DOC PREVIEW
Columbia COMS W4705 - Final Review and Wrap Up

This preview shows page 1-2-15-16-31-32 out of 32 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 32 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 32 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 32 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 32 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 32 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 32 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 32 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

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 ProcessingFinal: December 17th 1:10-4, 1024 Mudd◦Closed book, notes, electronicsDon’t forget courseworks evaluation: only 4% so far have done it.Office hours as usual next weekAnnouncementsNatural Language for the Web (Spring 10)◦TIME CHANGE: Thursdays 6-8pmSpoken Language Processing (Spring 10)Statistical natural language (Spring 10)Machine translation (Fall 10)What’s Next?Seminar style classReading original papers◦Presentation and discussionSemester long projectThe 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 WebSpeech phenomena◦Acoustics, intonation, disfluencies, laughter◦Tools for speech annotation and analysisSpeech technologies◦Text-to-Speech◦Automatic Speech Recognition◦Speaker Identification◦Dialogue SystemsCS 4706: Spoken Language ProcessingChallenges for speech technologies◦Pronunciation modeling◦Modeling accent, phrasing and contour◦Spoken cues to Discourse segmentationInformation statusTopic detectionSpeech actsTurn-takingFun stuff: emotional speech, charismatic speech, deceptive speech….Stop by and visitCS AdvisingRecommendation lettersResearch projectAdvice on applying to graduate schoolAn experiment done by outgoing ACL President Bonnie Dorrhttp://www.youtube.com/v/k4cyBuIsdy4http://www.youtube.com/v/CUSxWsj7y0whttp://www.youtube.com/v/Nz_sSvXBdfkWhat is Computational Linguistics? (NLP)Fill-in-the-blank/multiple choiceShort answerProblem solvingEssayComprehensive (Will cover the full semester)Form of Final ExamMeaning Representations◦Predicate/argument structure and FOPCThematic 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 variablesNon-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 questionsRepresenting time: ◦Reichenbach ’47Utterance time (U): when the utterance occursReference time (R): the temporal point-of-view of the utteranceEvent 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, achievementsWordnet: pros and consTypes 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 RelationsWhat 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 wordsWhat features are used?EvaluationSemi-supervised◦Use bootstrapping: how?Baselines◦ Lesk method◦ Most frequent meaningWord Sense DisambiguationInformation Extraction◦Three types of IE: NER, relation detection, QA◦Three approaches: statistical sequence labeling, supervised, semi-supervised◦Learning patterns: Using WikipediaUsing GoogleLanguage modeling approachInformation Retrieval◦TF/IDF and vector-space model◦Precision, recall, F-measureRobust semanticsWhat 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 QuestionReferring expressions, anaphora, coreference, antecedentsTypes 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◦PragmaticsAlgorithms for reference resolution◦Hobbes – most recent mention◦Lappin and Leas◦CenteringChallenges for MT◦Orthographical◦Lexical ambiguity◦Morphological◦Translational divergencesMT Pyramid◦Surface, transfer, interlingua◦Statistical?Word alignmentPhrase alignmentEvaluation strategies◦Bleu◦Human levels of grading criteriaMTHow 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

Columbia COMS W4705 - Final Review and Wrap Up

Download Final Review and Wrap Up
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Final Review and Wrap Up and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Final Review and Wrap Up 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?