2015年10月_zypandora

原创 Week5-3The exponential problem in parsing

Attachment ambiguitiesA key parsing decision is how we “attach various constituents”.ExampleEvery number(a constituent) can freely attach to different places, and it is the source of the exponential

2015-10-22 18:04:52 253

原创 Week5-2Empirical/data driven approach to parsing

Classical parsingsymbolic grammer(CFG)…The problem and its solutionThe rise of annotated dataBuilding a treebank seems slower and less useful than building a grammarBut:

2015-10-22 17:22:44 234

原创 Week5-1Syntactic structure: Constituency vs Dependency

2 views of linguistic structureConstituencyPhrase structure orgnizes words into nested constituentsHow do we know what is a constituent? Distribution: a constituent behaves as a unit that can appear

2015-10-22 17:08:22 289

原创 Week1-5Why is NLP hard?

ExamplesTime flies like an arrow.InterpretationsMore ExamplesSyntax vs. semantics*Little a has Mary lambSyntactically wrong?Colorless green idea sleeps furiouslySyntactically ri

2015-10-13 17:39:52 303

原创 Week1-4Administration

4 major parts and 3 goalsAvailable BooksOther coursesThe alphabet soupResearch in NLP

2015-10-13 17:19:38 188

原创 Week1-3Funny Sentences

Silly SentencesMore ambiguous headlines Prepositional phrase attachment!!Ambiguity RecommendationsLexical ambiguityStructural ambiguityScope ambiguityOther …

2015-10-13 17:01:55 297

原创 Week1-2Examples of text

Understanding a news storyCurrent eventBackground eventSpeculationPropertyPronominal referenceGenres of textWebsitePapersMedical recordsLiterary textsPoetry is even harder!!

2015-10-13 16:51:14 205

原创 Week1-1Introduction

IntroductionThe course will be more introductoryMore focus on linguisticsWhat is NLP? The study of computational treatment of natural language(human language).Modern ApplicationsSearch enginesQ

2015-10-13 16:41:02 269

原创 Lecture6-3Bounding Function: inductive cases

Estimating B(4,3)B(4,3) B(4,3)B(4,3) = 11 after searching all 16 possibilities.Reorgnizing dichotomies of B(4,3)B(4,3)Check for B(3,3)B(3,3)α+β\alpha + \beta: # of different x1,x2,x3x_1, x_2, x_3 co

2015-10-12 15:39:32 310

原创 Lecture6-2Bounding Function

Bounding Function B(N,k)B(N,k) Maximum possible mm_{\mathcal{H}} when break point = kCombinatiorial quantity: no shatter of any length k points in N pointsirrelevant of details of \mathcal{H} or a

2015-10-12 14:51:04 300

原创 Lecture6-1Restriction of Break Point

What must be true when min break point is k=2k=2?N=1N=1, every m(N)=2m_{\mathcal{H}}(N)=2 by definitionN=1N=1, every m(N)<4m_{\mathcal{H}}(N)<4 by definitionN=3N=3?? Must coform that m(N)<4m_{\

2015-10-12 14:39:13 299

原创 Lecture5-4Breaking Point

The 4 growth functionsBreak point of mm_{\mathcal{H}}For 2D perceptron, we know:for 3 inputs, exists shatterfor 4 inputs, for all data no shatter If no k points can be shattered by \mathcal{H}, ca

2015-10-01 00:18:21 268

zypandora的博客