Urdu Linguistics and Computing

Pages

Home
Alphabets
Diacritics
Digits
Special Chars & Symbols
Project Urdu Corpus

Showing posts with label n-gram. Show all posts

Friday, May 6, 2016

A Hybrid Approach for NER System for Scarce Resourced Language-URDU: Integrating n-gram with Rules and Gazetteers

http://publications.muet.edu.pk/research_papers/pdf/pdf1145.pdf

Posted by Syed Muhammad Humayun at 11:22 AM No comments:

Email This BlogThis!Share to X Share to Facebook Share to Pinterest

Labels: bi-gram, gazetteer, n-gram, named entity recognition ner, natural language tool kit, paper, paper 2015, python, uni-gram

A Language Independent Approach To Develop Urdu Stemmer

http://www.academia.edu/9756536/A_LANGUAGE_INDEPENDENT_APPROACH_TO_DEVELOP_URDU_STEMMER

Posted by Syed Muhammad Humayun at 10:24 AM No comments:

Email This BlogThis!Share to X Share to Facebook Share to Pinterest

Labels: equivalence class, frequency based stripping, length based stripping, n-gram, paper, paper 2013, stemmer, unsupervised

Thursday, April 21, 2016

CLE Urdu Books N-grams

http://www.cle.org.pk/Publication/papers/2014/CLE%20Urdu%20Books%20N-grams.pdf

Posted by Syed Muhammad Humayun at 11:40 AM No comments:

Email This BlogThis!Share to X Share to Facebook Share to Pinterest

Labels: classification, corpus, corpus cleaning, n-gram, paper, paper 2014

Older Posts Home

Subscribe to: Posts (Atom)

Labels

add character lists acl (1)
affix elimination stemming (1)
affix list (2)
auto text summarization (1)
benchmark (1)
bi-gram (1)
case marker (1)
character normalization (1)
classification (1)
clir (1)
clustering (1)
collation (1)
connected component analysis (1)
consonants (1)
corpus (2)
corpus cleaning (1)
diacritic elimination (2)
entity finding (1)
equivalence class (1)
euclidean distance (1)
exception list (1)
feature extraction (1)
frequency based stop words (1)
frequency based stripping (1)
functional morphology fm (1)
gazetteer (1)
harf (1)
heuristics (1)
hmm tagger (1)
indexing (2)
infix stemming (1)
inverted index (1)
lemmas (1)
length based stripping (1)
levenshtein distance (1)
lexicon (1)
lexicon extraction (1)
lexicon format (1)
lexicon lookup word segmentation (1)
ligature (1)
longest suffix stripping algorithm (1)
manual affix list (2)
manual lexicon creation (1)
mean average precision map (1)
morphology (5)
n-gram (3)
named entity recognition ner (1)
natural language tool kit (1)
normalization (2)
open source (1)
opinion (1)
optical character recognition ocr (1)
orthography (2)
over stemming (1)
paper (14)
paper 2007 (1)
paper 2009 (3)
paper 2010 (1)
paper 2011 (1)
paper 2012 (1)
paper 2013 (1)
paper 2014 (1)
paper 2015 (3)
paper 2016 (3)
part of speech (4)
partial word (1)
phonemic transcription (1)
pl2 weighting model (1)
polarity (1)
pos tagger (1)
postfix stemming (1)
prefix stemming (1)
python (1)
retrieval (2)
rf tagger (1)
roman urdu (1)
roman urdu conversion (1)
rules based stemmer (3)
salience (1)
segmentation (1)
sentiments (1)
soundex (1)
space insertion (1)
spell checking (1)
stanford pos tagger (1)
statistical stemmer (1)
stem words dictionary (1)
stemmer (5)
stemming exception words (1)
stemming rules (1)
stop words (4)
svm tagger (1)
terrier (1)
tokenization (1)
tools (2)
translation (1)
transliteration (2)
tree tagger (1)
trigram-and-tag tnt (1)
under stemming (1)
uni-gram (1)
unicode variation (1)
unsupervised (1)
urdu grammar (1)
urdu infix classes (1)
utf-16 encoding (1)
vowels (1)
web page content extractor (1)
word forms (1)
word spotting (1)

Followers

About Me

Syed Muhammad Humayun

View my complete profile

Total Pageviews

Search This Blog

Researchers Resources

ACM Digital Library ($)
Google Scholar (Free)
Research Gate (Free)

Research Areas

Ambiguity resolution
Anaphora Resolution
Character Recognition
Corpus Linguistics
Discourse Analysis
Ellipses Resolution
Fonts
Information Retrieval
Localization
Machine Translation
Morphology
OCR
Part-of-Speech Tagging
Pattern Recognition
Phonology
Semantics
Speech Recognition
Syntax
Text to speech

Blog Archive

▼ 2016 (16)
- ▼ May (12)
- ► April (4)

Watermark theme. Powered by Blogger.