... Manuals in a Monte-Carlo Framework
S.R.K. Branavan David Silver * Regina Barzilay
Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology
{branavan, regina}@csail.mit.edu
* ... Regina Barzilay.
2010. Reading between the lines: Learning to map
high-level instructions to commands. In Proceedings
of ACL, pages 1268–1277.
S.R.K. Branavan, David...
... formalized
as minimizing the fraction of swapped pairs over all
rankings. This model is well suited to the features
that are available in clinical text. The assumption
that all MEs in a clinical narrative ... clinical narratives, our
objective is to induce a partial temporal ordering of
all medical events in each clinical narrative based on
their proximity to a reference dat...
... intractable to
find such a parameter vector, and thus slack vari-
ables are introduced that allow for training errors.
A parameter to the algorithm controls the trade-off
between ranking margin ... paraphrase in generation.
1113
criminative reranking to the task of adapting a lan-
guage generator to the strengths and weaknesses
of a particular synthetic voice. Our method in-...
... pareto vs. non-pareto
points ignores the fact that 2nd-place non-pareto
points may also lead to good practical solutions. A
better approach may be to adopt a graded definition
of Pareto optimality ... Association for Computational Linguistics
Learning to Translate with Multiple Objectives
Kevin Duh
∗
Katsuhito Sudoh Xianchao Wu Hajime Tsukada Masaaki Nagata
NTT Communication Science...
... requiring minimal human
intervention to prepare the training data.
3 Method
To find translations for a given term on the Web, a
promising approach is automatically learning to
extract phrasal ... and 24,000 bilingual
place names were obtained and forced aligned to
obtain transliteration relationships.
3.1.4 Generating distance feature. In the final
stage of preparing tra...
... imperative and spatial lan-
guage is heavily dependent on the physical set-
ting it is situated in, motivating automated learn-
ing approaches to acquiring meaning. Tradi-
tional accounts of learning ... direc-
tion language.
We also compare against the policy gradient
learning algorithm of Branavan et al. (2009). They
parametrize a probabilistic policy Pr(s |a; θ) as a
log-linear mode...
... ser-
vices that used to be performed by humans have
been automated by natural language dialogue sys-
tems, including information seeking functions, as
in timetable or banking applications, but also more
complex ... a train-
ing system; creating an MDP from these data and
the rewards assigned by the training users; off-line
policy learning based on this MDP.
The Q-function for a...
... alphanumeric character or a special character, and ci,j is a space character
ci,,j is a space character, and ci,j is an alphanumeric character or a special character
kin
Table 3: Feature values ...
cij is a space character and
ei,jq_ 1
is a space character; or ci,j is a special character
and ci,j+l is a special character
cij is an alphanumeric character or a special...
... Liang Huang, Kevin Knight, and Aravind Joshi. 2006.
Statistical syntax-directed translation with extended
domain of locality. In Proc. AMTA 2006, pages
65–73.
Alon Lavie, Alok Parlikar, and Vamshi ... 661–668.
Slav Petrov, Leon Barrett, Romain Thibaux, and Dan
Klein. 2006. Learning accurate, compact, and in-
terpretable tree annotation. In Proc. COLING-ACL
2006, pages 433–440.
Arjen Pou...