Báo cáo khoa học: "Evaluating Machine Translations using mNCD" doc
Báo cáo khoa học: "Evaluating Machine Translations using mNCD" doc
... Sweden, 11-16 July 2010.
c
2010 Association for Computational Linguistics
Evaluating Machine Translations using mNCD
Marcus Dobrinkat and Tero Tapiovaara and Jaakko V
¨
ayrynen
Adaptive Informatics ... com-
puted between the translations and the similarized
references to get the mNCD score.
Table 1 shows some hand-picked German–
English candidate translations along with a) the
refe...
Báo cáo khoa học: "Japanese Morphological Analyzer using Word " doc
... Japanese Morphological Analyzer using Word Co-occurrence
JTAG-
Takeshi FUCHI
NTT Information and Communication
Systems Laboratories ... is the
difficulty in adjusting the grammar and parameters.
Our tagger is also rule-based. By using the co-
occurrence of words, it reduces the difficulty and
generates a continuous increase ... that contains words used
frequently.
In practice,...
Báo cáo khoa học: "SAUMER: SENTENCE ANALYSIS USING METARULES" doc
... SAUMER: SENTENCE ANALYSIS USING METARULES
Fred Popowich
Natural Language Group
Laboratory for Computer and Communications ...
1. INTRODUCTION
The SAUMER system allows the user to specify a
grammar for a natural language using rules and metarules
rhts grammar can then be u¢,ed ~ obtain a semantic
interpretation of ...
(npr > [Terminal] : Terminal#) .
Transformations match with...
Báo cáo khoa học: "Evaluating Centering-based metrics of coherence for text structuring using a reliably annotated corpus" doc
... Evaluating Centering-based metrics of coherence for text
structuring using a reliably annotated corpus
Nikiforos Karamanis,
♣
Massimo Poesio,
♦
Chris Mellish,
♠
and ... novel aspect is that our approach is
based on the position that the most straight-
forward way of using Centering for text struc-
turing is by defining a Centering-based metric
of coherence Karamanis ... Centering-based met...
Báo cáo khoa học: "Identifying Word Translations from Comparable Corpora Using Latent Topic Models" potx
... document pairs.
We test its performance on a collection of compara-
ble texts which are document-aligned and therefore
share their topics. BiLDA takes advantage of the
document alignment by using ... in the original word-
document space (Cos), with aligned documents.
Table 1 shows the Precision@1 scores (the per-
centage of words where the first word from the list
of translations is the co...
Báo cáo khoa học: "Stochastic Language Generation Using WIDL-expressions and its Application in Machine Translation and Summarization" pot
... We generate WIDL-
expressions starting from an input document.
First, we extract a weighted list of topic keywords
from the input document using the algorithm of
Zhou and Hovy (2003). This list ... our headline generation system,
we use the documents from the DUC 2003 eval-
uation competition. Half of these documents
are used as development set (283 documents),
1109
ALG (uni) (bi) Len. Roug...
Tài liệu Báo cáo khoa học: "Grammar Error Correction Using Pseudo-Error Sentences and Domain Adaptation" pdf
... and
method.
• TRG: The models were trained using only the
real-error corpus (baseline).
• SRC: Trained using only the pseudo-error corpus.
• ALL: Trained using the real-error and pseudo-
error corpora ... task is hindered
by the difficulty of collecting large error cor-
pora. We tackle this problem by using pseudo-
error sentences generated automatically. Fur-
thermore, we apply domain...
Tài liệu Báo cáo khoa học: "Identifying Text Polarity Using Random Walks" pptx
... achieves better performance by only using
WordNet synonym, hypernym and similar to rela-
tions. Adding co-occurrence statistics slightly im-
proved performance, while using glosses did not
help at ... handful of seeds is used to define the
two polarity classes. The method is exper-
imentally tested using a manually labeled
set of positive and negative words. It out-
performs the state of...
Tài liệu Báo cáo khoa học: "Automatic Headline Generation using Character Cross-Correlation" doc
...
observation of a document and the step of generat-
ing a title from the estimated information source,
but it was for English documents.
1.1 Headline Length
One of the tasks of the Document Understanding ... contains almost two million
documents with nearly 600 million words. For this
work, 260 documents were selected from the cor-
pus based on the following steps:
• 3170 documents were...
Tài liệu Báo cáo khoa học: "Robust Machine Translation Evaluation with Entailment Features∗" pptx
... NIST
measure MT quality by using the strong correla-
tion between human judgments and the degree of
n-gram overlap between a system hypothesis trans-
lation and one or more reference translations. The
resulting ... Manning
Stanford University
{mgalley,jurafsky,manning}@stanford.edu
Abstract
Existing evaluation metrics for machine translation
lack crucial robustness: their correlations wi...
Từ khóa: