Natural Language Processing
|
|
- Roger Anderson
- 5 years ago
- Views:
Transcription
1 atural Language Processg Info 159/259 Lecture 19: Semantic parsg (Oct. 31, 2017) David Bamman, UC Berkeley
2 Announcements 259 fal project presentations: 3:30-5pm Tuesday, Dec. 5 (RRR week), 202 South Hall
3 Semantics The meang of a sentence is the set of possible worlds it picks out Collections of possible worlds can be compactly represented with logical forms Pieces of logical forms correspond to pieces of language Types logic correspond to grammatical categories language From last time (Andreas)
4 Why is syntax important? Foundation for semantic analysis (on many levels of representation: semantic roles, compositional semantics, frame semantics) From 10/5
5 Why is syntax sufficient? Syntax encodes the structure of language but doesn t directly address meang. Even if we have a reference model for each word a sentence, syntax doesn t tell us how those referents changes as a function of their compositionally.
6 Representation of meang Constants name dividual entities the world Relations are sets of entities Variables refer to entities that have not yet been specified Quantifiers bd variables. (existential quantifier) (universal quantifier)
7 Representation of meang Constants: Pat, Sal Relations: likes(x,y) Pat likes Sal The denotation likes = the ordered set of entities for whom the relation is true likes(pat, Sal) = true likes = {(Pat, Sal), (, )}
8 Representation of meang Quantifiers bd variables. (existential quantifier) (universal quantifier) Order matters! x y speaks(x,y) y x speaks(x,y)
9 Representation of meang Relations: likes(x,y) is scoped over two variables We can represent the partial representation of meang with lambda expressions: λx.likes(x,sal) Expect one other argument to complete the meang of this relation
10 Representation of meang λx.likes(x,sal) Lambda expressions let us tie semantics explicitly to phrases (subtrees syntax) x S V VP likes Sal
11 Representation of meang λy.λx.likes(x,y) Lambda expressions let us tie semantics explicitly to phrases (subtrees syntax) x S V VP likes y
12 Compositional semantics is driven by syntax Prciple of compositionality
13 Syntax We could represent the relationship between syntax and semantics a CFG. But what we want is fe-graed control over the mappg between words and semantic primitives.
14 CCG Infitely large set of structured categories (types). Primitives: S,, PP, Complex types: S/ (S, except missg to right) S\ (S, except missg to left
15 CCG CFG has a large set of productions (e.g., S VP) CCG has a very small set of combators that us how to put the types together. Smith 2017
16 CCG Combators Forward application combator (X/Y X) / / yellow dog Smith 2017
17 CCG Combators Forward application combator (X/Y X) / / / the / yellow dog Smith 2017
18 CCG Combators Backward application combator (X\Y X) S\ S S S\ I (S\)/ saw / the / yellow dog Smith 2017
19 CCG Combators Conjunction combator (X and X X) and dogs and cats Smith 2017
20 CCG Combators Forward composition (X/Y Y/Z X/Z) and backward composition (Y\Z X\Y X\Z) I S (S\)/ S\ (S\)/(S\) would (S\)/ prefer olives Smith 2017
21 24085 / adjective noun 2583 (S[dcl]\)/ transitive verb (declarative) 2107 S[adj]\ predicative adjectives (man is old) 1679 (S[b]\)/ transitive verb (bare fitive) 1628 (/)/(/) adjective adjective pairs 1431 S[pss]\ transitive verb (past participles) 1385 (S[ng]\)/ transitive verb (present participle) 1308 [num] numerals 1227 S[dcl]\ transitive verb (present participle) 1112 (S\)\(S\) adverbs Most frequent types CCGBank lexicon
22 S S\ I S\ (S\)\(S\) (S\)/ (S\)\(S\)/ shot / / an elephant my pajamas S S\ S\ (S\)\(S\) (S\)/ / (S\)\(S\)/ / I shot an elephant my pajamas
23 S S\ \ (S\)/ / (\)/ / I shot an elephant my pajamas
24 S S\ I (S\)/ shot \ S / an elephant (\)/ / S\ my pajamas I S\ (S\)\(S\) (S\)/ (S\)\(S\)/ shot / / an elephant my pajamas
25 I shot an elephant my pajamas [0,1] (S\)/ [1,2] / [2,3] [3,4] (\)/ (S\)\(S\)/ / [5,6] Hockenmaier, 2003 [6,7]
26 I shot an elephant my pajamas [0,1] S/ (S\)/ [1,2] / [2,3] [3,4] (\)/ (S\)\(S\)/ / [5,6] Hockenmaier, 2003 [6,7]
27 I shot an elephant my pajamas [0,1] S/ (S\)/ [1,2] / [2,3] [3,4] (\)/ (S\)\(S\)/ (Leavg out forward composition for clarity) / [5,6] Hockenmaier, 2003 [6,7]
28 I shot an elephant my pajamas [0,1] S/ (S\)/ [1,2] / [2,3] [3,4] (\)/ (S\)\(S\)/ / [5,6] Hockenmaier, 2003 [6,7]
29 I shot an elephant my pajamas [0,1] S/ (S\)/ [1,2] / [2,3] S\ [3,4] (\)/ (S\)\(S\)/ / [5,6] Hockenmaier, 2003 [6,7]
30 I shot an elephant my pajamas [0,1] S/ S (S\)/ [1,2] / [2,3] S\ [3,4] (\)/ (S\)\(S\)/ / [5,6] Hockenmaier, 2003 [6,7]
31 I shot an elephant my pajamas [0,1] S/ S (S\)/ [1,2] S\ / [2,3] [3,4] (\)/ (S\)\(S\)/ / [5,6] Hockenmaier, 2003 [6,7]
32 I shot an elephant my pajamas [0,1] S/ S (S\)/ [1,2] S\ / [2,3] [3,4] (\)/ (S\)\(S\)/ / [5,6] Hockenmaier, 2003 [6,7]
33 I shot an elephant my pajamas [0,1] S/ S (S\)/ [1,2] S\ / [2,3] [3,4] (\)/ (S\)\(S\)/ / [5,6] \ (S\)\(S\) Hockenmaier, 2003 [6,7]
34 I shot an elephant my pajamas [0,1] S/ S (S\)/ [1,2] S\ / [2,3] [3,4] (\)/ (S\)\(S\)/ / [5,6] \ (S\)\(S\) Hockenmaier, 2003 [6,7]
35 I shot an elephant my pajamas [0,1] S/ S (S\)/ [1,2] S\ / [2,3] [3,4] (\)/ (S\)\(S\)/ / [5,6] \ (S\)\(S\) Hockenmaier, 2003 [6,7]
36 I shot an elephant my pajamas [0,1] S/ S (S\)/ [1,2] S\ S\ S\ / [2,3] [3,4] (\)/ (S\)\(S\)/ / [5,6] \ (S\)\(S\) Hockenmaier, 2003 [6,7]
37 I shot an elephant my pajamas [0,1] S/ S/ S S/ (S\)/ [1,2] (S\)/ S\ (S\)/ S\ S\ / [2,3] / [3,4] (\)/ (S\)\(S\)/ (\)/ (S\)\ (S\) / [5,6] \ (S\)\(S\) Hockenmaier, 2003 [6,7]
38 I shot an elephant my pajamas [0,1] S/ S/ S S/ S S (S\)/ [1,2] (S\)/ S\ (S\)/ S\ S\ / [2,3] / [3,4] (\)/ (S\)\(S\)/ (\)/ (S\)\ (S\) / [5,6] \ (S\)\(S\) Hockenmaier, 2003 [6,7]
39 S S\ I (S\)/ shot \ S / an elephant (\)/ / S\ my pajamas I S\ (S\)\(S\) (S\)/ (S\)\(S\)/ shot / / an elephant my pajamas
40 CCG Lexicon Ambiguity CCG comes from the lexicon, not grammar
41 CCG Lexicon I 1438 I 22 I / 4 I \ 3 shot 25 shot (S[dcl]\)/ 8 shot S[dcl]\ 7 shot S[pss]\ 5 shot (S[pss]\)/ 1 elephant 5 elephant / 1 an [nb]/ 3685 an (\)/ 76 an ((S\)\(S\))/ 16 an (((S\)\(S\))\((S\)\(S\)))/ 8 an / 3 an / 3 an ((S\)\(S\))/((S\)\(S\)) 2 an (/)/(/) 2 an (S[qem]/(S[dcl]/))/ 2 an ((S/S)\(S/S))/ 1 an (S\S)/ 1 an, 1 an 1
42 CCG Lexicon (\)/ 8013 ((S\)\(S\))/ 7035 PP/ 1644 (S/S)/ 374 (S\)\(S\) 279 ((S\)/(S\))/ 241 ((S\)\(S\))/(S[ng]\) 155 (((S\)\(S\))\((S\)\(S\)))/ 125 (\)/(S[ng]\) 121 ((S[adj]\)\(S[adj]\))/ 110 PP/(S[ng]\) 106
43 (\)/ ((S\)\(S\))/ PP/ (S/S)/ (S\)\(S\) ((S\)/(S\))/ ((S\)\(S\))/(S[ng]\) (((S\)\(S\))\((S\)\ (S\)))/ (\)/(S[ng]\) ((S[adj]\)\(S[adj]\))/ PP/(S[ng]\) (S\S)/ (PP\PP)/ (((S\)\(S\))/(S[to]\))/ S[adj]\ ((\)\(\))/ (\)/(S[adj]\) (\)/ (((S\)\(S\))/((S\)\ (S\)))/ (/)/ ((S\)\(S\))/(S[adj]\) (PP/(S[ng]\))/ ((S\)/(S\))/(S[ng]\) ((S\)/(S\))/(S[adj]\) (S/S)/(S[ng]\) (S\)/ (((S\)/(S\))\((S\)/(S\)))/ (((S\)\(S\))/(S[to]\))/ (((S\)\(S\))/S[dcl])/ ((S[adj]\)\(S[adj]\))/(S[ng]\) ((S\)\(S\))/PP (\)/PP ((/)\(/))/(/) ((\)/(\))/ ((S\)\(S\))/S[em] (\)/S[qem] \ PP/(S[adj]\) PP/PP (((S\)\(S\))\)/ ((S\)\(S\))/((S\)\(S\)) (\)/ (S/(S[to]\))/ (S\S)/(S[ng]\) \ ((((S\)\(S\))/((S\)\(S\)))\ (((S\)\(S\))/((S\)\(S\))))/ ((/)\(/))/ (PP/PP)/ (S[adj]\)\(S[adj]\) (((S\)\(S\))/)/ ((PP/PP)\(PP/PP))/ ((S[adj]\)/(S[adj]\))/ ((S\)\(S\))/ ((S\)\(S\))/S[qem] ((S\S)\(S\S))/ (PP\)/ / PP PP/S[qem] ((((S\)\(S\))\((S\)\(S\)))\ (((S\)\(S\))\((S\)\(S\))))/ ((((S\)\(S\))\((S\)\(S\)))\ (((S\)\(S\))\((S\)\(S\))))/ (((S/S)\(S/S))\((S/S)\(S/S)))/ (((S\)/(S\))/(S[to]\))/ (((S\)\(S\))/(S[ng]\))/ ((/)/(/))/ ((\)/(S[ng]\))/ ((\)/)/ ((S/S)/(S/S))/ ((S[dcl]\)/PP)/ ((S\)\(S\))\((S\)\(S\)) ((S\S)/(S[to]\))/ ((S\S)/)/ (/)/(/) (/)/ (\)/(\)
44 Supertaggg The CCG lexicon + very small set of combators dictates the overall parse for a sentence. The base categories CKY for syntactic parsg are POS tags (~45 PTB) The base categories CKY for CCG parsg are the lexical rules (~1,363 CCGBank) This blows up the complexity of parsg; supertaggg reduces the lexical categories to a much small reset by predictg the likeliest tags context.
45 I shot an elephant my pajamas / \ (S[dcl]\)/ S[dcl]\ S[pss]\ (S[pss]\)/ / [nb]/ (\)/ ((S\)\(S\))/ (((S\)\(S\))\((S\)\(S\)))/ / / ((S\)\(S\))/((S\)\(S\)) (/)/(/) (S[qem]/(S[dcl]/))/ ((S/S)\(S/S))/ (S\S)/, (\)/ ((S\)\(S\))/ PP/ (S/S)/ (S\)\(S\) ((S\)/(S\))/ ((S\)\(S\))/ (S[ng]\) (((S\)\(S\))\ ((S\)\(S\)))/ (\)/(S[ng] \) ((S[adj]\)\ (S[adj]\))/ PP/(S[ng]\) (S\S)/ (PP\PP)/ (((S\)\(S\))/ (S[to]\))/ S[adj]\ ((\)\ (\))/ (\)/(S[adj] \) (\)/ (S/S)\(S/S) / [nb]/ \
46 I shot an elephant my pajamas (S[dcl]\)/ (\)/ ((S\)\(S\))/ PP/ (\)/ [nb]/ (\)/
47 MEMM General maxent form arg max y P (y x, ) n Maxent with first-order Markov assumption: Maximum Entropy Markov Model arg max y i=1 P (y i y i 1,x)
48 MEMM y1 y2 y3 y4 y5 y6 y7 x1 x2 x3 x4 x5 x6 x7
49 Features : (\)/ ((S\)\(S\))/ feature example xi = man 1 f(t i,t i 1 ; x 1,...,x n ) ti-1 = JJ 1 Features are scoped over the previous predicted tag and the entire observed put i=n (last word of sentence) xi ends -ly 0 1
50 Viterbi decodg Viterbi for MEMM: max conditional probability P (y x) v t (y) = max u Y [v t 1(u) P (y t = y y t 1 = u, x, )]
51 Supertaggg The sgle best sequence is often still too errorful to be the put for CCG parsg. Rather than predictg the sgle best sequence, we can identify the top k tags for each word that have the highest probability. ote this is not P(yi yi-1, x, β) but rather P(yi x, β) we can calculate usg the forward-backward algorithm.
52 Semantics Semantic parsg with CCG is simply syntactic parsg, assumg mappg from syntactic primitives to logical forms.
53 CCG Lexicon Utah utah Idaho idaho borders (S\)/ λx.λy(borders(y,x) adjos (S\)/ λx.λy(adjos(y,x) abuts (S\)/ λx.λy(abuts(y,x)
54 CCG Combators Each combator tells us what to do with the correspondg semantics Forward application: X/Y : f Y : g X f(g) (S\)/ : λx.λy(borders(y,x) : idaho S\ : λx.λy(borders(y,x)(idaho) S\ : λy(borders(y,idaho) Smith 2017
55 Semantics S borders(utah,idaho) S\ λy(borders(y,idaho) utah (S\)/ λx.λy(borders(y,x) idaho Utah borders Idaho
56 Semantics Utah utah Idaho idaho borders (S\)/ λx.λy(borders(y,x) adjos (S\)/ λx.λy(adjos(y,x) abuts (S\)/ λx.λy(abuts(y,x)
57 Semantics Utah utah Idaho idaho borders (S\)/ λx.λy(borders(y,x) adjos (S\)/ λx.λy(borders(y,x) abuts (S\)/ λx.λy(borders(y,x)
58 Semantics Utah utah Idaho idaho borders (S\)/ λx.λy(borders(y,x) adjos (S\)/ λx.λy(borders(y,x) abuts (S\)/ λx.λy(borders(y,x) Does Utah border California?
59 Semantics Semantic parsg with CCG is simply syntactic parsg, assumg mappg from syntactic primitives to logical forms. But this encounters two problems: We don t have those manual mappgs (taskspecific). We can t parse anythg not our lexicon.
60 Learng from logical forms We can tra a semantic parser a number of ways: Full derivational trees (CCGBank) Logical forms (Zettlemoyer and Colls 2005) Denotations (Berant et al. 2013)
61 Learng from trees S λx.state(x) ^ (borders(x,texas) (S/S\) λg.λx.state(x) ^ g(x) (S\) λy(borders(y,texas) (S/S\)/ λf.λg.λx.f(x) ^ g(x) λx.state(x) (S\)/ λx.λy(borders(y,x) texas what states border texas
62 Learng from trees S (S/S\) (S\) (S/S\)/ (S\)/ what states border texas
63 Learng from logical forms sentence what states border texas logical form λx.state(x) ^ borders(x, texas) Two core ideas: We ll learn the lexicon (cludg the lambda expressions) We ll learn CCG parser from that lexicon, and treat the true tree as a latent variable
64 Learng from trees S (S/S\) (S\) (S/S\)/ (S\)/ what states border texas We ll treat the tree (derivation) as a latent variable
65 Learng the lexicon sentence logical form Utah borders Idaho borders(utah,idaho) For a given sentence and logical form, return the set of lexicon entries that could have generated the logical form. Utah utah Idaho idaho borders (S\)/ λx.λy(borders(y,x)
66 Learng the lexicon sentence logical form Utah borders Idaho borders(utah,idaho) For a given sentence and logical form, return the set of lexicon entries that could have generated the logical form. All subsequences of x GELEX(S, L) ={x := y x W (S),y C(L)} All categories found logical form
67 C(L)
68 logical form utah idaho borders borders borders(utah,idaho) : utah : idaho (S\)/ : λx.λy.borders(y,x) (S\)/ : λx.λy.borders(x,y)
69 Learng the lexicon All subsequences of x All categories found logical form GELEX(S, L) ={x := y x W (S),y C(L)} Utah utah Idaho idaho borders idaho borders utah (S\)/ λx.λy(borders(y,x) borders (S\)/ λx.λy(borders(y,x)
70 Learng from logical forms If we create a lexicon λi = itial lexicon Λ0 + lexicon entries identified by GELEX, we can fd many parses for the sentence. sentence Utah borders Idaho logical form utah idaho idaho utah borders borders borders(utah,idaho) : utah : idaho : utah : idaho (S\)/ : λx.λy.borders(y,x) (S\)/ : λx.λy.borders(x,y)
71 Learng from logical forms Calculate the jot probability of a logical form L and derivation T for sentence S as: feature P (L, T S; )= exp(f(l, T, S) ) exp(f(l, T, S) ) L,T Utah := : utah Utah := : idaho sums over all valid trees/logical forms for the sentence borders := (S\)/ : λx.λy.borders(y,x) borders := (S\)/ : λx.λy.borders(x,y) f(l,t,s)
72 Learng from logical forms For all <sentence, logical form> pairs trag data, maximize the probability of the logical form by margalizg over the jot probability: Where P (L S; )= T P (L, T S; ) Start with random values for θ; update with SGD P (L, T S; )= exp(f(l, T, S) ) L,T exp(f(l, T, S) )
73 Learng from logical forms Learng from logical forms is means we don t need trag data the form of full CCG derivations + semantically enriched lexicon. But we do still need trag data the form of logical forms. Utah borders Idaho borders(utah,idaho) number of dramas starrg tom cruise???
74 Learng from denotations sentence logical form denotation what states border texas λx.state(x) ^ borders(x, texas) new_mexico, oklahoma, arkansas, louisiana sentence logical form number of dramas starrg tom cruise count(λx.genre(x,drama) ^ y.performance(x,y) ^ actor(y,tom_cruise)) denotation 28
75 Learng from denotations sentence logical form denotation what states border texas λx.state(x) ^ borders(x, texas) new_mexico, oklahoma, arkansas, louisiana sentence logical form number of dramas starrg tom cruise count(λx.genre(x,drama) ^ y.performance(x,y) ^ actor(y,tom_cruise)) denotation 28
76 Learng from denotations How could we use the prciples of learng from logical forms to learn from denotations? The meang of a sentence is the set of possible worlds consistent with that statement. Utah borders Idaho TRUE number of dramas starrg tom cruise 28
77 Learng from denotations Basic idea: maximize the probability of the tree T/ logical form z that, when executed agast a knowledge base K, yield the correct denotation y i=1 log T : T.z K =y i P (T S i, ) objective function
78 Why do we need CCG (or a syntactic representation) at all?
The Visual Denotations of Sentences. Julia Hockenmaier with Peter Young and Micah Hodosh University of Illinois
The Visual Denotations of Sentences Julia Hockenmaier with Peter Young and Micah Hodosh juliahmr@illinois.edu University of Illinois Sentence-Based Image Description and Search Hodosh, Young, Hockenmaier,
More informationCompositional Semantics. Jacob Andreas
Compositional Semantics Jacob Andreas Problem 1 Each of the three girls has a platypus. Each of the three girls climbed the mountain. How many platypuses? How many mountains? 2 Problem 1 Each of the three
More informationScalable Semantic Parsing with Partial Ontologies ACL 2015
Scalable Semantic Parsing with Partial Ontologies Eunsol Choi Tom Kwiatkowski Luke Zettlemoyer ACL 2015 1 Semantic Parsing: Long-term Goal Build meaning representations for open-domain texts How many people
More informationCS 562: STATISTICAL NATURAL LANGUAGE PROCESSING
CS 562: STATISTICAL NATURAL LANGUAGE PROCESSING August 2010 Instructors: Liang Huang and Kevin Knight TA: Jason Riesa Doesn t Google know everything? What animal does a cat eat? 2 Even Key Word Queries
More informationwinter but it rained often during the summer
1.) Write out the sentence correctly. Add capitalization and punctuation: end marks, commas, semicolons, apostrophes, underlining, and quotation marks 2.)Identify each clause as independent or dependent.
More informationLING/C SC 581: Advanced Computational Linguistics. Lecture Notes Feb 6th
LING/C SC 581: Advanced Computational Linguistics Lecture Notes Feb 6th Adminstrivia The Homework Pipeline: Homework 2 graded Homework 4 not back yet soon Homework 5 due Weds by midnight No classes next
More informationSyntax 3. S-selection. S-selection. C-selection. S-selection (semantic selection) C-selection (categorial selection)
S-selection (semantic selection) Syntax 3 c-selection, s-selection, Text pg. 226-233 -bar ory not text Sandy kissed Kim Sandy skidded *Sandy kissed *Sandy skidded Kim!The oppion kissed Kim!The oppion skidded
More informationIntroduction to Natural Language Processing Phase 2: Question Answering
Introduction to Natural Language Processing Phase 2: Question Answering Center for Games and Playable Media http://games.soe.ucsc.edu The plan for the next two weeks Week9: Simple use of VN WN APIs. Homework
More informationSentence Processing III. LIGN 170, Lecture 8
Sentence Processing III LIGN 170, Lecture 8 Syntactic ambiguity Bob weighed three hundred and fifty pounds of grapes. The cotton shirts are made from comes from Arizona. The horse raced past the barn fell.
More informationDynamic Semantics! (Part 1: Not Actually Dynamic Semantics) Brian Morris, William Rose
Dynamic Semantics! (Part 1: Not Actually Dynamic Semantics) Brian Morris, William Rose 2016-04-13 Semantics Truth-Conditional Semantics Recall: way back in two thousand and aught fifteen... Emma and Gabe
More informationThe word digital implies information in computers is represented by variables that take a limited number of discrete values.
Class Overview Cover hardware operation of digital computers. First, consider the various digital components used in the organization and design. Second, go through the necessary steps to design a basic
More informationPlurals Jean Mark Gawron San Diego State University
Plurals Jean Mark Gawron San Diego State University 1 Plurals, Groups Semantic analysis: We try to reduce novel semantic facts to the kinds of things we ve seen before: Program Reduce everything to claims
More informationVagueness & Pragmatics
Vagueness & Pragmatics Min Fang & Martin Köberl SEMNL April 27, 2012 Min Fang & Martin Köberl (SEMNL) Vagueness & Pragmatics April 27, 2012 1 / 48 Weatherson: Pragmatics and Vagueness Why are true sentences
More informationMATH 195: Gödel, Escher, and Bach (Spring 2001) Notes and Study Questions for Tuesday, March 20
MATH 195: Gödel, Escher, and Bach (Spring 2001) Notes and Study Questions for Tuesday, March 20 Reading: Chapter VII Typographical Number Theory (pp.204 213; to Translation Puzzles) We ll also talk a bit
More information1.1 The Language of Mathematics Expressions versus Sentences
. The Language of Mathematics Expressions versus Sentences a hypothetical situation the importance of language Study Strategies for Students of Mathematics characteristics of the language of mathematics
More informationI-language Chapter 8: Anaphor Binding
I-language Chapter 8: Anaphor Daniela Isac & Charles Reiss Concordia University, Montreal Outline 1 2 3 The beginning of science is the recognition that the simplest phenomena of ordinary life raise quite
More informationTwo Styles of Construction Grammar Do Ditransitives
Two Styles of Construction Grammar Do Ditransitives Cognitive Construction Grammar CCG) and Sign Based Construction Grammar SBCG) Paul Kay LSA Summer Institute, Stanford 7/2-3/07 The SBCG project team:
More informationMeaning 1. Semantics is concerned with the literal meaning of sentences of a language.
Meaning 1 Semantics is concerned with the literal meaning of sentences of a language. Pragmatics is concerned with what people communicate using the sentences of the language, the speaker s meaning. 1
More informationLecture 7. Scope and Anaphora. October 27, 2008 Hana Filip 1
Lecture 7 Scope and Anaphora October 27, 2008 Hana Filip 1 Today We will discuss ways to express scope ambiguities related to Quantifiers Negation Wh-words (questions words like who, which, what, ) October
More informationRecap: Roots, inflection, and head-movement
Syntax II Seminar 4 Recap: Roots, inflection, and head-movement Dr. James Griffiths james.griffiths@uni-konstanz.de he English verbal domain - Modified from the Carnie (2013) excerpt: (1) he soup could
More informationSentence Processing. BCS 152 October
Sentence Processing BCS 152 October 29 2018 Homework 3 Reminder!!! Due Wednesday, October 31 st at 11:59pm Conduct 2 experiments on word recognition on your friends! Read instructions carefully & submit
More informationKnowledge Representation
7 Knowledge Representation 7.0 Issues in Knowledge Representation 7.1 A Brief History of AI Representational Systems 7.2 Conceptual Graphs: A Network Language 7.3 Alternatives to Explicit Representation
More informationArticulating Medieval Logic, by Terence Parsons. Oxford: Oxford University Press,
Articulating Medieval Logic, by Terence Parsons. Oxford: Oxford University Press, 2014. Pp. xiii + 331. H/b 50.00. This is a very exciting book that makes some bold claims about the power of medieval logic.
More information! Japanese: a wh-in-situ language. ! Taroo-ga [ DP. ! Taroo-ga [ CP. ! Wh-words don t move. Islands don t matter.
CAS LX 522 Syntax I Episode 12b. Phases, relative clauses, and LF (ch. 10) Islands and phases, summary from last time! Sentences are chunked into phases as they are built up. Phases are CP and DP.! A feature
More informationLESSON 30: REVIEW & QUIZ (DEPENDENT CLAUSES)
LESSON 30: REVIEW & QUIZ (DEPENDENT CLAUSES) Teachers, you ll find quiz # 8 on pages 7-10 of this lesson. Give the quiz after going through the exercises. Review Clauses are groups of words with a subject
More informationAutomatic Speech Recognition (CS753)
Automatic Speech Recognition (CS753) Lecture 22: Conversational Agents Instructor: Preethi Jyothi Oct 26, 2017 (All images were reproduced from JM, chapters 29,30) Chatbots Rule-based chatbots Historical
More informationA picture of the grammar. Sense and Reference. A picture of the grammar. A revised picture. Foundations of Semantics LING 130 James Pustejovsky
A picture of the grammar Sense and Reference Foundations of Semantics LING 130 James Pustejovsky Thanks to Dan Wedgewood of U. Edinburgh for use of some slides grammar context SYNTAX SEMANTICS PRAGMATICS
More informationDigital Logic Design ENEE x. Lecture 24
Digital Logic Design ENEE 244-010x Lecture 24 Announcements Homework 9 due today Thursday Office Hours (12/10) from 2:30-4pm Course Evaluations at the end of class today. https://www.courseevalum.umd.edu/
More informationFrom Experiments in Music Intelligence (Emmy) to Emily Howell: The Work of David Cope. CS 275B/Music 254
From Experiments in Music Intelligence (Emmy) to Emily Howell: The Work of David Cope CS 275B/Music 254 Experiments in Musical Intelligence: Motivations 1990-2006 2 Emmy (overview) History Work began around
More informationCAS LX 522 Syntax I. Islands. Wh-islands. Phases. Complex Noun Phrase islands. Adjunct islands
CAS LX 522 Syntax I Week 14b. Phases, relative clauses, and LF (ch. 10) Islands There seem to be certain structures out of which you cannot move a wh-word. These are islands. CNP (complex noun phrase)
More informationLexical Semantics: Sense, Referent, Prototype. Sentential Semantics (phrasal, clausal meaning)
Lexical Semantics: Sense, Referent, Prototype 1. Semantics Lexical Semantics (word meaning) Sentential Semantics (phrasal, clausal meaning) 2. A word is different from its meaning The three phonemes in
More informationOntology and Taxonomy. Computational Linguistics Emory University Jinho D. Choi
Ontology and Taxonomy Computational Linguistics Emory University Jinho D. Choi Ontology Nature of being, becoming, existence, or reality, as well as the basic categories of being and their relations. Types,
More informationCambridge Primary English as a Second Language Curriculum Framework mapping to English World
Stage English World Reading Recognise, identify and sound, with some support, a range of language at text level Read and follow, with limited support, familiar instructions for classroom activities Read,
More informationFebruary 16, 2007 Menéndez-Benito. Challenges/ Problems for Carlson 1977
1. Wide scope effects Challenges/ Problems for Carlson 1977 (i) Sometimes BPs appear to give rise to wide scope effects with anaphora. 1) John saw apples, and Mary saw them too. (Krifka et al. 1995) This
More informationToward Computational Recognition of Humorous Intent
Toward Computational Recognition of Humorous Intent Julia M. Taylor (tayloj8@email.uc.edu) Applied Artificial Intelligence Laboratory, 811C Rhodes Hall Cincinnati, Ohio 45221-0030 Lawrence J. Mazlack (mazlack@uc.edu)
More informationAutomatic Harmonic Analysis of Jazz Chord Progressions Using a Musical Categorial Grammar. Mark Wilding
Automatic Harmonic Analysis of Jazz Chord Progressions Using a Musical Categorial Grammar Mark Wilding E H U N I V E R S I T Y T O H F R G E D I N B U Master of Science School of Informatics University
More informationFirst Order Logic. Xiaojin Zhu Computer Sciences Department University of Wisconsin, Madison. [Based on slides from Burr Settles]
First Order Logic Xiaojin Zhu jerryzhu@cs.wisc.edu Computer Sciences Department University of Wisconsin, Madison [Based on slides from Burr Settles] slide 1 Problems with propositional logic Consider the
More informationPeirce's Remarkable Rules of Inference
Peirce's Remarkable Rules of Inference John F. Sowa Abstract. The rules of inference that Peirce invented for existential graphs are the simplest, most elegant, and most powerful rules ever proposed for
More informationtech-up with Focused Poetry
tech-up with Focused Poetry With Beverly Flance, Staci Weber, & Donna Brown Contact Information: Donna Brown dbrown@ccisd.net @DonnaBr105 Staci Weber sweber@ccisd.net @Sara_Staci Beverly Flance bflance@ccisd.net
More informationSong Lessons Understanding and Using English Grammar, 3rd Edition. A lesson about adjective, adverb, and noun clauses (Chapters 12, 13, 17)
A lesson about adjective, adverb, and noun clauses (Chapters 12, 13, 17) Notes for the Teacher 1. The Song Do a search on the Internet to find the song Father and Daughter by Paul Simon. When you search,
More informationPractice Midterm Exam for Natural Language Processing
Practice Midterm Exam for Natural Language Processing Name: Net ID Instructions In the actual midterm there will be 7 questions, each will be worth 15 points. You also get 10 point for signing your name
More informationIndependent Clause. An independent clause is a group of words that has a subject and a verb that expresses a complete thought and can stand by itself.
Grammar Clauses Independent Clause An independent clause is a group of words that has a subject and a verb that expresses a complete thought and can stand by itself. Dependent (Subordinate) Clause A subordinate
More informationHow English Phrases Are Formed: Syntax I
Week 7. yntax: the study of how words are combined into sentences. How English Phrases Are Formed: yntax I remember brick, blick, and bnick? eal nape yntax: the study of how words are combined into sentences.
More informationMorphology, heads, gaps, etc.
Syntactic Attributes Morphology, heads, gaps, etc. Note: The properties of nonterminal symbols are often called features. However, we will use the alternative name attributes. (We ll use features to refer
More informationEnglish 9 Final Exam Study Guide
English 9 Final Exam Study Guide Vocab Review All vocab words from second semester are on Quizlet.com Final exam will include: multiple choice, fill in the blank, matching and true/false Literary Terms
More informationTake a Break, Bach! Let Machine Learning Harmonize That Chorale For You. Chris Lewis Stanford University
Take a Break, Bach! Let Machine Learning Harmonize That Chorale For You Chris Lewis Stanford University cmslewis@stanford.edu Abstract In this project, I explore the effectiveness of the Naive Bayes Classifier
More informationNissim Francez: Proof-theoretic Semantics College Publications, London, 2015, xx+415 pages
BOOK REVIEWS Organon F 23 (4) 2016: 551-560 Nissim Francez: Proof-theoretic Semantics College Publications, London, 2015, xx+415 pages During the second half of the twentieth century, most of logic bifurcated
More informationSurvey of Knowledge Base Content
Survey of Knowledge Base Content Introduction Fundamental Expression Types Top Level Collections Time and Dates Spatial Properties and Relations Event Types Information More Content Areas In this lesson
More informationStrand 6 English Language Arts and Reading
(11) Composition: Listening, Speaking, Reading Writing using Multiple Texts [Writing process]. The student uses the process recursively compose multiple texts that are legible use. The student is expected
More informationLinking semantic and pragmatic factors in the Japanese Internally Headed Relative Clause
Linking semantic and pragmatic factors in the Japanese Internally Headed Relative Clause Yusuke Kubota and E. Allyn Smith Department of Linguistics The Ohio State University http://www.ling.ohio-state.edu/~kubota/papers/rel07.pdf
More informationTHE ULTIMATE WEEKLY PLANNER FOR TEENS
THE ULTIMATE WEEKLY PLANNER FOR TEENS THE ULTIMATE WEEKLY PLANNER FOR TEENS Order brings peace. St. Augustine (traditional) School Year: Name: Address: Phone: E-mail: First Semester CLASSES Second Semester
More informationComparisons: Phrases & Sentences
02 Comparisons: Phres & Sentences Vocabulary Fill in the blanks 1. Simon is an doctor. 2. A sports car is more than a used car. 3. Ian likes to several activities and now he h a lot of friends. 4. A usually
More informationComparatives, Indices, and Scope
To appear in: Proceedings of FLSM VI (1995) Comparatives, Indices, and Scope Christopher Kennedy University of California, Santa Cruz 13 July, 1995 kennedy@ling.ucsc.edu 1 Russell's ambiguity Our knowledge
More informationThe Interpretation of the Logophoric Pronoun in Ewe Hazel Pearson. The distribution of the logophoric pronoun yè in Ewe is as follows:
1. Introduction The Interpretation of the Logophoric Pronoun in Ewe Hazel Pearson The distribution of the logophoric pronoun yè in Ewe is as follows: (1) Kofi be yè dzo. Kofi say LOG leave Kofii say that
More informationArts, Computers and Artificial Intelligence
Arts, Computers and Artificial Intelligence Sol Neeman School of Technology Johnson and Wales University Providence, RI 02903 Abstract Science and art seem to belong to different cultures. Science and
More information(The) most in Dutch: Definiteness and Specificity. Koen Roelandt CRISSP, KU Leuven HUBrussel
(The) most in Dutch: Definiteness and Specificity Koen Roelandt CRISSP, KU Leuven HUBrussel koen.roelandt@hubrussel.be 1 Introduction (1) Jan heeft de meeste bergen beklommen. John has thepl.masc. most
More informationLongman Academic Writing Series 4
Writing Objectives Longman Academic Writing Series 4 Chapter Writing Objectives CHAPTER 1: PARAGRAPH STRUCTURE 1 - Identify the parts of a paragraph - Construct an appropriate topic sentence - Support
More informationFigurative Language Processing: Mining Underlying Knowledge from Social Media
Figurative Language Processing: Mining Underlying Knowledge from Social Media Antonio Reyes and Paolo Rosso Natural Language Engineering Lab EliRF Universidad Politécnica de Valencia {areyes,prosso}@dsic.upv.es
More informationCSE 517 Natural Language Processing Winter 2013
CSE 517 Natural Language Processing Winter 2013 Phrase Based Translation Luke Zettlemoyer Slides from Philipp Koehn and Dan Klein Phrase-Based Systems Sentence-aligned corpus Word alignments cat chat 0.9
More informationLESSON 26: DEPENDENT CLAUSES (ADVERB)
LESSON 26: DEPENDENT CLAUSES (ADVERB) Relevant Review Clauses are groups of words with a subject and a verb. Adverbs describe verbs, adjectives, and adverbs. Lesson o They answer the adverb questions.
More informationLearning and Teaching English through the Bible: A Pictorial Approach BIBLE STUDY WORKBOOK PROSE
PROSE Definition of Prose: Ordinary form of spoken or written language that does not make use of any of the special forms of structure, rhythm, or meter that characterize poetry. 1 To understand what the
More informationPARTICIPIAL PHRASES: EXERCISE #1
PARTICIPIAL PHRASES: EXERCISE #1 PART I DIRECTIONS: Look at each verb below. If it looks like a present participle, mark "pres" in the space at the left. If it looks like a past participle, mark "past."
More informationused to speak about a noun. A or an is generally a noun. to show how clauses and each other. relate to (p. 34) (p. 28) happening words. (p.
Wow! My lazy cats and dogs jump quickly on the chair. Interjection Pronoun Adjective Noun Conjunction Noun Verb Adverb Preposition Article Noun Used to express feelings. 1. 2. 3. Used in place of a noun.
More informationGrade ade 4 English & English & Grammar 4 Grammar School Success Subjects Proper Nouns Starts Here! Verb Tenses English & Gr
English & Grammar Grade 4 School Success Starts Here! Subjects Proper Nouns Verb Tenses Adjectives and Adverbs Punctuation Verb Tenses Predicates A noun names a person, place or thing person sister, uncle,
More informationEncoders and Decoders: Details and Design Issues
Encoders and Decoders: Details and Design Issues Edward L. Bosworth, Ph.D. TSYS School of Computer Science Columbus State University Columbus, GA 31907 bosworth_edward@colstate.edu Slide 1 of 25 slides
More informationInterpreting quotations
Interpreting quotations Chung-chieh Shan Rutgers Linguistics October 12, 2007 Mixed quotes appear to mix mention and use, or direct and indirect quotation. (1) Quine says that quotation has a certain anomalous
More informationHarmonic Analysis of Music Using Combinatory Categorial Grammar
This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (e.g. PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions
More informationLesson 84: Station and Airport Announcements (20-25 minutes)
Main Topic 15: Travel Lesson 84: Station and Airport Announcements (20-25 minutes) Today, you will: 1. Learn useful vocabulary related to STATION AND AIRPORT ANNOUNCEMENTS. 2. Review Participial Phrases.
More informationLess is More: Picking Informative Frames for Video Captioning
Less is More: Picking Informative Frames for Video Captioning ECCV 2018 Yangyu Chen 1, Shuhui Wang 2, Weigang Zhang 3 and Qingming Huang 1,2 1 University of Chinese Academy of Science, Beijing, 100049,
More informationAn HPSG Account of Depictive Secondary Predicates and Free Adjuncts: A Problem for the Adjuncts-as-Complements Approach
An HPSG Account of Depictive Secondary Predicates and Free Adjuncts: A Problem for the Adjuncts-as-Complements Approach Hyeyeon Lee (Seoul National University) Lee, Hyeyeon. 2014. An HPSG Account of Depictive
More informationBBC LEARNING ENGLISH 6 Minute Grammar Adverb position 1
BBC LEARNING ENGLISH 6 Minute Grammar Adverb position 1 This is not a word-for-word transcript Hello and welcome to 6 Minute Grammar with me,. And me,. Hello. In this programme we're talking about adverbs
More informationLESSON TWELVE VAGUITY AND AMBIGUITY
LESSON TWELVE VAGUITY AND AMBIGUITY Most often, we make or produce certain sentences statements, questions or commands and realize that these sentences do not have any meanings or have meanings, but the
More informationOn Meaning. language to establish several definitions. We then examine the theories of meaning
Aaron Tuor Philosophy of Language March 17, 2014 On Meaning The general aim of this paper is to evaluate theories of linguistic meaning in terms of their success in accounting for definitions of meaning
More informationSemantics. Philipp Koehn. 16 November 2017
Semantics Philipp Koehn 16 November 2017 Meaning 1 The grand goal of artificial intelligence machines that do not mindlessly process data... but that ultimately understand its meaning But what is meaning?
More informationCOMMON GRAMMAR ERRORS. By: Dr. Elham Alzoubi
COMMON GRAMMAR ERRORS THERE VS. THEIR VS. THEY'RE They re: This is a short form of they are. E.g. They re the children of our neighbors. There: It can be used as an expletive to start a sentence or can
More informationLanguage and Inference
Language and Inference Day 5: Inference in the Real World Johan Bos johan.bos@rug.nl Semantic Analysis Pipeline tokenisation tokenised text POS-tagging parts of speech NE-tagging named entities parsing
More informationRelease Year Prediction for Songs
Release Year Prediction for Songs [CSE 258 Assignment 2] Ruyu Tan University of California San Diego PID: A53099216 rut003@ucsd.edu Jiaying Liu University of California San Diego PID: A53107720 jil672@ucsd.edu
More informationDIGITAL ELECTRONICS & it0203 Semester 3
DIGITAL ELECTRONICS & it0203 Semester 3 P.Rajasekar & C.M.T.Karthigeyan Asst.Professor SRM University, Kattankulathur School of Computing, Department of IT 8/22/20 Disclaimer The contents of the slides
More information1 The structure of this exercise
CAS LX 522 Syntax I Fall 2013 Extra credit: Trees are easy to draw Due by Thu Dec 19 1 The structure of this exercise Sentences like (1) have had a long history of being pains in the neck. Let s see why,
More informationGlossary alliteration allusion analogy anaphora anecdote annotation antecedent antimetabole antithesis aphorism appositive archaic diction argument
Glossary alliteration The repetition of the same sound or letter at the beginning of consecutive words or syllables. allusion An indirect reference, often to another text or an historic event. analogy
More information12/4/2013 Wed E Period
12/4/2013 Wed E Period Bellwork: Silently, review for your TKAM test. Objectives: Identify elements of an introduction paragraph. Explain Theme. Identify Adverbs. homework Study nouns, pronouns, adjectives,
More informationBasic English. Robert Taggart
Basic English Robert Taggart Table of Contents To the Student.............................................. v Unit 1: Parts of Speech Lesson 1: Nouns............................................ 3 Lesson
More informationUNIT PLAN. Subject Area: English IV Unit #: 4 Unit Name: Seventeenth Century Unit. Big Idea/Theme: The Seventeenth Century focuses on carpe diem.
UNIT PLAN Subject Area: English IV Unit #: 4 Unit Name: Seventeenth Century Unit Big Idea/Theme: The Seventeenth Century focuses on carpe diem. Culminating Assessment: Research satire and create an original
More informationScientific Philosophy
Scientific Philosophy Gustavo E. Romero IAR-CONICET/UNLP, Argentina FCAGLP, UNLP, 2018 Philosophy of mathematics The philosophy of mathematics is the branch of philosophy that studies the philosophical
More informationGrammar is a way of thinking about language. Grammar is a way of thinking about language.
MAGIC LENS The Easiest and Least Time- Consuming Way for Students to Learn Grammar and Not Just Repeat Things That Have Been Done in the Classroom for the Past Six Years Grammar is a way of thinking about
More informationDETECTION OF SLOW-MOTION REPLAY SEGMENTS IN SPORTS VIDEO FOR HIGHLIGHTS GENERATION
DETECTION OF SLOW-MOTION REPLAY SEGMENTS IN SPORTS VIDEO FOR HIGHLIGHTS GENERATION H. Pan P. van Beek M. I. Sezan Electrical & Computer Engineering University of Illinois Urbana, IL 6182 Sharp Laboratories
More informationLANGUAGE ARTS GRADE 3
CONNECTICUT STATE CONTENT STANDARD 1: Reading and Responding: Students read, comprehend and respond in individual, literal, critical, and evaluative ways to literary, informational and persuasive texts
More informationIntensional Relative Clauses and the Semantics of Variable Objects
1 To appear in M. Krifka / M. Schenner (eds.): Reconstruction Effects in Relative Clauses. Akademie Verlag, Berlin. Intensional Relative Clauses and the Semantics of Variable Objects Friederike Moltmann
More information"There is no education like adversity."
"There is no education like adversity." Disraeli, Endymion 1 Purpose of presentation: This presentation provides a very basic introduction to the concept of parts of speech in language. Actually, the study
More informationSentence Clarity and Combining. Sentence Clarity. Common clarity problems. Misplaced modifiers Dangling modifiers Passive voice
Sentence Clarity and Combining A workshop brought to you by The Purdue University Writing Lab Sentence Clarity Why do we need to be concerned with sentence clarity? To communicate effectively to the reader
More informationSentence Clarity and Combining. Sentence Clarity. A workshop brought to you by The Purdue University Writing Lab
Sentence Clarity and Combining A workshop brought to you by The Purdue University Writing Lab Sentence Clarity Why do we need to be concerned with sentence clarity? To communicate effectively to the reader
More informationHandout 3 Verb Phrases: Types of modifier. Modifier Maximality Principle Non-head constituents are maximal projections, i.e., phrases (XPs).
Handout 3 Verb Phrases: Types of modifier Modifier Maximality Principle Non-head constituents are maximal projections, i.e., phrases (XPs). Compare buy and put: (1) a. John will buy the book on Tuesday.
More informationPLEASE SCROLL DOWN FOR ARTICLE
This article was downloaded by:[ingenta Content Distribution] On: 24 January 2008 Access Details: [subscription number 768420433] Publisher: Routledge Informa Ltd Registered in England and Wales Registered
More informationMusical Creativity. Jukka Toivanen Introduction to Computational Creativity Dept. of Computer Science University of Helsinki
Musical Creativity Jukka Toivanen Introduction to Computational Creativity Dept. of Computer Science University of Helsinki Basic Terminology Melody = linear succession of musical tones that the listener
More information7. The English Caused-Motion Construction. Presenter: 林岱瑩
7. The English Caused-Motion Construction Presenter: 林岱瑩 7.1 Introduction 7.1 Introduction Basic construction: [SUBJ [V OBJ OBL]] (V: a nonstative verb; OBL: a directional phrase) (1) They laughed the
More informationVideo Codec Requirements and Evaluation Methodology
Video Codec Reuirements and Evaluation Methodology www.huawei.com draft-ietf-netvc-reuirements-02 Alexey Filippov (Huawei Technologies), Andrey Norkin (Netflix), Jose Alvarez (Huawei Technologies) Contents
More informationThe Language of First-Order Predicate Logic
The Language of First-Order Predicate Logic (Note: First-Order Predicate Logic differs from ordinary Predicate Logic in that it contains individual variables and quantifiers. The designation first-order
More information10 Common Grammatical Errors and How to Fix Them
10 Common Grammatical Errors and How to Fix Them 1. Agreement Errors The subject and verb in a sentence must agree in number (singular vs. plural) and person (first, second, or third person). Pronouns
More informationThe structure of this ppt. Structural and categorial (and some functional) issues: English Hungarian
The structure of this ppt Structural and categorial (and some functional) issues: 1.1. 1.12. English 2.1. 2.6. Hungarian 2 1.1. Structural issues The VP lecture (1) S NP John VP laughed. read the paper.
More informationTarget Vocabulary (Underlining indicates a word or word form from the Academic Word
Chapter 7 Target Vocabulary (Underlining indicates a word or word form from the Academic Word List) arrange v.: to put things in a particular position or order assure v.: to tell someone that something
More information