The bank on 59th street◦Synonymy: big/large◦Hyponym/hypernym: poodle/dog◦Metonymy: waitress: the man who ordered the ham sandwich wants dessert./the ham sandwich wants dessert.◦The White House announced the bailout plan.Word RelationsWhat were some problems with WordNet that required creating their own dictionary?What are considerations about objects have to be taken into account when generating a picture that depicts an “on” relation?WordsEyeImplicit Constraint. The vase is on the nightstand. The lamp is next to the vase.Time flies like an arrow.Supervised methods◦Collocational◦Bag of wordsWhat features are used?EvaluationSemi-supervised◦Use bootstrapping: how?Baselines◦ Lesk method◦ Most frequent meaningWord Sense DisambiguationInformation Extraction◦Three types of IE: NER, relation detection, QA◦Three approaches: statistical sequence labeling, supervised, semi-supervised◦Learning patterns: Using WikipediaUsing GoogleLanguage modeling approachInformation Retrieval◦TF/IDF and vector-space model◦Precision, recall, F-measureRobust semanticsWhat are the advantages and disadvantages of using exact pattern matching versus using flexible pattern matching for relation detection?Given a Wikipedia page for a famous person, show how you would derive the patterns for place of birth.If we wanted to use a language modeler to answer definition questions (e.g., “What is a quark?”), how would we do it?IE QuestionReferring expressions, anaphora, coreference, antecedentsTypes of NPs, e.g. pronouns, one-anaphora, definite NPs, ….Constraints on anaphoric reference◦Salience◦Recency of mention◦Discourse structure◦Agreement◦Grammatical functionReference◦Repeated mention◦Parallel construction◦Verb semantics/thematic roles◦PragmaticsAlgorithms for reference resolution◦Hobbes – most recent mention◦Lappin and Leas◦CenteringChallenges for MT◦Orthographical◦Lexical ambiguity◦Morphological◦Translational divergencesMT Pyramid◦Surface, transfer, interlingua◦Statistical?Word alignmentPhrase alignmentEvaluation strategies◦Bleu◦Human levels of grading criteriaMTHow does lexical ambiguity affect MT? Compute the Bleu score for the following example, using unigrams and bigrams:◦Translation: One moment later Alice went down the hole.◦References:
View Full Document