... Feasibility Study for Ellipsis Resolution in Dialogues
by Machine-Learning Technique
YAMAMOTO Kazuhide and SUMITA Eiichiro
ATR Interpreting Telecommunications Research ... decision-tree learning research to itself.
3.3 Training Attributes
The training attributes that we prepared for
Japanese ellipsis resolution are listed in Table
2. The training attributes in...
...
process, therefore, requires a finer grain substation method than
simply inserting the highest level non-terminals in the in the
ellipsed input in place of the matching non-terminals in the parse ...
listed in the preceding section was underscored by an empirical
study we conducted to ascertain the most pressing needs of
natural language interfaces in interactive apl~lica...
... with the baselines, we do not rely
on additional labeled data for learning the ranker;
instead, we use half of the training texts for training
classifiers and the other half for ranking purposes.
Results ... encouragingly, gains in F-
measure are accompanied by simultaneous increase
in recall and precision for all three data sets.
Feature contribution. In an attempt to gain add...
... correct
parts in it.
In this paper we therefore propose a method for
correcting errors, which is characterized by learning the
trend of errors and expressions, and by processing in an
arbitrary ... the string including errors from the String-
Database (the former string is referred to as the
Similar-String, and the latter as the Error-String).
Finally, the correction is mad...
...
constructing a probabilistic dictionary (Table 3)
for use in aligning words in machine translation
(Brown et al., 1990), or for constructing a
bilingual concordance (Table 4) for use in
lexicography ...
French
According to our survey, 1988 sales of mineral
water and soft drinks were much higher than in
1987, reflecting the growing popularity of these
products. Cola drin...
...
those within the same family (say Indo-European).
Our bracketing method is based on a new formalism
called an inversion.invariant transduction grammar.
By
their nature inversion-invariant ...
Before turning to bracketing, we take note of three
lemmas for IITGs (proofs omitted):
Lemma l For any inversion-invariant transduction
grammar G, there exists an equivalent inversion-
inv...
... underlying
mechanisms behind these observations were not
defined. The aim of this study was therefore to provide
insights into this issue by determining the fate of SG-
dependent proteases in cells ... differenti-
ation in interleukin (IL)-3-containing medium were analyzed for total
intracellular b-hexosaminidase activity. Results are expressed as
percentages, where the b-hexosaminid...
... incorporated to a P
o
constructing a
compound preposition. In this way
tagging prepositions and parsing texts in
Natural Language Processing is defined
in a proper manner.
1 Introduction
Prepositions ... helpful in stemming
for information retrieval (IR), since knowing a
word’s POS can help tell us which
morphological affixes it can take. It can also help
an IR applicat...
... containing
the article by consulting the threading server. The
advantage of using XML is that it will be supported
by various tools, including Web browsers. Now we
are prototyping the threading ... standard for exchange of in-
formation on the Web. XML-based threads can be
used by webcasting or push services, since various
tools for parsing and visualizing threads are avail-...
... Computational Linguistics, vol.11, nos.1 and 2, March and June 1968]
Computer Backup for Field Work in Phonology
by Joseph E. Grimes, John R. Alsop, and Alan Wares, Summer Institute of Linguistics
In ... segments. Junctures were put
into the stream of speech by some linguists, and intona-
tional change points were added; but the characteristic
groupings of sounds in syllable...