... PROSPECTS mOR PRACTICAL NATURAL LANGUAGE SYSTEMS
Larry R. Harris
Artificial Intelligence Corporation
Newton Centre, ~ass. 02159
As the author of a " ;practical& quot; NL data ... effort to craft systems actually
worthy of being used. The missing link isn't
a utopian parsing algorithm yet to be
discovered. The hurdles to practical NL
systems are of a much more ... sugg...
... implications.
2 Previous Work in Information
Presentation
2.1 Tailoring to a User Model
Previous work in natural language generation
showed how a multi-attribute decision-theoretic
model of user preferences ... sound-
ing tailored descriptions reported in (Moore et al.,
2004).
4.1 Clustering
The clustering algorithm in our implementation is
based on that reported in (Polifroni et al., 200...
... for Computational Linguistics:shortpapers, pages 317–322,
Portland, Oregon, June 19-24, 2011.
c
2011 Association for Computational Linguistics
ParaSense or How to Use Parallel Corpora for Word ... assump-
tion that incorporating evidence from multiple lan-
guages into the feature vector will be more infor-
mative than a more restricted set of monolingual or
bilingual features. Furthermor...
... pair.
The readability evaluator assigns a score to each
term/sentence pair according to Formula 1
7
.
206.835−1.015×
#words
#sentences
−84.6×
#syllables
#words
(1)
Two points are worth noting here. Firstly, ... therefore cannot cover fresh words or
new usages of existing words. Secondly, their search
1
http://www.engkoo.com.
functions are often limited, making it hard for users
to effective...
... of
word sequences up to length five in a 10
12
word cor-
pus derived from publicly accessible Web pages. As
this corpus is several orders of magnitude larger than
the ones used in previous language ... context made up of the previ-
ous n−1 words. Let abc represent an n-gram where
a is the first word, c is the last word, and b repre-
sents zero or more words in between. One way to
estimate P...
... annotation scheme. Furthermore,
we created 20 factual and opinionated ques-
tions for each language and also the Gold
Standard for their answers in the corpus. The
purpose of our work is to study the ... such
as blogs or forum entries is growing in parallel
with the evolution of the Social Web. This pa-
per presents two corpora of blog posts in Eng-
lish and in Spanish, annotated acc...
... are stored in a trie structure as
shown in Figure 1. N-grams of different orders
are stored in different tables and each row corre-
sponds to a particular w
n
1
, consisting of a word id
for w
n
, ... Delpratt et al.,
2006) for compact representation of the trie.
For an M node ordinal trie, there exist
1
2M +1
2M +1
M
different tries. Therefore,
its information-theoretical lower bound is...
... acquisi-
tion of fixed word order languages such as English,
word order errors are "trifingly few". For example,
English children are never to seen to produce word
order variations other ...
smith for comments and discussion. This work is supported
by an NSF graduate fellowship.
It is worth noting that the developmental compati-
bility condition has been largely ignored in t...
... motivated by planning
theory, but they also allow for an element of
arbitrariness in just which forms are idiomatic to a
language, and just which words and features mark it.
For this
reason,
conventions ... features are more suggestive than
definitive. The presence of a benefactive case (rule
above) may be evidence for an offer or request, or
just happen to appear in an inform o...
... MULTI-MODAL NATURAL LANGUAGE GENERA-
TOR which specifies linguistic and non-linguistic real-
izations for the dialogue acts in the dialogue plan.
•
A SPEECH SYNTHESIS MODULE, which adds infor-
mation for ... temporal coordination of gestures and speech.
•
A PLAYER, which plays the animated characters and
the corresponding speech sound files.
Each step in the pipeline adds more concrete in...