CS460/626 : Natural Language Processing/Speech, NLP and the Web (Lecture 8 POS tagset) Pushpak Bhattacharyya CSE Dept., IIT Bombay 17 th Jan, 2012

Similar documents
CS838-1 Advanced NLP: Hidden Markov Models

Empirical Methods in Natural Language Processing Lecture 11 Part-of-speech tagging and HMMs

CS460/626 : Natural Language Processing/Speech, NLP and the Web

CS626: NLP, Speech and the Web. Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture 14: Parsing Algorithms 30 th August, 2012

Lecture 13: Structured Prediction

HMM and Part of Speech Tagging. Adam Meyers New York University

Hidden Markov Models (HMMs)

CS460/626 : Natural Language

Hidden Markov Models

Hidden Markov Models

INF4820: Algorithms for Artificial Intelligence and Natural Language Processing. Hidden Markov Models

Processing/Speech, NLP and the Web

CS460/626 : Natural Language

Lecture 7: Sequence Labeling

ACS Introduction to NLP Lecture 2: Part of Speech (POS) Tagging

INF4820: Algorithms for Artificial Intelligence and Natural Language Processing. Hidden Markov Models

CS460/626 : Natural Language Processing/Speech, NLP and the Web (Lecture 18 Alignment in SMT and Tutorial on Giza++ and Moses)

POS-Tagging. Fabian M. Suchanek

Part of Speech Tagging: Viterbi, Forward, Backward, Forward- Backward, Baum-Welch. COMP-599 Oct 1, 2015

10/17/04. Today s Main Points

Statistical Methods for NLP

LECTURER: BURCU CAN Spring

Part-of-Speech Tagging

Lecture 9: Hidden Markov Model

Statistical methods in NLP, lecture 7 Tagging and parsing

Sequence Labeling: HMMs & Structured Perceptron

Lecture 6: Part-of-speech tagging

Graphical models for part of speech tagging

CS 712: Topics in NLP Linguistic Phrases and Statistical Phrases

INF4820: Algorithms for Artificial Intelligence and Natural Language Processing. Language Models & Hidden Markov Models

CS : Speech, NLP and the Web/Topics in AI

Natural Language Processing

More on HMMs and other sequence models. Intro to NLP - ETHZ - 18/03/2013

Hindi Generation from Interlingua (UNL) Om P. Damani, IIT Bombay (Joint work with S. Singh, M. Dalal, V. Vachhani, P.

Artificial Intelligence

Language Processing with Perl and Prolog

Lecture 12: Algorithms for HMMs

Lecture 12: Algorithms for HMMs

Natural Language Processing

Part-of-Speech Tagging

Probabilistic Graphical Models

Hidden Markov Models

LECTURER: BURCU CAN Spring

Hidden Markov Models

Hidden Markov Models in Language Processing

Part-of-Speech Tagging + Neural Networks CS 287

Sequential Data Modeling - The Structured Perceptron

NLP Programming Tutorial 11 - The Structured Perceptron

Midterm sample questions

Parsing. Based on presentations from Chris Manning s course on Statistical Parsing (Stanford)

Today s Agenda. Need to cover lots of background material. Now on to the Map Reduce stuff. Rough conceptual sketch of unsupervised training using EM

TnT Part of Speech Tagger

Lecture 3: ASR: HMMs, Forward, Viterbi

Text Mining. March 3, March 3, / 49

Statistical NLP for the Web Log Linear Models, MEMM, Conditional Random Fields

Posterior vs. Parameter Sparsity in Latent Variable Models Supplementary Material


LING 473: Day 10. START THE RECORDING Coding for Probability Hidden Markov Models Formal Grammars

Log-Linear Models, MEMMs, and CRFs

CSE 517 Natural Language Processing Winter2015

CS388: Natural Language Processing Lecture 4: Sequence Models I

The Noisy Channel Model and Markov Models

PRONOUN सव न म. Mishra English Study Centre BY M. K. Mishra

Extraction of Opposite Sentiments in Classified Free Format Text Reviews

CSCI 5832 Natural Language Processing. Today 2/19. Statistical Sequence Classification. Lecture 9

Degree in Mathematics

Natural Language Processing

COMP90051 Statistical Machine Learning

CMSC 723: Computational Linguistics I Session #5 Hidden Markov Models. The ischool University of Maryland. Wednesday, September 30, 2009

Extracting Information from Text

Sequences and Information

Natural Language Processing CS Lecture 06. Razvan C. Bunescu School of Electrical Engineering and Computer Science

Statistical Methods for NLP

Natural Language Processing : Probabilistic Context Free Grammars. Updated 5/09

Lecture 4: Smoothing, Part-of-Speech Tagging. Ivan Titov Institute for Logic, Language and Computation Universiteit van Amsterdam

with Local Dependencies

Time & Tense समय और य क प. Mishra English Study Centre BY M. K. Mishra

Hidden Markov Models, Part 1. Steven Bedrick CS/EE 5/655, 10/22/14

Sentence-level processing

Advanced Natural Language Processing Syntactic Parsing

Ahmedabad. Orientation ( ) (Class-III)

AN ABSTRACT OF THE DISSERTATION OF

Ngram Review. CS 136 Lecture 10 Language Modeling. Thanks to Dan Jurafsky for these slides. October13, 2017 Professor Meteer

Today. Finish word sense disambigua1on. Midterm Review

Hidden Markov Models Hamid R. Rabiee

NLP= Linguistics + ML? Pushpak Bhattacharyya IIT Patna and IIT Bombay CICLING special event 23rd March, 2018 Hanoi

Probabilistic Context-free Grammars

Parsing with Context-Free Grammars

Natural Language Processing

Sequential Supervised Learning

Applied Natural Language Processing

ST.ALBANS SCHOOL HOLIDAY HOMEWORK ( ) CLASS III SUBJECT- ENGLISH Learn and recite the poem

A gentle introduction to Hidden Markov Models

10 : HMM and CRF. 1 Case Study: Supervised Part-of-Speech Tagging

Statistical Methods for NLP

A.I. in health informatics lecture 8 structured learning. kevin small & byron wallace

Recap: HMM. ANLP Lecture 9: Algorithms for HMMs. More general notation. Recap: HMM. Elements of HMM: Sharon Goldwater 4 Oct 2018.

L.P.Savasni Academy. Yearly Syllabus Class VI Hindi SST. Maths. Science. Sanskrit. Computer. [Type text] [Type text] [Type text]

CS395T: Structured Models for NLP Lecture 5: Sequence Models II

Background of Indic segmentation

Transcription:

CS460/626 : Natural Language Processing/Speech, NLP and the Web (Lecture 8 POS tagset) Pushpak Bhattacharyya CSE Dept., IIT Bombay 17 th Jan, 2012

HMM: Three Problems Problem Problem 1: Likelihood of a sequence Forward Procedure Backward Procedure Problem 2: Best state sequence Viterbi Algorithm Problem 3: Re-estimation Baum-Welch ( Forward- Backward Algorithm ) CRF Algorithm Parsing Morph Analysis HMM MEMM Semantics Part of Speech Tagging Hindi Marathi POS tagging English NLP Trinity French Language

Tagged Corpora ^_^ _ The_DT guys_nns that_wdt make_vbp traditional_jj hardware_nn are_vbp really_rb being_vbg obsoleted_vbn by_in microprocessorbased_jj machines_nns,_, _ said_vbd Mr._NNP Benton_NNP._.$_$

For Hindi Rama achhaa gaata hai. (hai is VAUX : Auxiliary verb) ; Ram sings well Rama achha ladakaa hai. (hai is VCOP : Copula verb) ; Ram is a good boy

Example of difficulty in POS tagging

Tags Content Word Function Word Noun Adjective Verb Tags Prepositi Pronoun on Conjunctio n Proper Noun NNP (for NER) Common Noun NN NNS VBP VBD VBG VBN Injection

Difficulty in POS Tagging Consider the following sentences: र म अ छ ग त ह _VAUX (auxiliary verb) Ram good sing is : Ram sings well GNPTAM for ग त only : Male, Singular,??,??,??,- GNPTAM for ग त ह : Male, Singular, 2 nd or 3 rd, Present, Default, Declarative र म अ छ लड़क ह _VCOP (copular verb) Ram good boy is : Ram is a good boy In general, VAUX, VM (main verb) and VCOP cannot be separated easily

Difficulty in POS Tagging To POS Tag based on Rules, one simple rule could be: ह Preceded by verb Preceded by nominal VAUX VCOP Facilitates co-reference स म न धकरण This is a High Precision, Low Recall rule, i.e. when it says Yes is indeed Yes but a No may not actually be No

Exceptions to the previous rule False Negative for VAUX Particle Injection (Particles: भ -Bhi, त -To, ह -Hi, नह -Nahi) Consider the following sentences: र म ग त त अ छ ह, पर... र म अ छ ह _VCOP र म त ग त अ छ ह _VAUX POS TAGs of ह vary here despite the preceding word being an adjective

Evaluation of POS Tag Accuracy Precision, Recall and F-Score Given G (what our system returns) False Positive Agreement Ideal I (Actual Tags) False Negative Precision P= G I / I Recall R= G I / I F-Score = 2PR/(P+R)

POS tag computation (1/2) Best tag sequence = T* = argmax P(T W) = argmax P(T)P(W T) (by Baye s Theorem) P(T) = P(t 0 =^ t 1 t 2 t n+1 =.) = P(t 0 )P(t 1 t 0 )P(t 2 t 1 t 0 )P(t 3 t 2 t 1 t 0 ) P(t n t n-1 t n-2 t 0 )P(t n+1 t n t n-1 t 0 ) = P(t 0 )P(t 1 t 0 )P(t 2 t 1 ) P(t n t n-1 )P(t n+1 t n ) N+1 = P(t i t i-1 ) Bigram Assumption i = 0

POS tag computation (2/2) P(W T) = P(w 0 t 0 -t n+1 )P(w 1 w 0 t 0 -t n+1 )P(w 2 w 1 w 0 t 0 -t n+1 ) P(w n w 0 -w n-1 t 0 -t n+1 )P(w n+1 w 0 -w n t 0 -t n+1 ) Assumption: A word is determined completely by its tag. This is inspired by speech recognition = P(w o t o )P(w 1 t 1 ) P(w n+1 t n+1 ) n+1 = P(w i t i ) i = 0 n+1 i = 1 = P(w i t i ) (Lexical Probability Assumption)

Example People jump high. People : Noun/Verb jump : Noun/Verb high : Noun/Adjective We can start with probabilities.

VM VM JJ ^ $ N N N ^ Peopl e Jump High $ Trellis diagram 8 POS TAG sequences are possible, given these valid tags for each word taken from dictionary

Bigram Assumption Best tag sequence = T* = argmax P(T W) = argmax P(T)P(W T) (by Baye s Theorem) P(T) = P(t 0 =^ t 1 t 2 t n+1 =.) = P(t 0 )P(t 1 t 0 )P(t 2 t 1 t 0 )P(t 3 t 2 t 1 t 0 ) P(t n t n-1 t n-2 t 0 )P(t n+1 t n t n-1 t 0 ) = P(t 0 )P(t 1 t 0 )P(t 2 t 1 ) P(t n t n-1 )P(t n+1 t n ) N+1 = P(t i t i-1 ) Bigram Assumption i = 0

Lexical Probability Assumption P(W T) = P(w 0 t 0 -t n+1 )P(w 1 w 0 t 0 -t n+1 )P(w 2 w 1 w 0 t 0 -t n+1 ) P(w n w 0 -w n-1 t 0 -t n+1 )P(w n+1 w 0 -w n t 0 -t n+1 ) Assumption: A word is determined completely by its tag. This is inspired by speech recognition = P(w o t o )P(w 1 t 1 ) P(w n+1 t n+1 ) n+1 = P(w i t i ) i = 0 n+1 i = 1 = P(w i t i ) (Lexical Probability Assumption)

Calculation from actual data Corpus ^ Ram got many NLP books. He found them all very interesting. Pos Tagged ^ N V A N N. N V N A R A.

Recording numbers ^ N V A R. ^ 0 2 0 0 0 0 N 0 1 2 1 0 1 V 0 1 0 1 0 0 A 0 1 0 0 1 1 R 0 0 0 1 0 0. 1 0 0 0 0 0

Probabilities ^ N V A R. ^ 0 1 0 0 0 0 N 0 1/5 2/5 1/5 0 1/5 V 0 1/2 0 1/2 0 0 A 0 1/3 0 0 1/3 1/3 R 0 0 0 1 0 0. 1 0 0 0 0 0

Penn tagset (1/2)

Penn tagset (2/2)

Indian Language Tagset: Noun

Indian Language Tagset: Pronoun

Indian Language Tagset: Quantifier

Indian Language Tagset: Demonstrative 3 Demonstrative DM DM Vaha, jo, yaha, 3.1 Deictic DMD DM DMD Vaha, yaha 3.2 Relative DMR DM DMR jo, jis 3.3 Wh-word DMQ DM DMQ kis, kaun Indefinite DMI DM DMI KoI, kis

Indian Language Tagset: Verb, Adjective, Adverb

Indian Language Tagset: Postposition, conjunction

Indian Language Tagset: Particle

Indian Language Tagset: Residuals