#108This paper addresses the problem of the automatic detection of those activities in meeting situation and everyday rejoinders.
infrastructure
</term>
for this purpose . In this
paper
we show how two standard outputs from
<term>
#276In this paper we show how two standard outputs from information extraction (IE) systems - named entity annotations and scenario templates - can be used to enhance access to text collections via a standard text browser.
machine learning techniques
</term>
. In this
paper
, we address the problem of combining several
#1029In this paper, we address the problem of combining several language models (LMs).
conducted with the U.S. military . This
paper
proposes a practical approach employing
#1242This paper proposes a practical approach employing n-gram models and error-correction rules for Thai key prediction and Thai-English language identification.
Thai-English language identification
</term>
. The
paper
also proposes
<term>
rule-reduction algorithm
#1263The paper also proposes rule-reduction algorithm applying mutual information to reduce the error-correction rules.
one or more
<term>
sentences
</term>
. In this
paper
, we present
<term>
SPoT
</term>
, a
<term>
sentence
#1337In this paper, we present SPoT, a sentence planner, and a new methodology for automatically training SPoT on the basis of feedback provided by human judges.
human-ranked sentence plan
</term>
. In this
paper
, we compare the relative effects of
<term>
#1463In this paper, we compare the relative effects of segment order, segmentation and segment contiguity on the retrieval performance of a translation memory system.
parsed in O ( n6 )
<term>
time
</term>
. In this
paper
, we study a
<term>
parsing technique
</term>
#1681In this paper, we study a parsing technique whose purpose is to improve the practical efficiency of RCL parsers.
<term>
syntactic paraphrases
</term>
. This
paper
presents a formal analysis for a large
#1817This paper presents a formal analysis for a large class of words called alternative markers, which includes other (than), such (as), and besides.
or rule-based approaches
</term>
. In this
paper
We experimentally evaluate a
<term>
trainable
#2053In this paper We experimentally evaluate a trainable sentence planner for a spoken dialogue system by eliciting subjective human judgments.
relationships among the target variables . This
paper
describes a method for
<term>
utterance classification
#2207This paper describes a method for utterance classification that does not require manual transcription of training data.
average precision metric
</term>
. In this
paper
we present
<term>
ONTOSCORE
</term>
, a system
#2438In this paper we present ONTOSCORE, a system for scoring sets of concepts on the basis of an ontology.
the performance of our systems . In this
paper
, we introduce a
<term>
generative probabilistic
#2670In this paper, we introduce a generative probabilistic optical character recognition (OCR) model that describes an end-to-end process in the noisy channel framework, progressing from generation of true text through its transformation into the noisy output of an OCR system.
conversational speech
</term>
are limited . In this
paper
, we show how
<term>
training data
</term>
#3031In this paper, we show how training data can be supplemented with text from the web filtered to match the style and/or topic of the target recognition task, but also that it is possible to get bigger performance gains from the data by using class-dependent interpolation of N-grams.
</term>
for some
<term>
NE types
</term>
. In this
paper
, we describe a
<term>
phrase-based unigram
#3392In this paper, we describe a phrase-based unigram model for statistical machine translation that uses a much simpler set of model parameters than similar phrase-based models.
</term>
and
<term>
phrase length
</term>
. In this
paper
, we propose a novel
<term>
Cooperative Model
#3480In this paper, we propose a novel Cooperative Model for natural language understanding in a dialogue system.
question answering session
</term>
. In this
paper
we present a novel , customizable
<term>
#3714In this paper we present a novel, customizable IE paradigm that takes advantage of predicate-argument structures.
high quality
<term>
IE results
</term>
. This
paper
proposes the
<term>
Hierarchical Directed
#3791This paper proposes the Hierarchical Directed Acyclic Graph (HDAG) Kernel for structured natural language data.
<term>
new event detection
</term>
. In this
paper
we formulate
<term>
story link detection
</term>
#4066In this paper we formulate story link detection and new event detection as information retrieval task and hypothesize on the impact of precision and recall on both systems.
Experimental results validate our hypothesis . This
paper
concerns the
<term>
discourse understanding
#4128This paper concerns the discourse understanding process in spoken dialogue systems.