Download presentation
Presentation is loading. Please wait.
1
Christel Kemke 1 2007/08 COMP 4060 Natural Language Processing PARSING
2
2007/08 Christel Kemke 2 Parsing Language, Syntax, Parsing Problems in Parsing Ambiguity Attachment / Binding Bottom vs. Top Down Parsing Chart-Parsing Earley-Algorithm
3
2007/08 Christel Kemke 3 Natural Language - Parsing Parsing derive the syntactic structure of a sentence based on a language model (grammar) construct a parse tree, i.e. the derivation of the sentence based on the grammar (rewrite system)
4
2007/08 Christel Kemke 4 Natural Language - Grammar Natural Language Syntax described through a formal language, often a context-free grammar (CFG): G=(NT,T,P,S): the Start-Symbol S NT ≡ sentence symbol Non-Terminals NT ≡ syntactic constituents Terminals T ≡ lexical entries/ words Production Rules P NT (NT T) + ≡ grammar rules
5
2007/08 Christel Kemke 5 Sample Grammar Grammar (S, NT, T, P) Sentence Symbol S NT, Part-of-Speech NT, Constituents NT, Terminals, Word T Grammar Rules P NT (NT T)* S NP VPstatement S Aux NP VPquestion S VPcommand NP Det Nominal NP Proper-Noun Nominal Noun | Noun Nominal | Nominal PP VP Verb | Verb NP | Verb PP | Verb NP PP PP Prep NP Det that | this | a Noun book | flight | meal | money Proper-Noun Houston | American Airlines | TWA Verb book | include | prefer Aux does Prep from | to | on
6
2007/08 Christel Kemke 6 Parsing Task Parse "Does this flight include a meal?"
7
2007/08 Christel Kemke 7 Parse "Does this flight include a meal?" S Aux NP VP Det Nominal Verb NP Noun Det Nominal does this flight include a meal Sample Parse Tree
8
2007/08 Christel Kemke 8 Problems in Parsing - Ambiguity Ambiguity syntactical/structural ambiguity – several parse trees are possible e.g. above sentence semantic/lexical ambiguity – several word meanings e.g. bank (where you get money) and (river) bank even different word categories possible (interim) e.g. “ He books the flight. ” vs. “ The books are here. “ or “ Fruit flies from the balcony ” vs. “ Fruit flies are on the balcony. ” “Peter saw Mary with the telescope / her friend / his friend.”
9
2007/08 Christel Kemke 9 Problems in Parsing – Attachment 1 Attachment in particular PP (prepositional phrase) binding; often referred to as binding problem. See next slides.
10
2007/08 Christel Kemke 10 Problems in Parsing – Attachment 2 “One morning, I shot an elephant in my pajamas.” Binding 2: VP Verb NP and NP Det Nominal and Nominal Nominal PP and Nominal Noun (S... (NP (PNoun I )) (VP (Verb shot ) (NP (Det an) (Nominal (Nominal (Noun elephant ) (PP in my pajamas )... ) Binding 1: VP Verb NP PP (S... (NP (PNoun I )(VP (Verb shot ) (NP (Det an (Nominal (Noun elephant ))) (PP in my pajamas ))...)
11
2007/08 Christel Kemke 11 Problems in Parsing – Attachment 3 “One morning, I shot an elephant in my pajamas.” Binding 2: VP Verb NP and NP Det Nominal and Nominal Nominal PP and Nominal Noun (S... (NP (PNoun I )) (VP (Verb shot ) (NP (Det an) (Nominal (Nominal (Noun elephant ) (PP in my pajamas )... ) “How he got into them, I don’t know.”
12
2007/08 Christel Kemke 12 Bottom-up – from word-nodes to sentence-symbol Top-down Parsing – from sentence-symbol to words S Aux NP VP Det Nominal Verb NP NounDet Nominal doesthis flight include a meal Bottom-up and Top-down Parsing
13
2007/08 Christel Kemke 13 Problems with Bottom-up and Top-down Parsing Problems with left-recursive rules like NP NP PP: don ’ t know how many times recursion is needed Pure Bottom-up or Top-down Parsing is inefficient because it generates and explores too many structures which in the end turn out to be invalid (several grammar rules applicable ‘interim’ ambiguity). Combine top-down and bottom-up approach: Start with sentence; use rules top-down (look-ahead); read input; try to find shortest path from input to highest unparsed constituent (from left to right). Chart-Parsing / Earley-Parser
14
2007/08 Christel Kemke 14 Chart Parsing / Early Algorithm Earley-Parser based on Chart-Parsing Essence: Integrate top-down and bottom-up parsing. Keep recognized sub-structures (sub-trees) for shared use during parsing. Top-down: Start with S-symbol. Generate all applicable rules for S. Go further down with left-most constituent in rules and add rules for these constituents until you encounter a left-most node on the RHS which is a word category (POS). Bottom-up: Read input word and compare. If word matches, mark as recognized and move parsing on to the next category in the rule(s).
15
2007/08 Christel Kemke 15 Chart A Chart is a graph with n+1 nodes marked 0 to n for a sequence of n input words. Arcs indicate recognized part of RHS of rule. The indicates recognized constituents in rules. Jurafsky & Martin, Figure 10.15, p. 380
16
2007/08 Christel Kemke 16 Chart Parsing / Earley Parser 1 Chart Sequence of n input words; n+1 nodes marked 0 to n. States in chart represent possible rules and recognized constituents. RHS of recognized rule is covered by arc. Interim state S VP, [0,0] top-down look at rule S VP nothing of RHS of rule yet recognized ( is far left) arc at beginning, no coverage (covers no input word; beginning of arc at node 0 and end of arc at node 0)
17
2007/08 Christel Kemke 17 Chart Parsing / Earley Parser 2 Interim states NP Det Nominal, [1,2] top-down look with rule NP Det Nominal Det recognized ( after Det) arc covers one input word which is between node 1 and node 2 look next for Nominal, top-down NP Det Nominal, [1,3] Nominal was recognized, move after Nominal move end of arc to cover Nominal; change 2 to 3 structure is completely recognized; arc is inactive; mark NP as recognized in other rules (move ), bottom up
18
2007/08 Christel Kemke 18 Chart - 0 Book this flight S . VP VP . V NP
19
2007/08 Christel Kemke 19 Chart - 1 VP V. NP V Book this flight S . VP NP . Det Nom
20
2007/08 Christel Kemke 20 Chart - 2 VP V. NP V Book this flight S . VP NP Det. Nom Det Nom . Noun
21
2007/08 Christel Kemke 21 Chart - 3a VP V. NP V Book this flight S . VP NP Det. Nom Det Nom Noun. Noun
22
2007/08 Christel Kemke 22 Chart - 3b VP V. NP V Book this flight S . VP NP Det Nom. Det Nom Noun. Noun
23
2007/08 Christel Kemke 23 Chart - 3c VP V NP. V Book this flight NP Det Nom. Det Nom Noun. Noun S . VP
24
2007/08 Christel Kemke 24 Chart - 3d VP V NP. V Book this flight S VP. NP Det Nom. Det Nom Noun. Noun
25
2007/08 Christel Kemke 25 Chart – Valid and Invalid Rules/Arcs NP Det Nom. VP V. NP Nom Noun. VDetNoun Book this flight S . VP VP . V NP NP . Det Nom NP Det. Nom VP V NP. S VP. Nom . Noun
26
2007/08 Christel Kemke 26 Chart - Final States NP Det Nom. Nom Noun. V Det Noun Book this flight VP V NP. S VP.
27
2007/08 Christel Kemke 27 Chart 0 with two S- and two VP-Rules Book this flight S . VP VP . V NP additional S-rule S . VP NP additional VP-rule VP . V
28
2007/08 Christel Kemke 28 Chart 1a with two S- and two VP-Rules VP V. NP V Book this flight S . VP NP . Det Nom S . VP NP VP V.
29
2007/08 Christel Kemke 29 Chart 1b with two S- and two VP-Rules VP V. NP V Book this flight S VP. NP . Det Nom S VP. NP VP V.
30
2007/08 Christel Kemke 30 Chart 2 with two S- and two VP-Rules VP V. NP V Book this flight S VP. NP Det. Nom S VP. NP VP V. Nom . Noun
31
2007/08 Christel Kemke 31 VP V NP. V Book this flight S VP. NP Det Nom. Det Nom Noun. S VP NP. VP V. Chart 3 with two S- and two VP-Rules Noun
32
2007/08 Christel Kemke 32 NP Det Nom. Final Chart - with two S-and two VP-Rules VP V NP. V Book this flight S VP NP. Det Nom Noun. Noun S VP. VP V.
33
Christel Kemke 33 2007/08 Earley Parser
34
2007/08 Christel Kemke 34 Earley Algorithm - Functions predictor generates new rules for partly recognized RHS with constituent right of (top-down generation) scanner if word category (POS) is found right of the, the Scanner reads the next input word and adds a rule for it to the chart (bottom- up mode) completer if rule is completely recognized (the is far right), the recognition state of earlier rules in the chart advances: the is moved over the recognized constituent (bottom-up recognition).
35
2007/08 Christel Kemke 35 Earley – Chart for “book that flight” including references to completed states/rules
36
2007/08 Christel Kemke 36 Earley – Chart for “book that flight” from 2 nd edition
37
2007/08 Christel Kemke 37 function EARLEY-PARSE(words, grammar) returns chart ENQUEUE(( S, [0,0]), chart[0]) for i_from 0 to LENGTH(words) do for each state in chart[i] do if INCOMPLETE?(state) and NEXT-CAT(state) is not a part of speech then PREDICTOR(state) elseif INCOMPLETE?(state) and NEXT-CAT(state)is a part of speech then SCANNER(state) else COMPLETER(state) end return(chart) - continued - Earley-Algorithm
38
2007/08 Christel Kemke 38 procedure PREDICTOR((A B , [i,j])) for each (B ) in GRAMMAR-RULES-FOR(B, grammar) do ENQUEUE((B [j,j], chart[j]) end procedure SCANNER ((A B , [i,j])) if B PARTS-OF-SPEECH(word[j]) then ENQUEUE((B word[j], [j,j+1]), chart[j+1]) end procedure COMPLETER ((B , [j,k])) for each (A B , [i,j]) in chart[j] do ENQUEUE((A B , [i,k]), chart[k]) end procedure ENQUEUE(state, chart-entry) if state is not already in chart-entry then PUSH(state, chart-entry) end Earley-Algorithm (continued)
39
2007/08 Christel Kemke 39 Earley-Algorithm (copy from 2 nd edition) Earley – Algorithm main
40
2007/08 Christel Kemke 40 Earley-Algorithm (continued) Earley – Algorithm processes
41
2007/08 Christel Kemke 41 Earley – Algorithm complete
42
2007/08 Christel Kemke 42 Chart-Parser Algorithm (just FYI)
43
Christel Kemke 43 2007/08 Earley Algorithm - Figures Jurafsky & Martin, 2 nd ed., Ch. 13 Figures 13.16, 13.13, 13.14
44
2007/08 Christel Kemke 44 Additional References Jurafsky, D. & J. H. Martin, Speech and Language Processing, Prentice-Hall, 2000. (Chapters 9 and 10) Earley Algorithm Jurafsky & Martin, Figure 10.16, p.384 Earley Algorithm - Examples Jurafsky & Martin, Figures 10.17 and 10.18
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.