jurafsky&martin_3rdEd_17 (1).pdf

Initial distribution 126 observation likelihood 125

Info icon This preview shows pages 495–497. Sign up to view the full content.

View Full Document Right Arrow Icon
initial distribution, 126 observation likelihood, 125 observations, 125 simplifying assumptions for POS tagging, 149 states, 125 transition probabilities, 125 trigram POS tagging, 154 holonym, 304 homographs, 301 homonym, 301 homonymy, 301 homophones, 301 human parsing, 239 human sentence processing, 239, 239 Hungarian part-of-speech tagging, 162 hyperarticulation, 448 hypernym, 304 , 356 and information content, 320 in Extended Lesk, 321 lexico-syntactic patterns for, 357 hyponym, 304 IBM, 58 IBM Thomas J. Watson Research Center, 58 ice cream, 125 IDF, 278, 278 , 313 IDF term weighting, 278 immediately dominates, 170 imperative sentence structure, 174 implicit confirmation, 450 indefinite article, 176 indicator function, 93 indirect speech acts, 447 inference-based learning, 266 infinitives, 180 infoboxes, 356 information extraction (IE), 348 bootstrapping, 359 partial parsing for, 205 information gain, 99 for feature selection, 99 Information retrieval, 273 information-content word similarity, 319 initiative, 428 mixed, 429 single, 428 system, 428 inner product, 279 inside-outside algorithm, 220 , 242 intent determination, 430 interjection, 145 internal rule in a CFG parse, 226 interpersonal stance, 342 Interpolated Kneser-Ney discounting, 51, 52 interpolation in smoothing, 49 intonation, 448 intransitive verbs, 180
Image of page 495

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
496 Subject Index intrinsic evaluation, 41 inverse document frequency, 313 IOB, 351 , 432 IOB tagging, 207 Iolanthe , 61 IR IDF term weighting, 278 vector space model, 271 IS-A, 304 is-a, 356 ISO 8601, 367 Jaccard similarity metric, 281 Jaro-Winkler, 72 Jay, John, 89 Jensen-Shannon divergence, 282 Jiang-Conrath distance, 321 joint intention, 457 joint probability, 214 Katz backoff, 50 KBP, 375 KenLM, 54 , 59 KL divergence, 281 , 390 Kleene *, 13 sneakiness of matching zero things, 13 Kleene +, 13 Kneser-Ney discounting, 51 Kullback-Leibler divergence, 390 L1 regularization, 98 L2 regularization, 98 label bias, 162 labeled precision, 238 labeled recall, 238 language generation, 434 language model, 36 adaptation, 59 PCFG, 216 Laplace smoothing, 47 Laplace smoothing:for PMI, 277 lasso regression, 98 Latent Semantic Analysis, 286 latent semantic analysis, 287 , 298 LCS, 320 LDA, 316 LDC, 23, 218 learning rate, 113 lemma, 20 , 300 versus wordform, 20 lemmatization, 11 Lesk algorithm, 311 Corpus, 313 Extended, 321 Simplified, 311 letter-to-sound for spell checking, 72 Levenshtein distance, 27 lexical ambiguity resolution, 324 category, 170 database, 305 dependency, 212, 223 head, 242 semantics, 300 trigger, in IE, 365 lexical answer type, 413 lexical dependency, 223 lexical rule in a CFG parse, 226 lexical sample task in WSD, 307 Lexical-Functional Grammar (LFG), 194 lexicalized grammar, 225 lexico-syntactic pattern, 357 lexicon, 170 likelihood, 63 , 77 Lin similarity, 320 linear classifiers, 78 linear interpolation for N-grams, 50 linearly separable, 106 Linguistic Data Consortium, 23, 218 Link Grammar, 268 LIWC, 82 , 340 LM, 36 LOB corpus, 165 locative, 144 locative adverb, 144 log why used for probabilities, 41 log probabilities, 41, 41 log-linear, 92 log-linear classifiers, 92 logistic regression background, 92 conditional maximum likelihood estimation, 96 multinomial, 92 relation to neural networks, 111 long-distance dependency, 182 traces in the Penn Treebank, 182 wh-questions, 175 lookahead in RE, 19 loss, 111 lowest common subsumer, 320 LSA, 287 LSI, see latent semantic analysis, see latent semantic analysis LUNAR, 417
Image of page 496
Image of page 497
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern