... Association for Computational Linguistics, pages 16–19,
Avignon, France, April 23 - 27 2012.
c
2012 Association for Computational Linguistics
TransAhead: A Writing Assistant for CAT and CALL
...
view of reducing users’ burden on grammar and
word choice and enhancing their writing quality.
3. The TransAhead System
3.1 Problem Statement
For CAT and CALL, we focu...
... supplied
with the enzyme, and contained Aba, Abb and Abcat
40 nm each, and the start and stop primers Abstart and
Abstop at 600 nm each, and 200 lm each of dATP, dCTP,
dGTP and dTTP. The product ... of the purification, and the require-
ment for HPLC increases the length and complexity of
the purification procedure. Moreover, as with the
studies by Lee et al. [21] and Subr...
... classifier and alignment-based
string similarity for transliteration mining. These
methods model the conditional probability distribu-
tion and require supervised/semi-supervised infor-
mation for learning. ... least for alpha-
betic languages – and efficient. Unlike the pre-
vious unsupervised system, and unlike the super-
vised and semi-supervised systems we mentioned,
our mod...
... functional structure.
For the rule for S, for instance, we add an ele-
ment describing what the SUBJECT and PRED are
for. We could say that the SUBJECT is the
theme
and the PRED is the theme, ... the
word
run,
for instance. We can then start looking
for phrase types and for relations between phrase
types. We can perhaps be reasonably confident
about our basic classifi...
... machine,
and when the inference is distributed on an eight
core machine. Figure 6 plots the mean posterior
and standard error for five independent runs for
each scenario. Both sets of runs performed ... rules
of the form, X → e, f, a, where X is a non-
terminal, e and f are strings of terminals and non-
terminals and a specifies a one-to-one alignment
between non-terminals in e...
... marking up noun
chunks and named entities, as well as additional in-
formation such as part-of-speech tags and merging
these information into markables that are the start-
ing point for the mentions ... classical combination of tagger and chun-
ker, with the Stanford POS tagger (Toutanova et al.,
2003), the YamCha chunker (Kudoh and Mat-
sumoto, 2000) and the Stanford Named Entity...
... Features for Action Classification
For each word pair (w
1
, w
2
) we use the words,
their POS tags and also these features of the chil-
dren of w
1
and w
2
. We also include the lexicon
and POS ... the sentence, the
focus point and the current parent and children for
each word). Note that State changes when a pre-
diction is made and that the features extracted for
the act...
... speech and pen input, includ-
ing both pointing and handwriting (Figure 1). Our
application task also differs, focusing on search
and browsing of a large database of movies-on-
demand and supporting ... modalities and devices. The system provides
users with the flexibility to interact using spoken
commands, handwritten commands, unimodal
pointing (GUI) commands, and multimodal...
... stop-
words (SW) and a function for extracting the stem
of a given word (ST).
Suppose we have a given NLP application for
which we want to evaluate the candidate answer
set Candidates for some input ... stop-words (SW)
and a function for extracting the stem of a given
word (ST) as part of the definition.
As before, suppose we have a given NLP
application for which we want...
... algorithmic transforms, and numerical optimiza-
tion techniques. It will acquire more over time: we in-
tend for it to generalize and encapsulate best practices,
and serve as a testbed for new practices. ... Joshua Goodman, David McAllester, and
Paul Ruhlen for useful early discussions, and pioneer users Markus
Dreyer, David Smith, and Roy Tromble for their feedback and...