Báo cáo khoa học: "Corpus-based Discourse Understanding in Spoken Dialogue Systems" pot
Báo cáo khoa học: "Stochastic Discourse Modeling in Spoken Dialogue Systems Using Semantic Dependency Graphs" pdf
... for semantic understanding
in the spoken dialogue systems. Five main catego-
ries about medical application, clinic information,
Dr.’s information, confirmation for the clinic in-
formation, ... Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions, pages 937–944,
Sydney, July 2006.
c
2006 Association for Computational Linguistics
Stochastic Discourse Modeling in...
Báo cáo khoa học: "Corpus-based Discourse Understanding in Spoken Dialogue Systems" pot
... single
understanding result after each user ut-
terance. By holding multiple candidates
for understanding results and resolving the
ambiguity as the dialogue progresses, the
discourse understanding ... deals with the discourse understand-
ing component. Since we are resolving the ambi-
guity of speech understanding from the discourse
point of view and not within the speech und...
Báo cáo khoa học: "Optimising Information Presentation for Spoken Dialogue Systems" pdf
... the TALK TownInfo Evaluation. In
IEEE/ACL Spoken Language Technology.
Oliver Lemon. 2008. Adaptive Natural Language
Generation in Dialogue using Reinforcement Learn-
ing. In Proceedings of SEMdial.
Oliver ... 2007. The in uence of user tailoring
and cognitive load on user performance in spoken
dialogue systems. In Proc. of the 10th International
Conference of Spoken Langu...
Báo cáo khoa học: "STRUCTURE AND INTONATION IN SPOKEN LANGUAGE UNDERSTANDING*" pptx
...
of integrating syntax and other high-level mod-
ules in spoken language systems.
One quite normal prosody (13, below) for an answer
to the following question (a) intuitively impotes the
intonational ... advantages for automatic
spoken language understanding in such a theory.
Most obviously, where in the past parsing and phono-
logical processing have tended to deliver confl...
Báo cáo khoa học: "INFERRING DISCOURSE RELATIONS IN CONTEXT * " docx
...
In using this rule, an interpreter brings to bear
'top-down' information, in the following sense.
Up to now, discourse and temporal relations have
been determined by using the input ... pushing causing the falling, given
the discourse context in which the pushing and
falling are described in (2),
Narration is
inferred
after all, and so the falling precedes the pu...
Tài liệu Báo cáo khoa học: "A POOAFR MODIFICATIONS IN TEFRAIMOGSRP SLOHOML SFPG" potx
... distinguishing Immediate Dominance (IO) and
Linear Precedence (LP) rules in GPSG (cf GKPS,
pp. 44-50). A context free rule binds information
of two kinds in a single statement. By separating ...
tutes a nonmonotonic device in the formalism,
since final representations must not contain occur-
rences of ANY. In our terms, final representations
must not contain negation or disjunc...
Báo cáo khoa học: "Modeling with Structures in Statistical Machine Translation" pot
...
tion we are more interested in cross-linguistic
structures, similar to the case of using interlin-
gua to represent cross-linguistic information in
knowledge-based MT.
To obtain structures that ... We also
introduced an additional constraint in cluster-
ing, which requires that words in the same class
must have at least one common potential part-
of-speech.
Bilingual constra...
Báo cáo khoa học: "Identifying Word Translations in Non-Parallel Texts" potx
...
for checking the consistency of terminological usage
in translations, and for assisting the terminological
work of translators and interpreters.
However, despite serious efforts in the compilation ... non-corresponding word positions
c. Each of the curves increases monotonically, with
formula 1 having the steepest, i. e. best discriminat-
ing characteristic. The dotted curves in f...
Báo cáo khoa học: "The Surprising Variance in Shortest-Derivation Parsing" potx
... fragments of training
examples. Taken to the extreme, this intuition sug-
gests shortest derivation parsing (SDP), wherein a
test sentence is analyzed in a way which uses as few
training fragments ... trees for
a unit cost.
2
Assuming that the SWITCH rules are in
practice broken down into BEGIN and END sub-rules
as in Bansal and Klein (2010), the grammar is linear
in the size of the t...
Báo cáo khoa học: "Modeling Topic Dependencies in Hierarchical Text Categorization" pot
... consti-
tutes our MCC baseline.
Regarding the reranker, we divided the training
set in two chunks of data: Train1 and Train2. The
binary classifiers are trained on Train1 and tested on
Train2 (and vice versa) ... according to the number of
hypotheses (child-free setting).
using the complete hierarchy as representation, i.e.,
up to five times in training and eight time in test-
ing. This i...