NooJ2008 Budapest 2008-06-08 Verb Valency Enhanced Croatian Lexicon Kristina Vučković, Nives Mikelić Preradović, Zdravko Dovedan

Slides:



Advertisements
Similar presentations
Sentence Classification and Clause Detection for Croatian Kristina Vučković, Željko Agić, Marko Tadić Department of Information Sciences, Department of.
Advertisements

Grammar Spinner Touch any part of the screen to begin. (Or click your mouse) Touch the screen again each time you want to spin.
NP Movement Passives, Raising: When NPs are not in their theta positions.
Greenberg 1963 Some Universals of Grammar with Particular Reference to the Order of Meaningful Elements.
Deriving Nouns from Numerals NooJ2010 Komotini 1/15 Deriving Adjectives and Nouns from Numerals Kristina Vučković, Sara Librenjak, Zdravko Dovedan University.
Towards Parsing Croatian Complex Sentences: Dependent Noun Clauses Vanja Štefanec, Kristina Vučković, Zdravko Dovedan University of Zagreb, Faculty of.
Used in place of a noun pronoun.
Noun. Noun - verb noun Noun - verb article- adj. - adj. - Noun - verb.
Improved Parser for Simple Croatian Sentences NooJ2010 Komotini 1/22 Improved Parser for Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko.
LING NLP 1 Introduction to Computational Linguistics Martha Palmer April 19, 2006.
1 A Hidden Markov Model- Based POS Tagger for Arabic ICS 482 Presentation A Hidden Markov Model- Based POS Tagger for Arabic By Saleh Yousef Al-Hudail.
1 Words and the Lexicon September 10th 2009 Lecture #3.
Eden German Grammar: main developments March-July 2003 Increase in structural complexity covered –provision of X-bar structural backbone within noun phrases.
April 26, 2007Workshop on Treebanking, NAACL-HTL 2007 Rochester1 Treebanks: Layering the Annotation Jan Hajič Institute of Formal and Applied Linguistics.
Syntax Phrase and Clause in Present-Day English. The X’ phrase system Any X phrase in PDE consists of: – an optional specifier – X’ (X-bar) which is the.
1 Introduction to Computational Linguistics Eleni Miltsakaki AUTH Fall 2005-Lecture 2.
1 CSC 594 Topics in AI – Applied Natural Language Processing Fall 2009/ Outline of English Syntax.
PARTS OF SPEECH 1 The principles of the traditional classification of the English vocabulary 2 Notional and functional parts of speech. 3 The field structure.
Improved Parser for Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty of Humanities and Social Sciences.
NooJ2009 Tozeur /22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.
11 CS 388: Natural Language Processing: Syntactic Parsing Raymond J. Mooney University of Texas at Austin.
Participles A participle is a form of a verb that acts as an adjective. –The crying woman left the movie theater. –The frustrated child ran away from home.
Chapter 4 Basics of English Grammar Business Communication Copyright 2010 South-Western Cengage Learning.
Probabilistic Parsing Reading: Chap 14, Jurafsky & Martin This slide set was adapted from J. Martin, U. Colorado Instructor: Paul Tarau, based on Rada.
Daily Grammar Practice
Macedonian DELAS – first results Aleksandar Petrovski Tetovo, Macedonia.
Integrating Semantic Dictionaries for English, French and Bulgarian into the NooJ System for the Purposes of Information Retrieval Svetla Koeva, Max Silbetztein.
A Cascaded Finite-State Parser for German Michael Schiehlen Institut für Maschinelle Sprachverarbeitung Universität Stuttgart
Notes on Pinker ch.7 Grammar, parsing, meaning. What is a grammar? A grammar is a code or function that is a database specifying what kind of sounds correspond.
_____________________ Definition Part of Speech (circle one) Picture Antonym (Opposite) Vocab Word Noun Pronoun Adjective Adverb Conjunction Verb Interjection.
A Remedial English Grammar. CHAPTERS ARTICLES AGREEMENT OF VERB AND SUBJECT CONCORD OF NOUNS, PRONOUNS AND POSSESSIVE ADJECTIVES CONFUSION OF ADJECTIVES.
Linguistic Essentials
Review of basic concepts.  The knowledge of sentences and their structure.  Syntactic rules include: ◦ The grammaticality of sentences ◦ Word order.
NooJ 2012 Paris Skup Mjesto gggg-mm-dd Derivation of Adjectives from Proper Nouns Kristina Vučković, Sara Librenjak, Zdravko Dovedan Han University.
Parsing and Translating
Grammar Eng B Let’s eat Grandpa! Let’s eat, Grandpa!
LING 388: Language and Computers Sandiway Fong Lecture 21.
Parts of Speech Review. A Noun is a person, place, thing, or idea.
Daily Grammar & Vocabulary Practice
What do we mean by Syntax? Unit 6 – Presentation 1 “the order or arrangement of words within a sentence” And what is a ‘sentence’? A group of words that.
 Chapter 8 (Part 2) Transformations Transformational Grammar Engl 424 Hayfa Alhomaid.
Grammar Slides KAPITEL 16. Relative Pronouns Recognizing Relative Clauses.
1 Introduction to Computational Linguistics Eleni Miltsakaki AUTH Spring 2006-Lecture 2.
Leonid Iomdin Institute for Information Transmission Problems, Russian Academy of Sciences
◦ Process of describing the structure of phrases and sentences Chapter 8 - Phrases and sentences: grammar1.
AUTONOMOUS REQUIREMENTS SPECIFICATION PROCESSING USING NATURAL LANGUAGE PROCESSING - Vivek Punjabi.
Parts of Speech By: Miaya Nischelle Sample. NOUN A noun is a person place or thing.
Syntax II. Specifiers Specifiers tell us more information about nouns, verbs, adjectives, adverbs and prepositions The, a, this, three, some, many etc.
What do we do with this Latin Part of Speech ( PoS )? Latin to English.
Natural Language Processing Vasile Rus
Descriptive Grammar – 2S, 2016 Mrs. Belén Berríos Droguett
The theory of word classes in modern grammar studies
Lecture – VIII Monojit Choudhury RS, CSE, IIT Kharagpur
CKY Parser 0Book 1 the 2 flight 3 through 4 Houston5 6/19/2018
Probabilistic CKY Parser
Nouns Nouns not noun noun noun not not
Grammar Review.
Chapter 4 Basics of English Grammar
CKY Parser 0Book 1 the 2 flight 3 through 4 Houston5 11/16/2018
CS 388: Natural Language Processing: Syntactic Parsing
How To Answer Questions in Latin!
Daily Grammar Practice
Towards Parsing Croatian Complex Sentences: Dependent Noun Clauses
Extracting verb valency frames with NooJ
Parts of speech.
PREPOSITIONAL PHRASES
Linguistic Essentials
Chapter 4 Basics of English Grammar
Daily Grammar & Vocabulary Practice
Daily Grammar & Vocabulary Practice
Presentation transcript:

NooJ2008 Budapest Verb Valency Enhanced Croatian Lexicon Kristina Vučković, Nives Mikelić Preradović, Zdravko Dovedan Faculty of Humanities and Social Sciences University of Zagreb Department of Information Sciences Ivana Lucica 3, Zagreb, Croatia

NooJ2008 Budapest The Plan OOur agenda? IIncrease # of unambiguos NPs BBy means of? EExisting chunker VVerb valency tags WWhy? TTo raise the chunker performence to a higher level MMake preparations for a Croatian parser

NooJ2008 Budapest Overview CCroatian verb valency lexicon mmain characteristics sselected data ..xml to.dic conversion hhow we did it pprevious grammars for <<VP> |<NP> | <PP> selection nnew enhanced grammars <<VP+DCobl> <<VP+PCobl> <<VP+PCtyp> rresults comparison pprecision, rrecall, ff-measure

NooJ2008 Budapest Croatian verb valency lexicon - CROVALLEX  Formal description of verb valency frames  1739 verbs  selected from the Croatian frequency dictionary,  5118 valency frames (in average: 3 frames per verb)  Each frame entry contains descriptions of  valence frame  frame attributes  frame attributes are either obligatory or optional i.e. obligatory or typical!

NooJ2008 Budapest Selected data 1.Reflexive particle ‘ se ’  if the verb is derived reflexive (e.g. vratiti se)  reflexiva tantum (e.g. smijati se).

NooJ2008 Budapest Selected data 2.Pure (prepositionless) case.  7 morphological cases in Croatian.  0 - hidden nominative,  1 - nominative,  2 - genitive,  3 - dative,  4 - accusative,  5 - vocative,  6 - locative,  7 - instrumental.

NooJ2008 Budapest Selected data 3.Prepositional case.  Lemma of the preposition and  number of the required morphological case are specified, e.g.  od+2,  na+4,  o+6

NooJ2008 Budapest  pjevati,aspect=inf+DC_obl=0+AL_typ+PC_obl=6+… CROVALLEX *.xml

NooJ2008 Budapest Converting to *.dic

NooJ2008 Budapest Croatian lexicon  Nouns –  Adjectives –  Verbs  Adverbs  Proper Nouns –  S + C + Q + I + PRO - 363

NooJ2008 Budapest Previous grammars

NooJ2008 Budapest Perfect

NooJ2008 Budapest II. Future

NooJ2008 Budapest

NooJ2008 Budapest New Grammars

NooJ2008 Budapest Verb + Obligatory DC

NooJ2008 Budapest Verb + obligatory PC

NooJ2008 Budapest Verb + typical PC

NooJ2008 Budapest VP+DCobl=

NooJ2008 Budapest VP+DCobl=Genitiv

NooJ2008 Budapest VP+DCobl=Dativ

NooJ2008 Budapest agreement

NooJ2008 Budapest Results By handBefore CROVALLEX After CROVALLEX # of NP # of T unambiguous NP # of ambiguous NP # of F unambiguous NP 26+20

NooJ2008 Budapest P-R-F for unambiguous NPs Before CROVALLEX After CROVALLEX Precision 33,3168,13 Recall 52,2663,39 F-measure 40,6965,68

NooJ2008 Budapest Future work  Subordinating conjunction.  Infinitive construction can appear  with a preposition (e.g. 'nego+inf')  with the morphological case (e.g. 'inf+4').  Construction with adjectives.  e.g. adj-7 ('Osjećam se osvježenim' - 'I feel fresh').  Construction with adverbs.  e.g. adv-hrabro ('Osjećam se hrabro' - 'I feel brave').  Construction with nominative predicate.  e.g. nom_pred ('Historija je postala legendom' - 'History has become a legend').