Báo cáo khoa học: "Capturing Salience with a Trainable Cache Model for Zero-anaphora Resolution" doc
Báo cáo khoa học: "Capturing Salience with a Trainable Cache Model for Zero-anaphora Resolution" doc
... sentence-based cache
model, SCM: static cache model, DCM (w/o ZAR): dynamic
cache model disregarding updateSalienceInfo, DCM (with
ZAR): dynamic cache model using the information of correct
zero-anaphoric ... empirical evaluation on Japanese
zero-anaphora resolution shows that our learning-
based cache model drastically reduces the search
space while preserving accuracy....
Báo cáo khoa học: "Chinese Segmentation with a Word-Based Perceptron Algorithm" docx
... information, 3 to 5 con-
tain character and length information, 6 and 7 con-
tain only character information, 8 to 12 contain word
and character information, while 13 and 14 contain
Input: raw ... with
each candidate in the source agenda and puts the
generated candidates onto the target agenda. After
each character is processed, the items in the target
agenda are copied to the source agenda...
Báo cáo khoa học: "PROCESSING ENGLISH WITH A GENERALIZED PHRASE STRUCTURE GRAMMAR" pdf
...
can be captured in a context-free
grammar with a
metagrammor,
i.e. a higher-level
grammar that generates the actual grammar as its
language. The
metagrammar
has two kinds of
statements: ... :
1. Grammar
a. Lexicon
b. Rules and Metarules
2. Parser and Grammar Compiler
3. Semantics Handler
4. Disambiguator
5. HIRE database
3. GRAMMAR AND LEXICON
The grammar that has be...
Báo cáo khoa học: "Machine Translation with a Stochastic Grammatical Channel" doc
... requires massive
manual labor effort for each language pair. Instead,
our approach is to take a more readily acquired
monolingual context-free grammar for the target
language, and use (or perhaps ... SITG: 3
all
A -4 [AA]
aO
A + (AA)
A b(54Y) x/y VX, y lexical translations
A b(.~¢) .z'/~?
VX language 1 vocabulary
A b(_~y) e/y Vy language 2 vocabulary
In the propos...
Báo cáo khoa học: "Lexicon acquisition with a large-coverage unification-based grammar" pot
... features. Barg and Walther (1998)
talk about generalisable and revisable information.
The former are values that are too specific (e.g.
case), while the latter are values that should be
changeable. ... chose
for a statistical PoS tagger,
i.c.
Trigrams'n'Tags
(TnT) (Brants, 2000). These taggers return a num-
ber of alternatives each associated with a proba-
bility, so tha...
Báo cáo khoa học: "Meaningful Conversation with a Mobile Robot" pot
... combined with further background
knowledge (frame axioms and axioms about tem-
poral states, plus ontological information), and the
resulting formula 0 is sent to both a model gener-
ator and a theorem ... representation it uses
for navigation and communication with the dia-
logue manager, and the navigation component.
3.1 Godot, the Robot
Godot is an RWI Magellan Pro mobile robot...
Báo cáo khoa học: "Capturing CFLs with Tree Adjoining Grammars" potx
... partial answer to the more
general issue of characterizing the TAGs that generate
local sets. It serves as a normal form for these TAGs in
the same way that regular grammars serve as a normal
form ...
form for CFGs that generate regular languages. While
for every TAG that generates a local set there is a TAG
in regular form that generates the same set, and every
TAG in re...
Tài liệu Báo cáo khoa học: "Lexical transfer using a vector-space model" doc
... Vector-space model
This section explains our trial for applying
a vector-space model to lexical transfer starting
from a basic idea.
2.1 Basic idea
We can select an appropriate target word
for a ... from case-frame
representations of simple sentences with a
thesaurus for generalization (Akiba et. al., 1996
and Tanaka, 1995); (2) approaches using
structural matching...
Báo cáo khoa học: "Automatic construction of a hypernym-labeled noun hierarchy from text" docx
... 50,000 array of values (or a trian-
gular array of about half this size). With
our current hardware, the largest array we
can comfortably handle is about 100 times
smaller; that is, we can build ... they approximated this
data by just looking at the nearest NP on
each side of a particular NP. Roark and
Charniak (1998) built on that work by actu-
ally using conjunction and apposi...
Báo cáo khoa học: "Automatic Editing in a Back-End Speech-to-Text System" doc
... Vozila Olivier Divay Jeff Adams
Nuance Communications
One Wayside Road
Burlington, MA 01803, U.S .A.
{maximilian.bisani,paul.vozila,olivier.divay,jeff.adams}@nuance.com
Abstract
Written documents ... need
to perform a significant amount of editing to obtain
a document conforming to the customary standards.
We need to look for what the user wants rather than
what he says.
Natural languag...