|
<term>
conversation
</term>
for documentation .
|
The
|
question is , however , how an interesting
|
#36
Given the development of storage media and networks one could just record and store a conversation for documentation. The question is, however, how an interesting information piece would be found in a large database. |
|
Language System at Lincoln Laboratory )
</term>
.
|
The
|
<term>
CCLINC Korean-to-English translation
|
#411
At MIT Lincoln Laboratory, we have been developing a Korean-to-English machine translation system CCLINC (Common Coalition Language System at Lincoln Laboratory). The CCLINC Korean-to-English translation system consists of two core modules, language understanding and generation modules mediated by a language neutral meaning representation called a semantic frame. |
|
</term>
called a
<term>
semantic frame
</term>
.
|
The
|
key features of the
<term>
system
</term>
include
|
#439
The CCLINC Korean-to-English translation system consists of two core modules, language understanding and generation modules mediated by a language neutral meaning representation called a semantic frame. The key features of the system include: (i) Robust efficient parsing of Korean (a verb final language with overt case markers, relatively free word order, and frequent omissions of arguments). |
|
understanding of the
<term>
original document
</term>
.
|
The
|
purpose of this research is to test the
|
#544
Having been trained on Korean newspaper articles on missiles and chemical biological warfare, the system produces the translation output sufficient for content understanding of the original document. The purpose of this research is to test the efficacy of applying automated evaluation techniques, originally devised for the evaluation of human language learners, to the output of machine translation (MT) systems. |
|
<term>
machine translation outputs
</term>
.
|
The
|
subjects were given three minutes per extract
|
#712
Some of the extracts were expert human translations, others were machine translation outputs. The subjects were given three minutes per extract to determine whether they believed the sample output to be an expert human translation or a machine translation. |
|
</term>
at which they made this decision .
|
The
|
results of this experiment , along with
|
#755
Additionally, they were asked to mark the word at which they made this decision. The results of this experiment, along with a preliminary analysis of the factors involved in the decision making process will be presented here. |
|
place a supply or information request .
|
The
|
request is passed to a
<term>
mobile , intelligent
|
#847
Using LCS-Marine, tactical personnel can converse with their logistics system to place a supply or information request. The request is passed to a mobile, intelligent agent for execution at the appropriate database. |
|
sophisticated at responding to the
<term>
user
</term>
.
|
The
|
issue of
<term>
system response
</term>
to
<term>
|
#968
However, the improved speech recognition has brought to light a new problem: as dialog systems understand more of what the user tells them, they need to be more sophisticated at responding to the user. The issue of system response to users has been extensively studied by the natural language generation community, though rarely in the context of dialog systems. |
|
performance
</term>
of an
<term>
oracle
</term>
.
|
The
|
<term>
oracle
</term>
knows the
<term>
reference
|
#1070
We find that simple interpolation methods, like log-linear and linear interpolation, improve the performance but fall short of the performance of an oracle. The oracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where each word string has been obtained by using a different LM. |
|
network
</term>
or a
<term>
decision tree
</term>
.
|
The
|
method amounts to tagging
<term>
LMs
</term>
|
#1172
We suggest a method that mimics the behavior of the oracle using a neural network or a decision tree. The method amounts to tagging LMs with confidence measures and picking the best hypothesis corresponding to the LM with the best confidence. |
|
</term>
of
<term>
spoken dialogue systems
</term>
.
|
The
|
three tiers measure
<term>
user satisfaction
|
#1207
We describe a three-tiered approach for evaluation of spoken dialogue systems. The three tiers measure user satisfaction, system support of mission success and component performance. |
|
Thai-English language identification
</term>
.
|
The
|
paper also proposes
<term>
rule-reduction
|
#1262
This paper proposes a practical approach employing n-gram models and error-correction rules for Thai key prediction and Thai-English language identification. The paper also proposes rule-reduction algorithm applying mutual information to reduce the error-correction rules. |
|
selects the top-ranked
<term>
plan
</term>
.
|
The
|
<term>
SPR
</term>
uses
<term>
ranking rules
</term>
|
#1422
Second, the sentence-plan-ranker (SPR) ranks the list of output sentence plans, and then selects the top-ranked plan. The SPR uses ranking rules automatically learned from training data. |
|
evidence that our findings are scalable .
|
The
|
theoretical study of the
<term>
range concatenation
|
#1597
We also provide evidence that our findings are scalable. The theoretical study of the range concatenation grammar [RCG] formalism has revealed many attractive properties which may be used in NLP. |
|
practical efficiency of
<term>
RCL parsers
</term>
.
|
The
|
<term>
non-deterministic parsing choices
</term>
|
#1700
In this paper, we study a parsing technique whose purpose is to improve the practical efficiency of RCL parsers. The non-deterministic parsing choices of the main parser for a language L are directed by a guide which uses the shared derivation forest output by a prior RCL parser for a suitable superset of L. |
other,32-5-P01-1007,bq |
</term>
for a suitable
<term>
superset of L.
|
The
|
results of a practical
</term><term>
evaluation
|
#1735
The non-deterministic parsing choices of the main parser for a language L are directed by a guide which uses the shared derivation forest output by a prior RCL parser for a suitable superset of L. The results of a practical evaluation of this method on a wide coverage English grammar are given. |
|
</term>
's
<term>
operational semantics
</term>
.
|
The
|
value of this approach is that as the
<term>
|
#1903
I show that the performance of a search engine can be improved dramatically by incorporating an approximation of the formal analysis that is compatible with the search engine's operational semantics. The value of this approach is that as the operational semantics of natural language applications improve, even larger improvements are possible. |
|
transcription
</term>
of
<term>
training data
</term>
.
|
The
|
method combines
<term>
domain independent
|
#2223
This paper describes a method for utterance classification that does not require manual transcription of training data. The method combines domain independent acoustic models with off-the-shelf classifiers to give utterance classification performance that is surprisingly close to what can be achieved using conventional word-trigram recognition requiring manual transcription. |
|
to a
<term>
phone-string classifier
</term>
.
|
The
|
<term>
classification accuracy
</term>
of the
|
#2290
In our method, unsupervised training is first used to train a phone n-gram model for a particular domain; the output of recognition with this model is then passed to a phone-string classifier. The classification accuracy of the method is evaluated on three different spoken language system domains. |
|
answers
</term>
in multiple
<term>
corpora
</term>
.
|
The
|
<term>
answering agents
</term>
adopt fundamentally
|
#2352
Motivated by the success of ensemble methods in machine learning and other areas of natural language processing, we developed a multi-strategy and multi-source approach to question answering which is based on combining the results from different answering agents searching for answers in multiple corpora. The answering agents adopt fundamentally different strategies, one utilizing primarily knowledge-based mechanisms and the other adopting statistical techniques. |