Notes on Features. Ling 571 Deep Techniques for NLP February 10, 2014

Similar documents
Chapter 4: Valence & Agreement CSLI Publications

An Interactive Intelligent Language Tutor Over The Internet

Feature-Based Grammar

CS 598 Natural Language Processing

Indeterminacy by Underspecification Mary Dalrymple (Oxford), Tracy Holloway King (PARC) and Louisa Sadler (Essex) (9) was: ( case) = nom ( case) = acc

Underlying and Surface Grammatical Relations in Greek consider

Introduction to HPSG. Introduction. Historical Overview. The HPSG architecture. Signature. Linguistic Objects. Descriptions.

Basic Parsing with Context-Free Grammars. Some slides adapted from Julia Hirschberg and Dan Jurafsky 1

Case government vs Case agreement: modelling Modern Greek case attraction phenomena in LFG

Natural Language Processing. George Konidaris

Developing a TT-MCTAG for German with an RCG-based Parser

Approaches to control phenomena handout Obligatory control and morphological case: Icelandic and Basque

Gender and defaults *

Syntactic types of Russian expressive suffixes

Language Learning and Development. ISSN: (Print) (Online) Journal homepage:

A Minimalist Approach to Code-Switching. In the field of linguistics, the topic of bilingualism is a broad one. There are many

ENGBG1 ENGBL1 Campus Linguistics. Meeting 2. Chapter 7 (Morphology) and chapter 9 (Syntax) Pia Sundqvist

On the Notion Determiner

In Udmurt (Uralic, Russia) possessors bear genitive case except in accusative DPs where they receive ablative case.

EAGLE: an Error-Annotated Corpus of Beginning Learner German

Enhancing Unlexicalized Parsing Performance using a Wide Coverage Lexicon, Fuzzy Tag-set Mapping, and EM-HMM-based Lexical Probabilities

Context Free Grammars. Many slides from Michael Collins

Modeling full form lexica for Arabic

Construction Grammar. University of Jena.

Inflection Classes and Economy

Phenomena of gender attraction in Polish *

Words come in categories

Author: Fatima Lemtouni, Wayzata High School, Wayzata, MN

Syntax Parsing 1. Grammars and parsing 2. Top-down and bottom-up parsing 3. Chart parsers 4. Bottom-up chart parsing 5. The Earley Algorithm

Grammars & Parsing, Part 1:

11/29/2010. Statistical Parsing. Statistical Parsing. Simple PCFG for ATIS English. Syntactic Disambiguation

UC Berkeley Berkeley Undergraduate Journal of Classics

MODELING DEPENDENCY GRAMMAR WITH RESTRICTED CONSTRAINTS. Ingo Schröder Wolfgang Menzel Kilian Foth Michael Schulz * Résumé - Abstract

Tutorial on Paradigms

Parsing of part-of-speech tagged Assamese Texts

Type Theory and Universal Grammar

Accurate Unlexicalized Parsing for Modern Hebrew

Participate in expanded conversations and respond appropriately to a variety of conversational prompts

6.863J Natural Language Processing Lecture 12: Featured attraction. Instructor: Robert C. Berwick

Compositional Semantics

cmp-lg/ Jul 1995

Applications of memory-based natural language processing

Interactive Corpus Annotation of Anaphor Using NLP Algorithms

The building blocks of HPSG grammars. Head-Driven Phrase Structure Grammar (HPSG) HPSG grammars from a linguistic perspective

Dreistadt: A language enabled MOO for language learning

The presence of interpretable but ungrammatical sentences corresponds to mismatches between interpretive and productive parsing.

Language Acquisition by Identical vs. Fraternal SLI Twins * Karin Stromswold & Jay I. Rifkin

Specifying a shallow grammatical for parsing purposes

arxiv:cmp-lg/ v1 7 Jun 1997 Abstract

Citation for published version (APA): Veenstra, M. J. A. (1998). Formalizing the minimalist program Groningen: s.n.

THE VERB ARGUMENT BROWSER

INTRODUCTION TO MORPHOLOGY Mark C. Baker and Jonathan David Bobaljik. Rutgers and McGill. Draft 6 INFLECTION

Constraining X-Bar: Theta Theory

Ensemble Technique Utilization for Indonesian Dependency Parser

(12) United States Patent Bernth et al.

Chunk Parsing for Base Noun Phrases using Regular Expressions. Let s first let the variable s0 be the sentence tree of the first sentence.

AN EXPERIMENTAL APPROACH TO NEW AND OLD INFORMATION IN TURKISH LOCATIVES AND EXISTENTIALS

Type-driven semantic interpretation and feature dependencies in R-LFG

Informatics 2A: Language Complexity and the. Inf2A: Chomsky Hierarchy

A Computational Evaluation of Case-Assignment Algorithms

Derivational and Inflectional Morphemes in Pak-Pak Language

Using dialogue context to improve parsing performance in dialogue systems

Using a Native Language Reference Grammar as a Language Learning Tool

International Journal of Informative & Futuristic Research ISSN (Online):

Adapting Stochastic Output for Rule-Based Semantics

Derivational: Inflectional: In a fit of rage the soldiers attacked them both that week, but lost the fight.

Morphosyntactic and Referential Cues to the Identification of Generic Statements

The Role of the Head in the Interpretation of English Deverbal Compounds

Aspectual Classes of Verb Phrases

The History of Language Teaching

(3) Vocabulary insertion targets subtrees (4) The Superset Principle A vocabulary item A associated with the feature set F can replace a subtree X

The analysis starts with the phonetic vowel and consonant charts based on the dataset:

Argument structure and theta roles

Control and Boundedness

Objectives. Chapter 2: The Representation of Knowledge. Expert Systems: Principles and Programming, Fourth Edition

Universal Grammar 2. Universal Grammar 1. Forms and functions 1. Universal Grammar 3. Conceptual and surface structure of complex clauses

Formulaic Language and Fluency: ESL Teaching Applications

Introduction, Organization Overview of NLP, Main Issues

Beyond the Pipeline: Discrete Optimization in NLP

Specification and Evaluation of Machine Translation Toy Systems - Criteria for laboratory assignments

Analysis of Probabilistic Parsing in NLP

Hindi Aspectual Verb Complexes

Multiple case assignment and the English pseudo-passive *

Basic concepts: words and morphemes. LING 481 Winter 2011

Refining the Design of a Contracting Finite-State Dependency Parser

BASIC ENGLISH. Book GRAMMAR

The Acquisition of Person and Number Morphology Within the Verbal Domain in Early Greek

C.A.E. LUSCHNIG ANCIENT GREEK. A Literary Appro a c h. Second Edition Revised by C.A.E. Luschnig and Deborah Mitchell

Modeling Attachment Decisions with a Probabilistic Parser: The Case of Head Final Structures

1 The problem with optional syntactic rules in the paraphrasing system of MTT

The Acquisition of English Grammatical Morphemes: A Case of Iranian EFL Learners

Syntactic Agreement. Roberta D Alessandro 18 November 2015

"f TOPIC =T COMP COMP... OBJ

2014 Colleen Elizabeth Fitzgerald

Target Language Preposition Selection an Experiment with Transformation-Based Learning and Aligned Bilingual Data

Some Principles of Automated Natural Language Information Extraction

Character Stream Parsing of Mixed-lingual Text

Semi-supervised methods of text processing, and an application to medical concept extraction. Yacine Jernite Text-as-Data series September 17.

AQUA: An Ontology-Driven Question Answering System

THE MORPHO-PHONOLOGY OF POLISH MASCULINE PERSONAL DECLENSIONS Sławomir Zdziebko

Transcription:

Notes on Features Ling 571 Deep Techniques for NLP February 10, 2014

Feature Grammar in NLTK NLTK supports feature-based grammars Includes ways of associating features with CFG rules Includes readers for feature grammars.fcfg files Includes parsers Nltk.parse.FeatureEarleyChartParser

Feature Structures >>> fs1 = nltk.featstruct( [NUM= pl ] ) >>> print fs1 [NUM= pl ] >>> print fs1[ NUM ] pl More complex structure >>> fs2 = nltk.featstruct( [POS= N, AGR=[NUM= pl,per=3]] )

Reentrant Feature Structures First instance Parenthesized integer: (1) Subsequent instances: Pointer : -> (1) >>> print nltk.featstruct("[a='a', B=(1)[C='c'], D->(1)] [ A = a ] [ B = (1) [ C = c ]] [ D -> (1) ]

Augmenting Grammars Attach feature information to non-terminals, on N[AGR=[NUM='pl']] -> 'students N[AGR=[NUM= sg']] -> 'student So far, all values are literal or reentrant Variables allow generalization:?a Allows underspecification, e.g. Det[GEN=?a] NP[AGR=?a] -> Det[AGR=?a] N[AGR=?a]

Mechanics >>> fs3 = nltk.featstruct(num= pl,per=3) >>> fs4 = nltk.featstruct(num= pl ) >>> print fs4.unify(fs3) [NUM = pl ] [PER = 3 ]

Morphosyntactic Features Grammatical feature that influences morphological or syntactic behavior English: Number: Dog, dogs Person: Am; are; is Case: I me; he him; etc Countability:

Semantic Features Grammatical features that influence semantic(meaning) behavior of associated units E.g.:

Semantic Features Grammatical features that influence semantic(meaning) behavior of associated units E.g.:?The rocks slept.

Semantic Features Grammatical features that influence semantic(meaning) behavior of associated units E.g.:?The rocks slept.?colorless green ideas sleep furiously.

Semantic Features Many proposed: Animacy: +/- Natural gender: masculine, feminine, neuter Human: +/- Adult: +/- Liquid: +/- Etc. The milk spilled.?the cat spilled.

Examples The climber hiked for six hours. The climber hiked on Saturday. The climber reached the summit on Saturday. *The climber reached the summit for six hours. Contrast:

Examples The climber hiked for six hours. The climber hiked on Saturday. The climber reached the summit on Saturday. *The climber reached the summit for six hours. Contrast: Achievement vs activity

Semantic features & Parsing Can filter some classes of ambiguity Old men and women slept. (Old men) and (women) slept. (Old (men and women)) slept. Sleeping people and books lie flat. (Sleeping people) and (books) lie flat. (Sleeping (people and books ))lie flat.

Semantic features & Parsing Can filter some classes of ambiguity Old men and women slept. (Old men) and (women) slept. (Old (men and women)) slept. Sleeping people and books lie flat. (Sleeping people) and (books) lie flat. *(Sleeping (people and books ))lie flat.

Summary Features Enable compact representation of grammatical constraints Capture basic linguistic patterns Unification Creates and maintains consistency over features Integration with parsing allows filtering of illformed analyses

More Complex German Subject singular, masc der Hund The dog Example Subject plural, masc die Hunde The dogs

More Complex German Example Objects determined by verb Dative singular, masc dem Hund The dog Accusative plural, masc die Hunde The dogs

Contrast Subject: Die Katze The cat Subject: plural Die Katzen The cats

Contrast Object: Die Katze The cat Object: Der Katze The cat

Analysis What are the key contrasts? Number Singular, plural Gender Masc, Fem,. Case: Subject (nom), dative, accusative,. + Interactions

Feature Interaction Interactions of German case, number, gender Case Masc Fem Neut PL Nom Der Die Das Die Gen Des Der Des Den Dat Dem Der Dem Den Acc Den Die Das Die

Examples of Interaction Die The.Nom.Fem.sg The cat sees the dog Katze Cat.3.FEM.SG Sieht See.3.sg Den The.Acc.Masc.sg Hund Dog.3.Masc.sg

Examples of Interaction Die The.Nom.Fem.sg The cat sees the dog Katze Cat.3.FEM.SG Sieht See.3.sg Den The.Acc.Masc.sg Hund Dog.3.Masc.sg *Die The.Nom.Fem.sg The cat sees the dog Katze Cat.3.FEM.SG Sieht See.3.sg Dem The.Dat.Masc.sg Hund Dog.3.Masc.sg

Examples of Interaction Die The.Nom.Fem.sg The cat sees the dog Katze Cat.3.FEM.SG Sieht See.3.sg Den The.Acc.Masc.sg Hund Dog.3.Masc.sg *Die The.Nom.Fem.sg The cat sees the dog Katze Cat.3.FEM.SG Sieht See.3.sg Dem The.Dat.Masc.sg Hund Dog.3.Masc.sg Die The.Nom.Fem.sg The cat helps the dog Katze Cat.3.FEM.SG hilft help.3.sg Dem The.Dat.Masc.sg Hund Dog.3.Masc.sg

Examples of Interaction Die The.Nom.Fem.sg The cat sees the dog Katze Cat.3.FEM.SG Sieht See.3.sg Den The.Acc.Masc.sg Hund Dog.3.Masc.sg *Die The.Nom.Fem.sg The cat sees the dog Katze Cat.3.FEM.SG Sieht See.3.sg Dem The.Dat.Masc.sg Hund Dog.3.Masc.sg Die The.Nom.Fem.sg The cat helps the dog Katze Cat.3.FEM.SG hilft help.3.sg Dem The.Dat.Masc.sg Hund Dog.3.Masc.sg *Die The.Nom.Fem.sg The cat sees the dog Katze Cat.3.FEM.SG hilft help.3.sg Dem The.Acc.Masc.sg Hund Dog.3.Masc.sg German verbs in, at least, 2 classes: assign diff t object case