Dekai Wu Presented by David Goss-Grubbs

Slides:



Advertisements
Similar presentations
CSA2050: DCG I1 CSA2050 Introduction to Computational Linguistics Lecture 8 Definite Clause Grammars.
Advertisements

Translator Architecture Code Generator ParserTokenizer string of characters (source code) string of tokens abstract program string of integers (object.
Syntactic analysis using Context Free Grammars. Analysis of language Morphological analysis – Chairs, Part Of Speech (POS) tagging – The/DT man/NN left/VBD.
Grammars, constituency and order A grammar describes the legal strings of a language in terms of constituency and order. For example, a grammar for a fragment.
May 2006CLINT-LN Parsing1 Computational Linguistics Introduction Approaches to Parsing.
March 1, 2009 Dr. Muhammed Al-Mulhem 1 ICS 482 Natural Language Processing Probabilistic Context Free Grammars (Chapter 14) Muhammed Al-Mulhem March 1,
Chapter 4 Lexical and Syntax Analysis Sections 1-4.
ISBN Chapter 4 Lexical and Syntax Analysis The Parsing Problem Recursive-Descent Parsing.
Parsing — Part II (Ambiguity, Top-down parsing, Left-recursion Removal)
Normal forms for Context-Free Grammars
Chapter 3: Formal Translation Models
Models of Generative Grammar Smriti Singh. Generative Grammar  A Generative Grammar is a set of formal rules that can generate an infinite set of sentences.
11 CS 388: Natural Language Processing: Syntactic Parsing Raymond J. Mooney University of Texas at Austin.
Unsupervised learning of Natural languages Eitan Volsky Yasmine Meroz.
Stochastic Inversion Transduction Grammars Dekai Wu Advanced Machine Translation Seminar Presented by: Sanjika Hewavitharana 04/13/2006.
May 2006CLINT-LN Parsing1 Computational Linguistics Introduction Parsing with Context Free Grammars.
Context Free Grammars Reading: Chap 9, Jurafsky & Martin This slide set was adapted from J. Martin, U. Colorado Instructor: Rada Mihalcea.
11 Chapter 14 Part 1 Statistical Parsing Based on slides by Ray Mooney.
November 2011CLINT-LN CFG1 Computational Linguistics Introduction Context Free Grammars.
CSA2050 Introduction to Computational Linguistics Parsing I.
PARSING 2 David Kauchak CS159 – Spring 2011 some slides adapted from Ray Mooney.
CS 4705 Lecture 10 The Earley Algorithm. Review Top-Down vs. Bottom-Up Parsers –Both generate too many useless trees –Combine the two to avoid over-generation:
Parser: CFG, BNF Backus-Naur Form is notational variant of Context Free Grammar. Invented to specify syntax of ALGOL in late 1950’s Uses ::= to indicate.
PARSING David Kauchak CS159 – Fall Admin Assignment 3 Quiz #1  High: 36  Average: 33 (92%)  Median: 33.5 (93%)
LING 575 Lecture 5 Kristina Toutanova MSR & UW April 27, 2010 With materials borrowed from Philip Koehn, Chris Quirk, David Chiang, Dekai Wu, Aria Haghighi.
Context Free Grammars & Parsing CPSC 388 Fall 2001 Ellen Walker Hiram College.
10/31/00 1 Introduction to Cognitive Science Linguistics Component Topic: Formal Grammars: Generating and Parsing Lecturer: Dr Bodomo.
Natural Language Processing Vasile Rus
Context Free Grammars. Slide 1 Syntax Syntax = rules describing how words can connect to each other * that and after year last I saw you yesterday colorless.
Describing Syntax and Semantics Chapter 3: Describing Syntax and Semantics Lectures # 6.
Natural Language Processing Vasile Rus
Comp 411 Principles of Programming Languages Lecture 3 Parsing
Chapter 3 – Describing Syntax
Describing Syntax and Semantics
Parsing Recommended Reading: Ch th Jurafsky & Martin 2nd edition
Introduction to Parsing
Programming Languages Translator
CS510 Compiler Lecture 4.
Lexical and Syntax Analysis
Fall Compiler Principles Context-free Grammars Refresher
Introduction to Parsing (adapted from CS 164 at Berkeley)
Basic Parsing with Context Free Grammars Chapter 13
Syntax Specification and Analysis
Parsing — Part II (Top-down parsing, left-recursion removal)
What does it mean? Notes from Robert Sebesta Programming Languages
Syntax Analysis Chapter 4.
4 (c) parsing.
Parsing Techniques.
Top-Down Parsing.
CSCI 5832 Natural Language Processing
Compiler Design 4. Language Grammars
Lexical and Syntax Analysis
Training Tree Transducers
ENERGY 211 / CME 211 Lecture 15 October 22, 2008.
Earley’s Algorithm (1970) Nice combo of our parsing ideas so far:
Chapter 2: A Simple One Pass Compiler
Parsing and More Parsing
Lecture 7: Introduction to Parsing (Syntax Analysis)
R.Rajkumar Asst.Professor CSE
Compilers Principles, Techniques, & Tools Taught by Jing Zhang
Chapter 4: Lexical and Syntax Analysis Sangho Ha
Fall Compiler Principles Context-free Grammars Refresher
Chapter 3 Describing Syntax and Semantics.
David Kauchak CS159 – Spring 2019
High-Level Programming Language
Compilers Principles, Techniques, & Tools Taught by Jing Zhang
Discrete Maths 13. Grammars Objectives
David Kauchak CS159 – Spring 2019
COMPILER CONSTRUCTION
Parsing CSCI 432 Computer Science Theory
Presentation transcript:

Dekai Wu Presented by David Goss-Grubbs Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora Dekai Wu Presented by David Goss-Grubbs

Inversion Transduction Grammars What they are How they work What they can do

What an ITG is A formalism for modeling bilingual sentence pairs A transducer: it defines a relation between sentences Conceived as generating pairs of sentences rather than translating

Grammar Scope Not intended to relate a sentence to all and only its correct translations Used to extract useful information from parallel corpora They will overgenerate wildly.

How ITGs work A subset of ‘context-free syntax-directed transduction grammars’. A simple transduction grammar is just a CFG whose terminals are pairs of symbols (or singletons) In an ITG the order of the constituents in one language may be the reverse of the other language, for any given rule.

Notation The right-hand side of a rule is in square brackets [ ] when the order is the same in both languages Angle brackets   are used when the order is reversed.

Yoda Speak S  SubjAux VP SubjAux  [NP Aux] VP  ‘begun’ / ‘begunY’ NP  ‘the-clone-war’ / ‘the-clone-warY’ Aux  ‘has’ / ‘hasY’ ‘the-clone-war has begun’  ‘begunY the-clone-warY hasY’

Yoda Speak S SubjAux VP NP Aux begun The clone war has

Normal Form For any ITG there is a weakly equivalent grammar in the normal form All right-hand sides are either: Terminal couples Terminal singletons Pairs of non-terminals with straight orientation Pairs of non-terminals with inverted orientation

Expressiveness Limits Not every way of matching is possible ‘Obi (has) not won victory’ cannot be matched with ‘notY victoryY ObiY wonY’. This is a good thing: We only have to consider a subset of the possible matchings The percentage of possibilities eliminated increases rapidly as the number of tokens increases

Expressiveness Limits

Stochastic ITGs A probability can be added to each rewrite rule. The probabilities of all the rules with a given left hand side must sum to 1. An SITG will give the most probable matching parse for a sentence pair.

Parsing with an SITG: the chart Five dimensions to the chart: start and stop indices for sentence 1; start and stop indices for sentence 2; nonterminal category. Each cell stores the probability of the most likely parse covering the appropriate substrings, rooted in the appropriate category.

Parsing with an SITG: the algorithm Initialize the cells corresponding to terminals using a translation lexicon For the other cells, find the most probable way of getting that category. Compute the probability by multiplying the probability of the rule by the probabilities of both the constituents Store that probability plus the orientation of the rule

What you can do with an ITG Segmentation Bracketing Alignment Bilingual Constraint Transfer

Segmentation Several words might go together to make a single lexical entry Several characters might go together to make a single word “sandwiches there” vs “sand which is there” A segmentation may make sense in the monolingual case, but not in the bilingual case

Segmentation Change the parsing algorithm: Allow the initialization step to find strings of any length in the translation lexicon. The recursive step stores the most probable way of creating a constituent, whether it came from the lexicon or from rules.

Bracketing How to assign structure to a sentence with no grammar available? Get a parallel corpus pairing it with some other language Get a reasonable translation dictionary Parse it with a bracketing transduction grammar

Bracketing Transduction Grammars A minimal, generic ITG Just one nonterminal A  [A A], A A, terminal couples, singletons The important probabilities are on the rules that rewrite to terminal couples, taken from the translation lexicon.

Bracketing Transduction Grammars Given lexical translation probabilities, only a subset of otherwise possible bracketings are available. ‘Obi not won victory’  ‘not victory Obi won’ is a limiting case – no bracketings ‘the-clone-war has begun’ has two bracketings When paired with ‘begun the-clone-war has’, it has just one bracketing

Bracketing with Singletons Singletons don’t help in bracketing. Depending on the language, Wu uniformly attaches them to the left or to the right. They are then ‘pushed down’ using yield-preserving transformations. e.g. [ x  A B  ] =   x A  B 

Avoiding Arbitrary Choices Some arrangements leave us with an arbitrary choice ‘create a-perimeter around-the-survivors’  ‘around-the-survivors a-perimeter create’   A B  C  and  A  B C   both work. Use a more complex bracketing grammar that makes such things left-branching Fix it in post-processing to be  A B C 

Bracketing Experiment They tested on 2000 English-Chinese sentence pairs They rejected sentence pairs that weren’t adequately covered by the translation lexicon. 80% bracket precision for English, 78% bracket precision for Chinese

Alignment Alignments (phrasal or lexical) are a natural byproduct of bilingual parsing. Unlike ‘parse-parse-match’ methods, this Doesn’t require a fancy grammar for both languages Guarantees compatibility between parses Has a principled way of choosing between possible alignments Provides a more reasonable ‘distortion penalty’.

Bilingual Constraint Transfer A high-quality parse for one language can be leveraged to get structure for the other. Alter the parsing algorithm to only allow constituents that match the parse that already exists for the well-known language. This works for any sort of constraint supplied for the well-known language.