... Natural Language for Expert Systems:
Comparisons with Database Systems
Kathleen R. McKeown
Department of Computer Science
Columbia University
New York, N.Y. 10027
1
Introduction
Do natural language ... the database
system.
We are currently working on natural language
for expert systems at Columbia and thus, expert
systems provide a natural alternative envir...
... are very restricted in
terms of the language used for the interaction with
machines. The problem with unrestricted natural
language for cor-unicacion with machines is chaC no
automatic way ... producing
natural-sounding speech for large vocabularies with
unrestricted gr w tical structures and for recog-
nizing spoken speech for large vocabularies with
unlimited...
... communicating with
other h~rmans using natural language, it is not clear
that we want to recreate these problems in dealing with
the computer. While there is some evidence that natur-
al language ... a group of users would end
up with would be very far from a natural language.
The argument is sometimes made that a natural language
interface might be useful for those who a...
... 94025
I INTRODUCTION
Although there have been many experimental
systems for
natural -language
access to databases,
with some now going into actual use, many problems
in this area remain to ...
their own choosing.
II QUANTITY QUESTIONS
Database query languages typically provide
some means for counting and totaling that must be
invoked for answering "how much" or...
... distributions. Therefore,
we also experimented with force aligning the gener-
ated corpus with the word alignment models trained
baseline corpus before building the phrase table.
6 Experiments
We performed ... sen-
tences have more slots for substitution. Therefore,
they have more occurrences in the generated corpus.
We used the NIST MT06 test set for tuning, and
experimented with 5...
... combined with target
language information in order to choose the best
translation, thus improving translation quality.
We position the problem of generating alterna-
tive texts for translation within ... language information as
well. This pruning reduces the load of the SMT
system, and allows for potential improvements in
translation quality by considering both source- and
target -l...
... for each con-
text, α ≥ 0, β ≥ 0, and α + β = 1, and that
for every D
n,C
n
(w
1
w
n
)
parameter, 0 ≤ D ≤
C
n
(w
1
. w
n
). For each context, whatever values
we choose for these parameters within ... schema, C
n
denotes the counting method
used for N-grams of length n. For most smoothing
methods, C
n
denotes actual training corpus counts
for all n. For KN smoothing and its va...
... word alignment for languages with
scarce resources using bilingual corpora
of other language pairs. To perform word
alignment between languages L1 and L2,
we introduce a third language L3. ...
word alignment for languages with scarce re-
sources using bilingual corpora of other language
pairs. To perform word alignment between lan-
guages L1 and L2, we introduce a third l...
... problems about human perform- 4.
ante with natural language usage on computers. Codd [5]
and Woods [8] describe informal studies in user perform- I)
ante with their natural language systems. Small ... rigorous comparison of
natural language with a database query language. Twenty
subjects worked with a subset of SEQUEL and an on-llne 2)
simulated natural language syste...
... affect lexicons for some color-emotion
associations. For instance, anger has a strong as-
sociation with red and brown, anticipation with
green, fear with black, joy with pink, sadness
with black, ... pink with joy, dark brown with trust vs.
India-based annotators who associate yellow with
joy and blue with trust.
4.3 Color-Concept Associations
In total, workers annotate...