Báo cáo khoa học: "Exploiting Heterogeneous Treebanks for Parsing" pptx
Báo cáo khoa học: "Exploiting Multiple Treebanks for Parsing with Quasi-synchronous Grammars" doc
... Association for Computational Linguistics, pages 675–684,
Jeju, Republic of Korea, 8-14 July 2012.
c
2012 Association for Computational Linguistics
Exploiting Multiple Treebanks for Parsing ... present a simple and effective framework
for exploiting multiple monolingual treebanks
with different annotation guidelines for pars-
ing. Several types of transformation patterns
(TP) a...
Báo cáo khoa học: "Exploiting Parallel Texts for Word Sense Disambiguation: An Empirical Study" potx
... problem is par-
ticular severe for WSD, since sense-tagged data
must be collected separately for each word in a
language.
One source to look for potential training data
for WSD is parallel texts, ... surrounding channel then forms
a training example for a supervised WSD program
in the next step.
The average time taken to perform manual se-
lection of target translations for...
Báo cáo khoa học: "Exploiting Web Redundancy for Answer Validation" pptx
... disturbing elements. As for morphol-
ogy, verbs are expanded with all their tense forms
(i.e. present, present continuous, past tense and past
participle). Synonyms and morphological forms are
added ... before, AltaVista was used as
search engine.
A baseline for the answer validation experiment
was defined by considering how often an answer oc-
curs in the top 10 documents among those (100...
Báo cáo khoa học: "An Optimization Tool for MaltParser" pptx
... Association for Computational Linguistics, pages 58–62,
Avignon, France, April 23 - 27 2012.
c
2012 Association for Computational Linguistics
MaltOptimizer: An Optimization Tool for MaltParser
Miguel ... we present MaltOptimizer, a tool
for optimizing MaltParser for a new language
or domain, based on an analysis of the train-
ing data. The optimization is performed in three
phases:...
Tài liệu Báo cáo khoa học: "k-best Spanning Tree Parsing" pptx
... the prefix c-; for example: p–pos,
p–form, c–pos, and c–form. In our model we
use both word form and POS tag and include
the composite form/POS features: p–form/c–
pos and p–pos/c–form.
Branch ... +∞
for unvisited vertex v do
get best in-edge b for v
5: if b ∈ A − Y then
f ← alternate edge into v
if swapping f with b results in smaller δ then
update δ, let e ← f
end if
10: end if
if b fo...
Tài liệu Báo cáo khoa học: "Statistical Machine Translation by Parsing" pptx
... Multitext Grammars and Multitrees
The algorithms in this paper can be adapted for any
synchronous grammar formalism. The vehicle for
the present guided tour shall be multitext grammar
(MTG), which is ... attention to MTGs in Generalized
Chomsky Normal Form (GCNF) (Melamed et al.,
2004). This normal form allows simpler algorithm
descriptions than the normal forms used by Wu
(1997) and Mela...
Tài liệu Báo cáo khoa học: "Exploiting N-best Hypotheses for SMT Self-Enhancement" doc
... Association for Computational Linguistics
Exploiting N-best Hypotheses for SMT Self-Enhancement
Boxing Chen, Min Zhang, Aiti Aw and Haizhou Li
Department of Human Language Technology
Institute for ... Chinese-to-English task
show performance improvements for all the
strategies. Moreover, the combination of the
three strategies achieves further improvements
and outperforms the...
Tài liệu Báo cáo khoa học: "Exploiting Non-local Features for Spoken Language Understanding" pptx
... exploit non-local information in the next
section.
3 Incorporating Non-local Information
3.1 Using Trigger Features
To exploit non-local information to sequential la-
beling for a statistical SLU, ... bet-
ter than CRF (the structured model) not only for
time cost but also for the performance on our ex-
periment
4
. This result shows that local informa-
tion provides the fundamental dec...
Tài liệu Báo cáo khoa học: "Exploiting Syntactic and Shallow Semantic Kernels for Question/Answer Classification" docx
... Introduction
Question answering (QA) is as a form of informa-
tion retrieval where one or more answers are re-
turned to a question in natural language in the form
of sentences or phrases. The typical ... selected
parameters appear as pessimistic estimates for the best model
improvement: the one for BOW is the absolute maximum, but
an average one is selected for the best model.
782
......
Tài liệu Báo cáo khoa học: "Exploiting Structure for Event Discovery Using the MDI Algorithm" doc
... 2007.
c
2007 Association for Computational Linguistics
Exploiting Structure for Event Discovery Using the MDI Algorithm
Martina Naughton
School of Computer Science & Informatics
University College ... of the
event, and represent the extracted information into
a structured form (Grishman, 1997). The types of
events to extract are known in advance. For exam-
ple, “Attack” and “Death”...