TALC-sef A Manually-Revised POS-TAgged Literary Corpus in Serbian, English and French.

Antonio Balvet Dejan Stosic Aleksandra Miletic

Published in: LREC (2014)

Keyphrases

mono lingual
linguistic features
cross lingual
part of speech
training corpus
unknown words
pos tagging
event extraction
hand crafted
link grammar
person names
statistical machine translation
open domain
machine translation

multiword
parallel corpus
penn treebank
broad coverage
qa clef
question answering
target language
english language
foreign language
word sense
wide coverage
parse tree
english words
manually constructed

natural language processing
semantic features
source language
machine translation system
translation model
semantic roles
wordnet
cross language information retrieval
parallel corpora
named entities
text classification
word sense disambiguation
cross language
sentence level

semi automatically
labor intensive
text analysis
language learning
n gram
english text
syntactic information
comparable corpora
query translation
information retrieval
pos taggers
noun phrases
language model