... particularly useful for
classroom management, but is also helpful in pacing and for assisting students who may
have questions or need help. In language classrooms where some translation is performed,
maintaining ... possible, to make a concerted effort to use
the target language in the classroom that in turn provides students with a role model who
has successfully learned the target language.
It is best to avoid ... translation, while the NSA is largely responsible for most of the target
language 'talking' in the class. In other situations, these NSAs perform as 'live tape-
recorders', undermining...
... Association for Computational Linguistics, pages 430–439,
Jeju, Republic of Korea, 8-14 July 2012.
c
2012 Association for Computational Linguistics
Fast Online Lexicon Learning for Grounded Language ... representa-
tion grammar (MRG) for their formal semantic lan-
guage. By using a MRG that correlates better to the
structure of natural language, we further improve the
performance on the navigation ... the
Stanford Chinese Word Segmenter (Chang et al.,
2008). We evaluated using the same three tasks as
before. This resulted in a precision, recall, and F1
of 87.07, 71.67, and 78.61, respectively for...
... improve performance on the
statistical spoken language understanding
(SLU) problem. The statistical natural
language parsers trained on text perform
unreliably to encode non-local informa-
tion ... selec-
tion algorithm is very efficient for both perfor-
mance and time complexity.
2 Spoken Language Understanding as a
Sequential Labeling Problem
2.1 Spoken Language Understanding
The goal of SLU ... exploit non-local information in the next
section.
3 Incorporating Non-local Information
3.1 Using Trigger Features
To exploit non-local information to sequential la-
beling for a statistical SLU,...
... June 2005.
c
2005 Association for Computational Linguistics
A Phonotactic Language Model for Spoken Language Identification
Haizhou Li and Bin Ma
Institute for Infocomm Research
Singapore ...
the 1996 NIST Language Recognition
Evaluation database.
1 Introduction
Spoken language and written language are similar
in many ways. Therefore, much of the research in
spoken language identification, ... Y. Chen of Institute for Info-
comm Research for insightful discussions.
References
Jerome R. Bellegarda. 2000. Exploiting latent semantic
information in statistical language modeling
, In...
... system, we currently use exact solution
for input size of 7 propositions or less and switch to
greedy for any larger input size to ensure sub-second
performance for the NLG component.
0
20
40
60
80
100
120
140
160
180
200
24689101214161820
# ... solution for input
Q and Q ⊂ P . To facilitate dynamic program-
ming, we remember the best solution for Q de-
rived by sbd(Q) in case Q is used to formulate
other solutions.
7. If the lower bound for ... 565–572,
Ann Arbor, June 2005.
c
2005 Association for Computational Linguistics
Instance-based Sentence Boundary Determination by Optimization for
Natural Language Generation
Shimei Pan and James C....
... allows us to enforce a
very coarse form of parse preferences (for exam-
ple, prefering complete sentences to sentence frag-
ments). These coarse preferences could also be
enforced by the parse ... Language& quot;, Cog-
nition, Vol. 2, No. 1, pp. 15-47.
MADCOW (1992). "Multi-site Data Collection for
a Spoken Language Corpus", in Proceedings
of the DARPA Speech and Natural Language ... can enforce both heuristics without conflict
and enforce the desired preferences for examples
like (2a) and (2b). He argues that Minimal At-
tachment and Right Association can be enforced...
... Domain
A class is defined for each constant of PAL. A class object
for a lexical item contains linguistic knowledge in a procedural
form. In other words, a class contains information as to how a ... to share methods for these cases. Any exceptional
method can be attached to lower level items.
For example, we can define a class "action verb" which has
methods for instrumental ... be the system and therefore the better
perspective we can obtain for writing a large grammar.
a.1 A Simple
Example
Let's start by seeing how our simple example for a sentence
"he...
... exists for physician
SPECIALTIES, we can nonetheless give a rule for this
predicate in way that is uniform with the rule given for
the predicate PATIENTS.
2This term, while a standard one in formal ...
X:S')
where
S' := (CONJ S P)
(4)
(forol l
X:S (-> (and (P X)
<rest>)
(FORMULA X))
=>
(forall X:S' (-> (end <rest>)
(FORMULA
X)))
In (2) and (4) above, the ... Simplification Transformation for
Natural Language Question-Answering Systems
David G. Stallard
BBN Laboratories Inc.
I0 Moulton St.
Cambridge, MA.
02238
Abstract
A new method is presented for simplifying...
... WordNet
for the Russian language does not exist yet. An-
other way to calculate semantic relatedness is us-
ing Wikipedia (Mihalcea, 2007; Turdakov and Ve-
likhov, 2008), but it takes much effort. ... dif-
ferent types of figurative language (metaphors,
metonymies etc.). However, there are some works
aimed at extracting particular types of figura-
tive language. For example, Nissim and Mark-
ert ... appear in a language
to remedy the gap in vocabulary (Black, 1954).
These metaphors do not indicate an author’s writ-
ing style: an author uses such metaphor for an ob-
ject because the language...
... number.
• For verbs, generated forms had to match the
original form for tense and negation.
• For adjectives, generated forms had to match
the original form for degree of comparison and
negation.
• For ... The forms pro-
duced by the tool from the lemma of an observed in-
flected word form were subjected to several restric-
tions:
• For nouns, generated forms had to match the
original form for number.
• ... generated forms had to match
the original form for number, case, and gender.
• Non-standard inflection forms for all POS were
excluded.
The following criteria were used to select rules for
which...
... application to Natural Language
Database Interfacing.
Ph.D. Thesis, Royal Institute
of Technology, Stockholm, Sweden.
316
Semantic Information Preprocessing
for Natural Language Interfaces ...
predicates). Output is a logical formula, consist-
ing of predicates meaningful to the database engine
(database predicates). AET provides a formalism
for describing how a formula consisting of lexical ... LDT was introduced for a sys-
tem, where input is a logical formula, whose predi-
cates approximately correspond to the content words
of the input utterance in natural language (lexical
predicates)....
... of the ST kernel for a natural language task.
In (Kazama and Torisawa, 2005), an interesting
algorithm that speeds up the average running time
is presented. Such algorithm looks for node pairs
that ... on
Lexicalized Tree Adjoining Grammar (LTAG) for
the parse-reranking task was proposed. Since
QTK was used for the kernel computation, the
high learning complexity forced the authors to
train different ... make a step back before Gildea and Juraf-
sky defined the first set of features for Semantic
Role Labeling (SRL). The idea that syntax may
have been useful to derive semantic information
was already...
... 202–210,
Athens, Greece, 30 March – 3 April 2009.
c
2009 Association for Computational Linguistics
Re-Ranking Models For Spoken Language Understanding
Marco Dinarelli
University of Trento
Italy
dinarelli@disi.unitn.it
Alessandro ... Systems, the Language Under-
standing module performs the task of translating
a spoken sentence into its meaning representation
based on semantic constituents. These are the
units for meaning ... probability evaluated by the Conceptual
Language Model, described in the next section.
2.1 Stochastic Conceptual Language Model
(SCLM)
An SCLM is an n-gram language model built on
semantic tags....