... Train-
ing with HaG only obtained similar results with 1-
best trained LGFN, which demonstrated that spu-
rious ambiguity highly affected the nbest list here,
resulting in a less accurate training. ... spu-
rious ambiguity for those alignments. We do an em-
pirical study of the in uence of spurious ambiguity
on parsing and discriminative learning by compar-
ing different gram...
... all distinguishable
entities.
2.2 Refining the notion of dis-
tinguishing description
Using the definition of distinguishing
description based on inclusion given above,
we are going to show ... points in a rather
simple and efficient manner.
In §2, we present our definitions of
distinguishing descriptions and
distinguishable entities and we use them to
deal with incomplete dis...
...
grouping of sentences containing coordinate
conjunctions. Finally, the algorithm is described
in Section 3.
I GAPPING, RIGHT NODE RAISING AND
REDUCED CONJUNCTION
I.I Gapping
Gapping is ... DEALING WITH CONJUNCTIONS
IN A MACHINE TRANSLATION ENVIRONMENT
Xiumlng HUANG
Institute of Linguistics
Chinese Academy of Social Sciences
BeiJing, China*
ABSTRACT
The paper ... an English-C...
... obligatory in this case. But in (2) it
is obligatory. Unfortunately the
distinctive complement with yon is not
obligatory, thus the distinction of these
two meanings requires also to take into ...
this distinction is very useful mainly
with respect to machine translation, as we
can see translating the different meanings
of the examples.
PRACTICAL CONCLUSIONS
As we have seen...
... define word specific rules. Such
rules can be invoked in many ways. For example, we
can associate a word selection rule for an ordinary
verb in a dictionary entry for a noun, as shown in
Fig. ...
problem in machine transla-
tion. There are varieties
of choices of translation
for a word in the source
language. Main principles
adopted in our system are,
(i) Area res...
... DEALING WITH CONJUNCTIONS
IN A MACHINE TRANSLATION ENVIRONMENT
Xiuming Huang
Institute of Linguistics
chinese Academy of Social Sciences
Beijing, China*
ABSTRACT
A set ... coordinator will
be called RIGHT-PHRASE.
VI CSDC RULES
Constraints for determining the grammatical-
ness of constructions involving coordinating con-
junctions have been suggested by linguists, ... coordinate...
... using an update interface on IUs. The appli-
cations in Figures 2 and 4 make use of this interface
to mark the words of the utterance in bold for com-
pleted, and in italic for ongoing words (incidentally,
the ... stream verbalising this
full utterance. At best, timing information is returned
as well so that a control component can determine in
case of an interruption / barge -in by...
... need only determine the first pre-
parenthesis word aligned with an in- parenthesis
word, whereas word alignment requires the respec-
tive linking of all such (pre ,in) -parenthesis word
pairs. However, ... generalize across instances
involving different in- parenthesis terms. Our algo-
rithm extends Competitive Linking to deal with
multi -word alignments and takes advantage...
... becomes
smaller with more training data, implying
the above limit also holds for large training
conditions.
1 Introduction
Word alignment is a central problem in statistical
machine translation ... alignment. Solid lines indicate regular word
correspondences while dashed lines indicate spe-
cial links. Tags inside [] indicate additional infor-
mation about the function of the wo...
...
GRAMMARS
1.1 Lexicalizing Phrase Structure rules
In most current linguistic theories the
information put in the lexicon has been increased
in both amount and complexity. Viewing
constituent structures ... is
systematically associated with one (or more)
lexical item serving as 'head'. These structures are
combined with one another with one or more
combining operat...