... Proceedings of the ACL Student Research Workshop, pages 127–132,
Ann Arbor, Michigan, June 2005.
c
2005 Association for Computational Linguistics
Using bilingual dependencies to align words in
Enlish/French ... Starting with an anchor pair
consisting of two words that are transla-
tions of one another within aligned sen-
tences, the alignment link is propagated to
syntact...
... grammar, in which the subtrees are specified
in advance, in an adaptor grammar the subtrees, as
well as their probabilities, are learnt from the train-
ing data. In order to make parsing and inference
tractable ... properties of the adaptor grammar inference
procedure is that it gives us a way of learning these
interacting linguistic structures simultaneously.
Adaptor grammars are al...
... ap-
proaches use aligned documents as training
data to learn an interlingual representation,
making them sensitive to the domain of the
training data. In this paper, we learn an in-
terlingual representation ... Multilin-
gual topic models for unaligned text. In Uncertainty
in Artificial Intelligence.
Scott Deerwester. 1988. Improving Information Re-
trieval with Latent Semantic In...
... data.
1 Introduction
Good clarification strategies in dialogue systems
help to ensure and maintain mutual understand-
ing and thus play a crucial role in robust conversa-
tional interaction. In dialogue ... real
system interactions, allows us to investigate how
humans clarify. In this study six people played the
role of an intelligent interface to an MP3 player
and were given acc...
... word can align to 0, 1, or 2 words
in the parallel sentence. In other settings, we en-
forced a minimum score in the bilingual dictionary
for a link to be accepted, . This means that
two words cannot ... number of words any word
can be aligned with. Set to: 1, 2, 3.
minscore Used in Competitive Linking algo-
rithm: Minimum score of a word pair in the
dictionary to...
... source domains to find the associa-
tion between words that express similar senti-
ments in different domains. The created the-
saurus is then used to expand feature vectors
to train a binary classifier. ... cross-domain sentiment classification.
In our method, we use the automatically created
thesaurus to expand feature vectors in a binary clas-
sifier at train and test times by...
... try to insert *U* in X
7 try to insert a VP ellipsis site in X
8 try to insert S*T* or SBAR in X
9 try to insert trace of topicalized XP in X
10 try to insert trace of extraposition in X ... nodes in the string, taking a POS-tagged
string as input, and outputting a POS-tagged string
with labeled empty nodes inserted. The PCFG
parser is then trained, using the enha...
... selecting fronted parse trees some-
times leads to false error critiques, it works well
for most cases in our domain.
BRACKETED INPUT STRINGS
In order to coerce our system into accepting
only ...
to have roughly the
same meaning as stative 'permissible' here, and
that led us to coerce an adjectival reading in the
bracketed input. If the unbracketed input had re-...
... grup.nom.ms (masculine singular), grup.nom.fs (fem-
inine singular), grup.nom.mp (masculine plural) etc. This
number and gender information is already encoded in the
POS tags of nouns heading these constituents.
2
The ... improvement over the baseline.
1 Introduction
The research presented in this paper forms
part of an ongoing effort to develop methods
to induce wide-coverage multili...