... Espa
˜
nola para el Proce-
samiento del Lenguaje Natural, (28):63–80, May.
Bogdan Babych and Anthony Hartley. 2003. Improv-
ing machine translation quality with automatic named
entity recognition. In ... coverage of named entity
extractor systems. In this setting, we assume that
we have available an NE extractor system for Span-
ish, and we want to adapt it so that it can perform...
... has as many valency
frames as it has meanings (t-manual, page 105).
Therefore, the query language has to be able to
distinguish valency frames and search for each one
of them, at least as ... Introduction
Searching in a linguistically annotated treebank is
a principal task in the modern computational lin-
guistics. A search tool helps extract useful infor-
mation from the treeba...
... training data, we can obtain NE candidates
for the rule. By comparing the candidates with the
given answer for the training data, we can classify
them into positive examples and negative exam-
ples ... Os-
aka Toyota) because Japanese POS taggers know
that TO-YO-TA is an organization name (a kind
of proper noun).
*:*:location-name, *:*:org-name
-> ORGANIZATION,0,0
Since Yokohama Honda a...
... in an article to another article in
the same language, and interwiki links which link
695
Figure 2: Candidate NEs for the English and Bulgarian
sentences according to baseline taggers.
from articles ... Smith et al.
(2010) to find parallel-foreign sentences using com-
parable documents linked by inter-wiki links. The
approach uses a small amount of manually annotated
article-pairs to t...
... Bootstrapping Noisy Arabic NER Data
Extracting the syntagmatic features from the
training data yields relatively small number of
instances. Hence the need for additional tagged
data. The new Arabic ... that Barack Obama governs
”, glossed “SrH/declared Ams/yesterday An/that
bArAk/Barack AwbAmA/Obama ytrAs/governs
”, is parsed in Figure 1. According to the phrase
structure parse, the first...
... (Collins and
Singer, 1999) classified NEs through co-training,
(Kozareva et al., 200 5a) used self-training and co-
training to detect and classify named entities in
news domain, (Shen et al., ... Bootstrapping Named Entity Recognition
with Automatically Generated Gazetteer Lists
Zornitsa Kozareva
Dept. de Lenguajes y Sistemas Inform
´
aticos
University of Alicante
Alicante, Spain
zkoz...
... the Arabic daily Al-Hayat. The articles have al-
ready been translated into English by professional
translators.
3
Named entity phrases in these articles
were hand-tagged, extracted, and paired ... or
Anyone as a last name. One way to do this is to
search using wild cards. Since we are not aware of
any search engine that allows wild-card Web search,
we can perform a wild-card search...
... between an ongoing task (a card
game) and a real-time task (a picture game). The
participants randomly had to interrupt the ongo-
ing task to solve a problem in the real-time task.
When studying ... example a math task)
and make the participants engage in the conversa-
tion.
The participants (two female and six male) be-
tween the ages of 25 and 36 drove a car in pairs
while i...
... different parsing models, in
particular data-driven models that can be trained
on syntactically annotated corpora (Yamada and
Matsumoto, 2003; Nivre et al., 2004; McDonald
et al., 200 5a; Attardi, ... based on treebank data
show that the expected running time is in
fact linear for the range of data attested in
the corpora. Evaluation on data from five
languages shows state-of-the-art acc...
...
ery anaphor has exactly one antecendent; (5)
antecedents are terminal nodes; (6) there are
no cyclic link chains; (7) if a link chain ends at
a variable then each anaphor in the chain must ... consistent renaming of bound vari-
ables (a- equality). Instead of variable names,
a A-structure provides a partial function on
tree-nodes for expressing variable binding. An
graphical i...