... Republic, June 2007.
c
2007 Association for Computational Linguistics
PERSONAGE: PersonalityGenerationfor Dialogue
Franc¸ois Mairesse
Department of Computer Science
University of Sheffield
Sheffield, ... methods for automati-
cally generating language that varies along
personality dimensions. We present PER-
SONAGE (PERSONAlity GEnerator), the
first highly parametrizable language gener-
ator for extraversion, ... such as RELATIVE CLAUSE for the
INFER relation, PERIOD HOWEVER CUE WORD for
CONTRAST, and ALTHOUGH ADVERBIAL CLAUSE
for CONCESS, that we hypothesize to result in more
formal language. Extravert...
... the information in and outside the organization.
Any information from any source can be useful, necessary for organizations as well as for
members and volunteer activities in general. For example, ... classes for clubs.
• Support clubs in terms of organization experience.
3.7. Backgrounds
VIET NAM GREEN GENERATIONFOR A GREEN GLOBE
PROPOSAL SUMMARY
1. Project Title: ‘Vietnam Green Generation ... globally-updated information
and technology, foreign languages and up-to-date knowledge. On one hand, many volunteers
groups are mushrooming to show their concern and care for social and environmental...
... DIKSIGN FOR I)IALOGUE COMPREHENSION
William C. Mann
USC Information Sciences Institute
Marina del Rey, CA
April, 1979
This
paper describes aspects of the design of a dialogue
comprehension ... llearsay-l[ and makes
Preeminence Scheduling fairly straightforward.
I. Dialogue Games, Speech Acts and DCS Examination
of actual human dialogue reveals structure extending over
• ~overal turns ... resolve. Our past work on dialogue has
led to an account of this structure, Dialogue Game theory
fLorin & Moore 1978; Moore, l,evlu & Mann 1977]. This
theory claims that dialogues (and
other...
... SAT
solver [8, 10, 25]. First, for each atomic formula of the form
x IS NULL we set the variable x to NULL, and then propagate
NULL values through the formula. If the formula evaluates
to UNKNOWN, ... constraint solver
for a satisfying assignment ¯s
1
of ϕ, then a satisfying assign-
ment ¯s
2
for ϕ∧¬[¯s
1
], then for ϕ∧¬[¯s
1
]∧¬[¯s
2
], etc. Iterating
157
Dynamic Test Input Generationfor Database ... the form δ
1
= δ
2
, δ
1
= δ
2
,
or δ LIKE ρ, for atoms δ
1
and δ
2
, and regular expressions
ρ. To do this normalization, we replace constraints of the
form δ = s (respectively δ = s), for...
... target
information during the measure word generation
process. We do not integrate our measure word
generation module into the SMT decoder since
there is only little target contextual information ... quantity of objects.
Therefore, in the English-to-Chinese machine
translation task we need to take additional efforts
to generate the missing measure words in Chinese.
For example, when translating ... word with the highest
probability will be chosen.
There are two reasons why we perform measure
word generationfor SMT systems as a post-
processing step. One is that in this way our method
can...
... lenient metric is applied
for generating the gold standard for this collection.
5 An Opinion System CopeOpi
A Chinese opinion extraction system for opinion-
ated information, CopeOpi, is introduced ... this system’s performance is satisfac-
tory, its behavior is not like human beings. For a
computer system, the lenient testing collection is
fuzzier and contains more information for judg-
ment. ... pages 89–92,
Prague, June 2007.
c
2007 Association for Computational Linguistics
Test Collection Selection and Gold Standard Generation
for a Multiply-Annotated Opinion Corpus
Lun-Wei Ku,...
... ‘‘%’’
for abandoned sentences and ‘‘x’’ for noise.
CallHome Spanish is further annotated for dialogue
games and activities. Dialogue game annotation is
based on the MapTask notion of a dialogue ... 7: Information gain for FLSA
is also a high performance improvement. Occasion-
ally, if the IG is small this does not hold. For exam-
ple, using the previous DA reduces the entropy by
0.21 for ... to dialogue act classi-
fication. Dialogue systems need to perform dia-
logue act classification, in order to understand the
role the user’s utterance plays in the dialogue (e.g.,
a question for...
... July 2006.
c
2006 Association for Computational Linguistics
A Flexible Approach to Natural Language Generationfor Disabled
Children
Pradipta Biswas
School of Information Technology
Indian ... Chinese. The
NLG part of this system uses trigram language
model for selecting appropriate inflectional form
for target language generation.
When NLG (or NLP) technology is ap-
plied in assistive ...
Rank(Pi)=Minimum(Counter(Tj)) for all j in Pi
Now before sentence realization the phrases are
ordered according to their rank. Each of these
phrase orders produces a separate sentence. As
for example let...
... the back-end, the Dialogue Manager can
re-consult SR for other hypotheses. Alterna-
tively, the Dialogue Manager can fire Natural
Language Generation with an output request for
clarification. ...
example dialogues have more primitive cousins
under development today.
Briefly, our example dialogue types are listed in
Table 3.
Dialogue
with an
Appliance
Dialogue
with an
Application
Dialogue ... it was first developed for
bilingual dialogue in a voice-to-voice machine
translation application. In this application, the
Dialogue Manager is available for meta-
dialogues with either user...
... 2007.
c
2007 Association for Computational Linguistics
Combining Multiple Knowledge Sources forDialogue Segmentation in
Multimedia Archives
Pei-Yun Hsueh
School of Informatics
University of Edinburgh
Edinburgh, ... interpretation does not hold
true for all tasks.
3
For example, Gruenstein et al.(2005) report kappa
(PK/WD) of 0.41(0.28/0.34) for determining the top-level and
0.45(0.27/0.35) for the sub-level segments ... dialogue act
type
4
and speaker role (e.g., project manager, mar-
4
In the annotations, each dialogue act is classified as one
of 15 types, including acts about information exchange (e.g.,
Inform),...
... tuples for train-
ing, 240 tuples for development and 240 for test-
ing). Documents and captions were parsed with
the Stanford parser (Klein and Manning, 2003) in
order to obtain dependencies for ... infor-
mation in a story.
7
This is an encouraging result
as it highlights the importance of the visual infor-
mation for the caption generation task. In general,
word overlap is the worst performing ... phrase-based model for both image annota-
tion and caption generation. We also believe that
our approach would benefit from more detailed
linguistic and non-linguistic information. For in-
stance,...