Study of Practical Eﬀectiveness for Machine Translation Using
Recursive Chain-link-type Learning
Hiroshi Echizen-ya
Dept. of Electronics and Information
Hokkai-Gakuen University
S 26-Jo, W 11-Chome, Chuo-ku
Sapporo, 064-0926 Japan
echi@eli.hokkai-s-u.ac.jp
Kenji Araki
Division of Electronics and Information
Hokkaido University
N 13-Jo, W 8-Chome, Kita-ku
Sapporo, 060-8628 Japan
araki@media.eng.hokudai.ac.jp
Yoshio Momouchi
Dept. of Electronics and Information
Hokkai-Gakuen University
S 26-Jo, W 11-Chome, Chuo-ku
Sapporo, 064-0926 Japan
momouchi@eli.hokkai-s-u.ac.jp
Koji Tochinai
Division of Business Administration
Hokkai-Gakuen University
4-Chome, Asahi-machi, Toyohira-ku
Sapporo, 060-8790 Japan
tochinai@econ.hokkai-s-u.ac.jp
Abstract
A number of machine translation systemsbased
on thelearningalgorithms are presented. These
methods acquire translation rules from pairs
of similar sentences in a bilingual text cor-
pora. This means that it is diﬃcult for the
systems to acquire the translation rules from
sparse data. As a result, these methods require
large amounts of training data in order to ac-
quire high-quality translation rules. To over-
comethis problem, we propose a method ofma-
chine translation using a Recursive Chain-link-
type Learning. In our new method, the system
can acquire many new high-quality translation
rules from sparse translation examples based on
already acquired translation rules. Therefore,
acquisition of new translation rules results in
the generation of more new translation rules.
Such aprocessofacquisitionoftranslationrules
islikealinkedchain. Fromtheresultsofevalua-
tionexperiments,weconﬁrmedtheeﬀectiveness
of Recursive Chain-link-type Learning.
1 Introduction
Rule-Based Machine Translation(MT)(Hutchins
and Somers, 1992) requires large-scale knowl-
edge to analyze both source language(SL)
sentences and target language(TL) sentences.
Moreover, it is diﬃcult for a developer to com-
pletely describe large-scale knowledge that can
analyze various linguistic phenomena. There-
fore, Rule-Based MT is time-consuming and
expensive. Statistical MT and Example-Based
MT have been proposed to overcome the dif-
ﬁculties of Rule-Based MT. These approaches
correspondto Corpus-Basedapproach. Corpus-
Based approach uses translation examples that
keep including linguistic knowledge. This
means that the system can improve the quality
ofitstranslationonlybyaddingnewtranslation
examples. However, in Statistical MT(Brown
et al., 1990), large amounts of translation
examples are required in order to obtain
high-quality translation. Moreover, Example-
Based MT(Sato and Nagao, 1990; Watanabe
and Takeda, 1998; Brown, 2001; Carl, 2001)
which relies on various knowledge resources
results in the same diﬃculties as Rule-Based
MT. Therefore, Example-Based MT, which
automatically acquires the translation rules
from only bilingual text corpora, is very eﬀec-
tive. However, existing Example-Based MT
systems using the learning algorithms require
large amounts of translation pairs to acquire
high-quality translation rules.
In Example-Based MT based on analogical
reasoning(Malavazos, 2000; Guvenir, 1998), the
diﬀerent parts are replaced by variables to gen-
eralize translation examples as shown in (1) of
Figure 1. However, the number of diﬀerent
parts of the two SL sentences must be same
as the number of diﬀerent parts of the two TL
sentences. This means that the condition of ac-
quisition of translation rules is very strict be-
cause this method allows only n:n mappings in
the number of the diﬀerent parts between the
SL sentences and the TL sentences. As a re-
sult, many translationrulescannot be acquired.
(McTait, 2001) generalizes both the diﬀerent
parts and the common parts as shown in Fig-
ure 1(2). This means that (McTait, 2001) al-
lows m:n mappings in the number of the diﬀer-
ent parts, or the number of the common parts.
However, itisdiﬃculttoacquirethetranslation
rules that correspond to the lexicon level. On
the other hand, we have proposed a method of
Machine Translation using Inductive Learning
with Genetic Algorithms(GA-ILMT)(Echizen-
ya et al., 1996). This method automatically
generates the similar translation examples from
only given translation examples by applying ge-
netic algorithms(Goldberg, 1989) as shown in
(3a) of Figure 1. Moreover, the system per-
forms Inductive Learning. By using Inductive
Learning, the abstract translation rules are ac-
quired by performing phased extraction of dif-
ferent parts as shown in Figure 1(3b) and (3c).
In all methods shown in Figure 1, the condi-
tion of acquisition of translation rules is that
two similar translation examples must exist. As
a result, the systems require large amounts of
translation examples.
We propose a method of MT using Recur-
sive Chain-link-type Learning as a method to
overcome the above problem. In our method,
the system acquires new translation rules from
sparse data using other already acquired trans-
lation rules. For example, ﬁrst, translation
rule B is acquired by using translation rule A
when the translation rule A exists in the dictio-
nary. Moreover, translation rule C is acquired
by using the translation rule B. Such a pro-
cess of acquisition of translation rules is like a
chain where each ring is linked. Therefore, we
call this mechanism Recursive Chain-link-type
Learning(RCL).Thismethodcaneﬀectively ac-
quire many translation rules from sparse data
withoutdependingon thediﬀerentparts ofsim-
ilar translation pairs. In this paper, we describe
the eﬀectiveness of RCL through evaluation ex-
periments.
2 Basic Idea
RCL is a method with an ability that automat-
ically acquires translation knowledge in a com-
puterwithoutanyanalyticalknowledge, suchas
GA-ILMT. This is the ability to extract corre-
g14975g14984g14976g14967g15006g15036g15045g15036g15049g15032g15043g15040g15057g15032g15051g15040g15046g15045g14967g15046g15037g14967g15003g15040g15037g15037g15036g15049g15036g15045g15051g14967g15015g15032g15049g15051g15050g14967g14975g15006g15154g15053g15036g15045g15040g15049 g15032g15045g15035g14967g15002g15040g15034g15036g15042g15043g15040g14979g14967g14984g14992g14992g14991g14976
g14975g14984g15032g14976g15000g15043g15040g15038g15045g15044g15036g15045g15051g15050g14993
g15008g15008g15008g15008g15038g15032g15053g15036g14967g15051g15039g15036g14967g15033g15046g15046g15042g15972g15042g15040g15051g15032g15033g14978g15056g15007 g15053g15036g15049g14978g15003g15007g14978g15044
g15024g15046g15052g15038g15032g15053g15036g14967g15051g15039g15036g14967g15047g15036g15045g15972g15042g15032g15043g15036g15044g14978g15056g15007 g15053g15036g15049g14978g15003g15007g14978g15045
g14975g14984g15033g14976g15006g15036g15045g15036g15049g15032g15043g15040g15057g15032g15051g15040g15046g15045g14967g15046g15037g14967g15003g15040g15037g15037g15036g15049g15036g15045g15051g14967g15015g15032g15049g15051g15050g14993
g15040g15037g14967g15040g15972g14978g15044 g15032g15045g15035g14967g15056g15046g15052g14967g15972g14978g15045g14967g15051g15039g15036g15045
g15023
g14984
g15038g15032g15053g15036g14967g15051g15039g15036g14967g15023
g14985
g15972g15023
g14985
g14978g15056g15007g14967g15053g15036g15049g14978g15003g15007g15023
g14984
g14975g14985g14976g15006g15036g15045g15036g15049g15032g15043g15040g15057g15032g15051g15040g15046g15045g14967g15046g15037g14967g15003g15040g15037g15037g15036g15049g15036g15045g15051g14967g15015g15032g15049g15051g15050g14967g15032g15045g15035g14967g15002g15046g15044g15044g15046g15045g14967g15015g15032g15049g15051g15050g14967g14975g15012g15034g15019g15032g15040g15051g14979g14967g14985g14983g14983g14984g14976
g14975g14985g15032g14976g15000g15043g15040g15038g15045g15044g15036g15045g15051g15050g14993
g15019g15039g15036g14967g15034g15046g15044g15044g15040g15050g15050g15040g15046g15045g15038g15032g15053g15036g14967g15051g15039g15036g14967g15047g15043g15032g15045g14967g15043 g14967g15043 g14967g15043 g14967g15052g15047
g15014g15052g15049g14967g15038g15046g15053g15036g15049g15045g15044g15036g15045g15051g15038g15032g15053g15036g14967g15032g15043g15043g14967g15043g15032g15054g15050g14967g15032g15043g15043g14967 g14967g15032g15043g15043g15032g15043g15043 g15052g15047
g14975g14985g15033g14976g15006g15036g15045g15036g15049g15032g15043g15040g15057g15032g15051g15040g15046g15045g14967g15046g15037g14967g15003g15040g15037g15037g15036g15049g15036g15045g15051g14967g15015g15032g15049g15051g15050g14993
g14975g15738g14976g14967g15038g15032g15053g15036g14967g14975g15738g14976g14967g15052g15047g14967g15972 g14975g15738g14976g14967g15032g15033g15032g15045g15035g15046g15045g15045g15032 g14975g15738g14976
g14975g14985g15034g14976g15006g15036g15045g15036g15049g15032g15043g15040g15057g15032g15051g15040g15046g15045g14967g15046g15037g14967g15002g15046g15044g15044g15046g15045g14967g15015g15032g15049g15051g15050g14993
g15019g15039g15036g14967g15034g15046g15044g15044g15040g15050g15050g15040g15046g15045g14967g14975g15738g14976g14967g15051g15039g15036g14967g15047g15043g15032g15045g14967g14975g15738g14976g14967g15972 g15011g15032g14967g15034g15046g15044g15044g15040g15050g15050g15040g15046g15045g14967g14975g15738g14976g14967g15043g15036g14967g15047g15043g15032g15045
g15014g15052g15049g14967g15038g15046g15053g15036g15049g15045g15044g15036g15045g15051g14967g14975g15738g14976g14967g15032g15043g15043g14967g15043g15032g15054g15050g14967g14975g15738g14976
g14975g14986g14976g15006g15000g14980g15008g15011g15012g15019g14967g14975g15004g15034g15039g15040g15057g15036g15045g14980g15056g15032 g15036g15051g14967g15032g15043g14981g14979g14967g14984g14992g14992g14989g14976
g15972g15013g15046g15051g15049g15036g14967g14967g14967g15013g15046g15051g15049g15036g15038g15046g15052g15053g15036g15049g15045g15036g15044g15036g15045g15051g15032g15033g15032g15045g15035g15046g15045g15045g15032g15051g15046g15052g15051g15036g15050g15043g15036g15050g14967g14967g14967g14967g15043g15046g15040g15050
g15972g15011g15032g14967g15034g15046g15044g15044g15040g15050g15050g15040g15046g15045g15032g15033g15032g15045g15035g15046g15045g15045g15032g15043g15036g14967g15047g15043g15032g15045
g15972 g15013g15046g15051g15049g15036g14967g15038g15046g15052g15053g15036g15049g15045g15036g15044g15036g15045g15051 g14975g15738g14976g14967g15051g15046g15052g15051g15036g15050 g15043g15036g15050g14967g15043g15046g15040g15050
g17128g15007g15036g14967g15043g15040g15042g15036g15050 g15051g15036g15032g14981g14967g14967g14967g14967g14967g17147g5328g14982g16946 g14982g16909g10789g14982g16911g14982g4450g16912g14982g16938g16924g17134g14976
g17128g15018g15039g15036 g15043g15040g15042g15036g15050 g15051g15036g15045g15045g15040g15050g14981g17147g5328g4442g14982g16946 g14982g17025g17030g17012g14982g16911g14982g4450g16912g14982g16938g16924g17134g14976
g14975g14986g15032g14976g15006g15036g15045g15036g15049g15032g15051g15040g15046g15045g14967g15046g15037g14967g15019g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15004g15055g15032g15044g15047g15043g15036g15050g14967g15033g15056g14967g15000g15047g15047g15043g15056g15040g15045g15038g14967g15006g15036g15045g15036g15051g15040g15034g14967g15000g15043g15038g15046g15049g15040g15051g15039g15044g15050
g17128g15007g15036g14967g15043g15040g15042g15036g15050g14967g15051g15036g15045g15045g15040g15050g14981g17147g5328g14982g16946g14982g17025g17030g17012g14982g16911g14982g4450g16912g14982g16938g16924g17134g14976
g17128g15018g15039g15036g14967g15043g15040g15042g15036g15050g14967g15051g15036g15032g14981g17147g5328g4442g14982g16946g14982g16909g10789g14982g16911g14982g4450g16912g14982g16938g16924g17134g14976
g14975g14986g15033g14976g15006g15036g15045g15036g15049g15032g15043g15040g15057g15032g15051g15040g15046g15045g14967g15032g15045g15035g14967g15004g15055g15051g15049g15032g15034g15051g15040g15046g15045g14967g15046g15037g14967g15003g15040g15037g15037g15036g15049g15036g15045g15051g14967g15015g15032g15049g15051g15050g14967g15033g15056g14967g15008g15045g15035g15052g15034g15051g15040g15053g15036g14967g15011g15036g15032g15049g15045g15040g15045g15038
g17128g15007g15036g14967g15043g15040g15042g15036g15050g14967g15051g15036g15045g15045g15040g15050g14981g17147g5328g14982g16946g14982g17025g17030g17012g14982g16911g14982g4450g16912g14982g16938g16924g17134g14976
g17128g15007g15036g14967g15043g15040g15042g15036g15050g14967g15051g15036g15032g14981g17147g5328g14982g16946g14982g16909g16909g10789g10789g14982g16911g14982g4450g16912g14982g16938g16924g17134g14976
g17128g15007g15036g14967g15043g15040g15042g15036g15050g14967g14999g14983g14981g17147g5328g14982g16946g14982g14999g14983g14982g16911g14982g4450g16912g14982g16938g16924g17134g14976
g14975g14986g15034g14976g15012g15046g15049g15036g14967g15006g15036g15045g15036g15049g15032g15043g15040g15057g15032g15051g15040g15046g15045g14967g15032g15045g15035g14967g15004g15055g15051g15049g15032g15034g15051g15040g15046g15045g14967g15046g15037g14967g15003g15040g15037g15037g15036g15049g15036g15045g15051g14967g15015g15032g15049g15051g15050g14967g15033g15056
g17128g15007g15036g15043g15040g15042g15036g15050g14967g14999g14983g14981g17147g5328g14982g16946g14982g14999g14983g14982g16911g14982g4450g16912g14982g16938g16924g17134g14976
g17128g15018g15039g15036g15043g15040g15042g15036g15050g14967g14999g14983g14981g17147g5328g4442g14982g16946g14982g14999g14983g14982g16911g14982g4450g16912g14982g16938g16924g17134g14976
g17128g14999g14984g14967g15043g15040g15042g15036g15050g14967g14999g14983g14981g17147g14999g14984g14982g16946g14982g14999g14983g14982g16911g14982g4450g16912g14982g16938g16924g17134g14976
g15006g15040g15053g15036g15045g14967g15019g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15004g15055g15032g15044g15047g15043g15036g15050
g15006g15036g15045g15036g15049g15032g15051g15036g15035g14967g15019g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15004g15055g15032g15044g15047g15043g15036g15050
g17128g15051g15036g15045g15045g15040g15050g17147g17025g17030g17012g17129g17132g17128g15051g15036g15032g17147g16909g10789g17129
g17128g15007g15036g17147g5328g17129g17132g17128g15018g15039g15036g17147g5328g4442g17129
g15008g15045g15035g15052g15034g15051g15040g15053g15036g14967g15011g15036g15032g15049g15045g15040g15045g15038
Figure 1: Previous works.
sponding parts from pairs of objects with which
itcorresponds. Inthispaper,weapplythisabil-
ity to a translation example that consists of SL
and TL sentences. A system with RCL can ac-
quire translation rules from sparse translation
examples. Figure 2 shows how translation rules
are acquired using this method
1
.
Figure 2 shows the process where translation
rules B, C and D are acquired one after another
using RCL. In this paper, source parts arethose
parts that are extracted from the SL sentences
of translation examples, and target parts are
those parts that are extracted from the TL sen-
tences of translation examples. Moreover, part
translation rules are pairs of source parts and
1
In Figure 2, the use of a Greek character means that
all language characters correspond to unknown character
strings for a computer.
g17128g17128g17128g17128
g15411g15411g15411g15411
g17147g17147g17147g17147
g15442g15442g15442g15442
g17129g17129g17129g17129
g17128g15406g15407
g15408g15409g15410
g15411
g15412g14981
g17147
g15437g15444g15442
g15443
g15441g15440g15445
g15439
g17134
g17129
g17128g17128g17128g17128
g15406g15407
g15408g15409g15410
g15406g15407
g15408g15409g15410
g15406g15407
g15408g15409g15410
g15406g15407
g15408g15409g15410
g14999g14999g14999g14999g17130
g17130g17130g17130
g15412g15412g15412g15412g14981
g14981g14981g14981
g17147g17147g17147g17147
g15437g15444g15437g15444g15437g15444g15437g15444
g14999g14999g14999g14999g17130
g17130g17130g17130
g15443g15441
g15440g15445
g15439
g15443g15441
g15440g15445
g15439
g15443g15441
g15440g15445
g15439
g15443g15441
g15440g15445
g15439
g17134g17134g17134g17134
g17129g17129g17129g17129
g17128g15415g15416
g15417g15410g15418
g15429
g15412g14981
g17147
g15446g15444g15449g15461
g15443g15441g15448
g15439
g17134
g17129
g17128g17128g17128g17128
g15418g15429g15418g15429g15418g15429g15418g15429
g17147g17147g17147g17147
g15449g15461g15449g15461g15449g15461g15449g15461
g17129g17129g17129g17129
g17128g15419g15420
g15428g15418g15429
g17160g14981g17147
g15450
g15444g15449g15461
g15443
g15460g15451g15452
g17134
g17129
g17128g17128g17128g17128
g15419g15420
g15428
g15419g15420
g15428
g15419g15420
g15428
g15419g15420
g15428
g14999g14999g14999g14999g17130
g17130g17130g17130
g17160g17160g17160g17160g14981
g14981g14981g14981
g17147g17147g17147g17147
g15450g15444g15450g15444g15450g15444g15450g15444
g14999g14999g14999g14999g17130
g17130g17130g17130
g15443g15460g15451
g15452
g15443g15460g15451
g15452
g15443g15460g15451
g15452
g15443g15460g15451
g15452
g17134g17134g17134g17134
g17129g17129g17129g17129
g15019g15049g15032
g15045
g15050g15043
g15032g15051g15040g15046g15045
g14967
g15036g15055g15032
g15044
g15047g15043g15036
g14967
g15013g15046g14981g14984
Pr
ocess
g15019g15049g15032
g15045
g15050g15043
g15032g15051g15040g15046g15045
g14967
g15036g15055g15032
g15044
g15047g15043g15036
g14967
g15013g15046g14981g14985
g15019g15049g15032
g15045
g15050g15043
g15032g15051g15040g15046g15045
g14967
g15036g15055g15032
g15044
g15047g15043g15036
g14967
g15013g15046g14981g14986
g15013g15046g14981g14984
Pr
ocessg15013g15046g14981g14985
Pr
ocessg15013g15046g14981g14986
g15015g15032g15049g15051
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043
g15036
g14967g15000
g15015g15032g15049g15051
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043
g15036
g14967g15000
g15015g15032g15049g15051
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043
g15036
g14967g15000
g15015g15032g15049g15051
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043
g15036
g14967g15000
g15018g15036g15045g15051g15036g15045
g15034
g15036
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967
g14967g14967
g14967g15049g15052g15043
g15036g14967
g15001
g15018g15036g15045g15051g15036g15045
g15034
g15036
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967
g14967g14967
g14967g15049g15052g15043
g15036g14967
g15001
g15018g15036g15045g15051g15036g15045
g15034
g15036
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967
g14967g14967
g14967g15049g15052g15043
g15036g14967
g15001
g15018g15036g15045g15051g15036g15045
g15034
g15036
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967
g14967g14967
g14967g15049g15052g15043
g15036g14967
g15001
g15015g15032g15049g15051
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043
g15036
g14967g15002
g15015g15032g15049g15051
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043
g15036
g14967g15002
g15015g15032g15049g15051
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043
g15036
g14967g15002
g15015g15032g15049g15051
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043
g15036
g14967g15002
g15018g15036g15045g15051g15036g15045
g15034
g15036
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036g14967g15003
g15018g15036g15045g15051g15036g15045
g15034
g15036
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036g14967g15003
g15018g15036g15045g15051g15036g15045
g15034
g15036
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036g14967g15003
g15018g15036g15045g15051g15036g15045
g15034
g15036
g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036g14967g15003
g17128g17128g17128g17128
g15018
g15046
g15052g15049
g15034g15036
g14967
g15047
g15032
g15049
g15051
g15018
g15046
g15052g15049
g15034g15036
g14967
g15047
g15032
g15049
g15051
g15018
g15046
g15052g15049
g15034g15036
g14967
g15047
g15032
g15049
g15051
g15018
g15046
g15052g15049
g15034g15036
g14967
g15047
g15032
g15049
g15051
g17147g17147g17147g17147
g15019g15032g15049g15038g15036g15051g14967
g15047
g15032g15049g15051
g15019g15032g15049g15038g15036g15051g14967
g15047
g15032g15049g15051
g15019g15032g15049g15038g15036g15051g14967
g15047
g15032g15049g15051
g15019g15032g15049g15038g15036g15051g14967
g15047
g15032g15049g15051
g17129g17129g17129g17129
g15019g15049
g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036
g15019g15049
g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036
g15019g15049
g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036
g15019g15049
g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036
Figure
2:
Sc
hema
in
pro
cess
of
acquisition
of
translation
rules
using
R
CL.
target
parts,
extracted
as
parts
like
translation
rules
A
and
C
i
n
Figure
2.
Sen
tence
translation
rules
are
pairs
of
source
and
target
parts
ex-
tracted
as
sen
tences
like
translation
rules
B
and
D
i
n
Figure
2.
On
the
other
hand,
translation
rules
that
are
used
as
starting
p
oin
ts
in
the
ac-
quisition
pro
cess
of
translation
rules,
like
trans-
lation
rule
A
i
n
Figure
2,
are
acquired
b
y
using
GA-ILMT.
The
reason
b
eing
that
the
system
can
p
erform
translation
based
on
only
learning
abilit
y
without
an
y
analytical
kno
wledge,
b
y
us-
ing
GA-ILMT
and
R
CL.
A
system
with
R
C
L
acquires
part
translation
rules
and
sen
tence
translation
rules
together.
As
a
result,
a
c
hain
reaction
causes
the
ac-
quisition
of
translation
rules.
In
the
pro
cess
No.1
of
Figure
2,
translation
rule
A
has
infor-
mation
that
the
system
can
extract
“Z”
from
the
SL
sen
tences
of
translation
examples,
or
the
source
parts
of
translation
rules,
and
can
extract
“
ζ
”
from
the
TL
sen
tences
or
the
target
parts.
Therefore,
the
system
can
acquire
the
sen
tence
translation
rule
B
b
y
extracting
“Z”
from
the
SL
sen
tence
of
translation
example
No.1
and
“
ζ
”
from
the
TL
sen
tence
of
translation
exam-
ple
No.1.
The
acquired
translation
rule
B
has
information
that
the
system
can
extract
from
the
righ
t
o
f
“E”
to
the
left
of
“H”
in
the
SL
sen
tences
of
translation
examples,
or
the
source
parts
of
translation
rules,
and
can
extract
from
the
righ
t
o
f
“
θ
”
t
o
the
left
of
“
η
”
i
n
the
TL
sen
tences
or
the
target
parts.
By
using
this
in-
formation,
in
pro
cess
2,
the
system
can
acquire
part
translation
rule
C
�
NΩ
�
νω
�
b
y
extract-
ing
“NΩ”
from
the
SL
sen
tence
of
translation
example
No.2
and
“
νω
”
from
the
TL
sen
tence.
Moreo
v
er,
in
pro
cess
3,
translation
rule
D
i
s
ac-
quired
based
on
translation
rule
C.
Suc
h
pro
cess
is
p
erformed
b
y
deciding
the
common
and
dif-
feren
t
parts
in
c
haracter
strings
of
translation
examples
(Araki
e
t
al.,
1995).
Therefore,
the
system
p
ossesses
an
abilit
y
t
o
decide
common
and
diﬀeren
t
parts
b
e
t
w
een
t
w
o
ob
jects.
3
Outline
g15018g15046g15052g15049
g15034g15036
g14967g15018
g15036g15045
g15051g15036
g15045
g15034
g15036
g15019g15049g15032
g15045
g15050g15043
g15032g15051g15040g15046g15045
g14967
g15015g15049g15046
g15034g15036g15050g15050
g15019g15049g15032
g15045
g15050g15043
g15032g15051g15040g15046g15045
g14967
g15017
g15036
g15050g15052g15043
g15051
g15015g15049g15046g15046g15037g15049g15036
g15032g15035g15040
g15045
g15038
g15002
g15046
g15049
g15049
g15036g15034
g15051g14967
g15019
g15049
g15032g15045
g15050
g15043
g15032g15051
g15040
g15046
g15045g14967g15017
g15036
g15050
g15052
g15043g15051
g15005g15036g15036g15035g15033g15032
g15034g15042g14967g15015g15049g15046
g15034g15036g15050g15050
g15011g15036
g15032g15049
g15045g15040
g15045g15038g14967g15015
g15049g15046g15034
g15036
g15050g15050
g15003
g15040
g15034
g15051
g15040
g15046
g15045g15032
g15049g15056g14967
g15037
g15046
g15049g14967
g15019g15049g15032
g15045
g15050g15043
g15032g15051g15040g15046g15045
g14967
g15017
g15052
g15043g15036g15050
Figure
3:
Pro
cess
ﬂo
w.
Figure
3
sho
ws
the
outline
of
an
English-to-
Japanese
MT
system
with
R
CL.
First,
a
user
in-
puts
a
S
L
sen
tence
in
English.
In
the
translation
pro
cess,
the
system
generates
translation
results
using
translation
rules
acquired
in
the
learning
pro
cess.
The
user
then
pro
ofreads
the
trans-
lated
sen
tences
c
hec
king
for
errors.
In
the
feed-
bac
kpro
cess,
the
system
ev
aluates
the
transla-
tion
rules
used
in
the
translation
pro
cess.
In
the
learning
pro
cess,
the
translation
rules
are
acquired
b
y
using
t
w
o
learning
algorithms.
One
is
GA-ILMT,
the
other
is
R
CL.
These
t
w
o
al-
gorithms
w
orkeac
h
other.
Namely
,
the
trans-
lation
rules
acquired
b
y
GA-ILMT
are
used
in
R
CL,
and
the
translation
rules
acquired
b
y
R
C
L
are
used
in
Inductiv
e
Learning
of
GA-ILMT.
In
this
pap
er,
w
e
implemen
ted
a
new
system
based
on
Figure
3
a
s
a
b
o
otstrapping
system,
and
w
e
then
ev
aluated
this
system.
4 Process
4.1 Translation process
In the translation process, the system gener-
ates translation results using acquired transla-
tion rules. First, the system selects the sen-
tence translation rules that can be applied to
the SL sentence. Second, the system generates
thetranslationresultsbyreplacingthevariables
in the sentence translation rules with the part
translation rules.
4.2 Feedback process
In the feedbackprocess, the system evaluates
the translation rules used. First, the system
evaluatesthetranslationruleswithoutvariables
by using the results of combinations between
the translation rules with variables and the
translation rules without variables(Echizen-ya
et al., 1996). Next, the system evaluates trans-
lationruleswithvariablesbyusingtheprocesses
of combinations between the translations rules
with variables and the translation rules without
variables(Echizen-ya et al., 2000). As a result,
the system increases the correct translation fre-
quencies, or the erroneous translation frequen-
cies, of the translation rules by using these eval-
uation methods for the translation rules.
4.3 Learning process
4.3.1 GA-ILMT
In this paper, by using the process of acquisi-
tion of translation rules in GA-ILMT, the sys-
tem acquires both sentence and part transla-
tion rules. These rules are then used as starting
points when the system performs RCL.
4.3.2 Recursive Chain-link-type
Learning(RCL)
In this section, we describethe processofacqui-
sition of translation rules using RCL. The de-
tails of the process of acquisition of part trans-
lation rules are as follows.
(1)The system selects translation examples
that have common parts with the sentence
translation rules.
(2)The system extracts the parts that corre-
spond to the variables in the source parts
and in the target parts of the sentence
translation rules from the SL sentences,
and the TL sentences of the translation ex-
amples.
(3)The system registers pairs, of the parts ex-
tractedfromtheSLsentencesandtheparts
extracted from the TL sentences, as the
part translation rules.
(4)The system gives the correct and erroneous
frequencies of sentence translation rules to
the acquired part translation rules.
Figure 4
2
shows an example of the acquisi-
tionofaparttranslationruleusingthesentence
translation rule. In Figure 4, (thirty;30[sanju])
as the part translation rule is acquired be-
cause “thirty” corresponds to the variable in
the source part of sentence translation rule and
“30[sanju]” corresponds to the variable in the
target part of sentence translation rule.
g14975g15014g15043g15035g14967g15005g15032g15040g15051g15039g15037g15052g15043g14967g15054g15040g15043g15043g14967g15033g15043g15046g15054g14967g15040g15045 g15051g15039g15040g15049g15051g15056 g15044g15040g15045g15052g15051g15036g15050 g14981g17147
g17128g15019g15039g15036g15056g14967g15032g15049g15036g14967g15038g15046g15040g15045g15038g14967g15051g15046g14967g15043g15036g15032g15053g15036g14967g15040g15045 g14999g14983g14967g14967g14967g14967g14967g14967g15044g15040g15045g15052g15051g15036g15050 g14981g17147
g15000g15034g15048g15052g15040g15050g15040g15051g15040g15046g15045g14967g15046g15037g14967g15051g15039g15036g14967g15047g15032g15049g15051g14967g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036g14967
g15052g15050g15040g15045g15038g14967g15051g15039g15036g14967g15050g15036g15045g15051g15036g15045g15034g15036g14967g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036
g17128g15051g15039g15040g15049g15051g15056g17147g17139g17136g15026g15050g15032g15045g15041g15052 g15028g17129
g15019g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15036g15055g15032g15044g15047g15043g15036
g15015g15032g15049g15051g14967g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036
g16997g17079g17062g17028g14982g17078g14982g17040g16994g16991g17012g17040g17062 g14982g16946g14982g17139g17136g14982g3261g14982g16938g14982g3655g16912g14982g2564g16911g16974g14982g16938g16922g16970g16905g17134g17129
g5328g16972g14982g16946g14982g14999g14983g14982g3261g14982g16922g14982g16930g16972g14982g3252g8850g14982g16924g16974g14982g16938g16922g16970g16905g17134g17129
g15018g15036g15045g15051g15036g15045g15034g15036g14967g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036
g15026g15014g15052g15049g15052g15035g15046 g15037g15036g15040g15050g15052g15037g15052g15049g15052 g15054g15032 g15050g15032g15045g15041g15052g15047 g15047g15052g15045 g15035g15036g14967g15037g15052g15042g15040 g15032g15038g15032g15049g15052 g15035g15036g15050g15039g15046 g14981g15028
g15026g15010g15032g15049g15036 g15054g15032 g14999g14983g14967g15047g15052g15045 g15050g15039g15040g14967g15051g15032g15049g15032 g15050g15039g15052g15051g15047g15032g15051g15050g15052 g15050g15052g15049g15052 g15035g15036g15050g15039g15046 g14981g15028
Figure 4: Example of the acquisition of a part
translation rule using the sentence translation
rule.
The details of the process of acquisition of
sentence translation rules are as follows:
(1)Thesystemselectstheparttranslationrules
in which the source parts are included in
theSLsentencesofthetranslationexample
or in the source parts of sentence transla-
tionrules, andinwhichthetargetpartsare
included in the TL sentences of the trans-
lation examples or in the target parts of
sentence translation rules.
(2)The system acquires new sentence transla-
tion rules by replacing the parts which are
same as the part translation rules with the
variablestothetranslationexamplesorthe
sentence translation rules.
(3)The system gives the correct and erroneous
frequencies of the part translation rules to
the acquired sentence translation rules.
2
Italics are the pronunciation in Japanese.
Figure 5 shows examples of the acquisition
of the sentence translation rules using the part
translation rules. In Figure 5, the system
acquires�It starts in @0 minutes.�f�/x
/@0/�/ho/y/���/�b}[Sore wa @0 pun
tate ba hajimari masu.]�as a sentence trans-
lation rule by using the part translation rule
(thirty;30[sanju]) acquired in Figure4, and�@1
starts in @0 minutes.�@1/x/@0/�/ho/y/
���/�b}[@1 wa @0 pun tate ba hajimari
masu.]�as the sentence translation rule, that is
more abstracted, is acquired by using the part
translation rule (it;f�[sore]).
g17128g15008g15051g14967g15050g15051g15032g15049g15051g15050g14967g15040g15045g14967g15051g15039g15040g15049g15051g15056 g15044g15040g15045g15052g15051g15036g15050g14981
g15000g15034g15048g15052g15040g15050g15040g15051g15040g15046g15045g14967g15046g15037g14967g15051g15039g15036g14967g15050g15036g15045g15051g15036g15045g15034g15036g14967g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967
g15049g15052g15043g15036g14967g15052g15050g15040g15045g15038g14967g15051g15039g15036g14967g15047g15032g15049g15051g14967g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036
g17128g15051g15039g15040g15049g15051g15056g17147g17139g17136 g15026g15050g15032g15045g15041g15052g15028g17129
g15006g15040g15053g15036g15045g14967g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967 g15036g15055g15032g15044g15047g15043g15036
g15015g15032g15049g15051g14967g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036
g17128g15008g15051g14967g15050g15051g15032g15049g15051g15050g14967g15040g15045g14967g14999g14983g14967g15044g15040g15045g15052g15051g15036g15050g14981
g17147g16928g16975g14982g16946g14982g17139g17136g14982g3261g14982g16930g16937g14982g16947g14982g4494g16961g16973g14982g16961g16924g17134
g17147g16928g16975g14982g16946g14982g14999g14983g14982g3261g14982g16930g16937g14982g16947g14982g4494g16961g16973g14982g16961g16924g17134
g17128g15040g15051g17147g16928g16975g15026g15050g15046g15049g15036g15028g17129g15015g15032g15049g15051g14967g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036
g15017g15036g15034g15052g15049g15050g15040g15053g15036g14967g15000g15034g15048g15052g15040g15050g15040g15051g15040g15046g15045g14967g15046g15037g14967g15051g15039g15036g14967g15050g15036g15045g15051g15036g15045g15034g15036g14967
g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036g14967g15052g15050g15040g15045g15038g14967g15051g15039g15036g14967g15047g15032g15049g15051g14967g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g15049g15052g15043g15036
g17128g14999g14984g14967g15050g15051g15032g15049g15051g15050g14967g15040g15045g14967g14999g14983g14967g15044g15040g15045g15052g15051g15036g15050g14981g17147g14999g14984g14982g16946g14982g14999g14983g14982g3261g14982g16930g16937g14982g16947g14982g4494g16961g16973g14982g16961g16924g17134
g17128g15008g15051g15050g15051g15032g15049g15051g15050g14967g15040g15045g14967g14999g14983g14967g15044g15040g15045g15052g15051g15036g15050g14981 g17147g16928g16975g14982g16946g14982g14999g14983g14982g3261g14982g16930g16937g14982g16947g14982g4494g16961g16973g14982g16961g16924g17134
g15000g15034g15048g15052g15040g15049g15036g15035g14967g15050g15036g15045g15051g15036g15045g15034g15036g14967g14967g15051g15049g15032g15045g15050g15043g15032g15051g15040g15046g15045g14967g14967g15049g15052g15043g15036
g15026g15018g15046g15049g15036g14967g15054g15032 g14999g14983g14967g15047g15052g15045g14967g15051g15032g15051g15036 g15033g15032 g15039g15032g15041g15040g15044g15032g15049g15040 g15044g15032g15050g15052g14981g15028g14976
g15026g15018g15046g15049g15036g14967g15054g15032 g15050g15032g15045g15041g15052g15047 g15047g15052g15045g14967g15051g15032g15051g15036 g15033g15032 g15039g15032g15041g15040g15044g15032g15049g15040 g15044g15032g15050g15052g14981g15028g14976
g15026g14999g14984g14967g15054g15032 g14999g14983g14967g15047g15052g15045g14967g15051g15032g15051g15036 g15033g15032 g15039g15032g15041g15040g15044g15032g15049g15040 g15044g15032g15050g15052g14981g15028g14976
g15026g15018g15046g15049g15036 g15054g15032 g14999g14983g14967g15047g15052g15045g14967g15051g15032g15051g15036 g15033g15032 g15039g15032g15041g15040g15044g15032g15049g15040 g15044g15032g15050g15052g14981g15028g14976
Figure 5: Examples of the acquisition of a sen-
tence translation rule using the part translation
rule.
5 Experiments for performance
evaluation
5.1 Experimental procedure
There are two kinds of data as experimental
data. One is learning data and the other is
evaluation data. In these experiments, 1,759
translationexampleswereusedaslearningdata.
These translation examples were taken from
textbooks(Nihon Kyozai(1), 2001; Nihon Ky-
ozai(2), 2001; Hoyu Shuppan, 2001) for second-
grade junior high school students. As well,
1,097 translation examples were used as eval-
uation data. These translation examples were
taken from textbooks(Bunri, 2001; Sinko Shup-
pan, 2001) for second-grade junior high school
students. Allofthesetranslationexampleswere
processed by the method outlined in Figure 3.
The initial condition of the dictionary is empty.
Moreover,weusedthreeothercommercialRule-
Based MT systems, comparing our system with
those systems. We call these three MT systems
A, B and C respectively.
5.2 Evaluation standards
The correct translation results are grouped into
two categories:
(1) The correct translation
Thismeansthatthetranslationresultscor-
respond to the correct translation results
taken from textbooks respectively(Bunri,
2001; Sinko Shuppan, 2001).
(2) A correct translation which includes un-
known words
This means that the translation results
with substituted nouns or adjectives as
variables correspond to the correct trans-
lation results taken from textbooks respec-
tively(Bunri, 2001; Sinko Shuppan, 2001).
In this paper, the eﬀective translation results
are the translation results that correspond to
(1) and (2), and the ineﬀective translation re-
sults are the translation results that do not cor-
respond to (1) and (2). Moreover, the eﬀec-
tive translation rate is the rate of the eﬀective
translation results in all the evaluation data.
The translation results are ranked when several
translation results are generated. The transla-
tion results using the translation rules whose
rate of correct translation frequency is high, are
ranked at the top. We evaluated the translation
results that are ranked from No.1 to No.3.
5.3 Experimental results and discussion
Table 1 shows examples of eﬀective translation
results in our system with RCL. Table 2 shows
the results of comparative experiments of our
system and the three Rule-Based MT systems.
We excluded 309 SL sentences from 1,097 SL
sentences used as evaluation data in Table 2. In
oursystem, the309SLsentencesbecamethein-
eﬀective translation results because of a lackof
learning data. Therefore, the 309 SL sentences
are not inadequate as evaluation data. Table 2
shows the eﬀective translation rates in 788 SL
sentences, which were left after excluding 309
SL sentences from the 1,097 SL sentences used
as evaluation data. In the other three Rule-
Based MT systems, the same 788 SL sentences
were used as evaluation data and the transla-
tion results which correspond to (1) and (2)
Table 1: Examples of eﬀective translation results.
Examples of the correct translation results
SL sentences TL sentences
This bag was made in France.\w���x����
apb}[Kono baggu wa furansu sei desu.]
We went there to play�h`hjx��b�h�f\��V�`h}
baseball. [Watashi tachi wa yakyu wo suru tame soko e iki mashi ta.]
Examples of the correct translation results which includes the unknown words
SL sentences TL sentences
@0���oMloK[�`�OT�
Shall I take you to the [@0 e tsure te itte age masho ka?]
amusement park?y@0 requires “!�[yuen chi]” which is equivalent for
ythe noun “the amusement park”.
@0T��a�prwX�Mw�mUK��bT�[@0 kara
How far is it from Kyoto to hiroshima made dono kurai no kyori ga ari masu ka?]
Hiroshima?y@0 requires “�N[kyoto]” which is equivalent for
ythe noun “Kyoto”.
described in section 5.2 were evaluated as the
correct translation results. The eﬀective trans-
lation rate in the system with only GA-ILMT
was 45.1%. In Table 2, the eﬀective translation
rate of system with RCL is almost the same as
the eﬀective translation rates of system A, but
is higher than systems B and C.
Table 2: Results of comparative experiments.
Eﬀective trans- Details
System
lation rates (1) (2)
Our system 85.0% 41.6% 58.4%
system A 85.8% 84.0% 16.0%
system B 81.7% 83.7% 16.3%
system C 76.9% 82.7% 17.3%
Table 3: Comparison of eﬀective translation
rates based on quality.
Eﬀective trans- Details
System
lation rates (1) (2)
Our system 73.7% 7.5% 52.5%
system A 70.3% 84.2% 15.8%
system B 63.8% 85.0% 15.0%
system C 58.7% 82.8% 17.2%
Moreover, we evaluated translation results
more strictly in terms of the quality of trans-
lation. Meaning that only translation results
that had almost the same character strings as
the correct translation results taken from the
textbooks(Bunri, 2001; Sinko Shuppan, 2001)
were eﬀective translation results. For exam-
ple, “f�x�10�TT��b[Sore wa yaku
juppun kakari masu.]” is an ineﬀective trans-
lation result because of the correct transla-
tion results for “It takes about ten minutes.”
is “�10�TT��b[Yaku juppun kakari
masu.]” in textbook(Bunri, 2001; Sinko Shup-
pan, 2001). In this Japanese sentence, phrase
“f�x[sore wa]” results in needlessly long.
Therefore, we evaluate the translation results
that have diﬀerent phrases to the correct trans-
lation results as the ineﬀective translation re-
sults in terms of the quality of translation. Ta-
ble3showsacomparisonofeﬀectivetranslation
ratesbasedon quality. InTable3, weconﬁrmed
that the system with RCL can generate more
high-quality translation results than the three
other Rule-Based MT systems.
In the system with RCL, the erroneous trans-
lation rules are also acquiredlike a linked chain.
For example, in Figure 2, the translation rules
B, C and D are acquired as the erroneous trans-
lation rules when the translation rule A is the
erroneous translation rule. Namely, a chain re-
actioncauses theacquisition oferroneous trans-
lation rules. In learning data, the rate of er-
roneous part translation rules to the acquired
part translation rules was 47.9%, and the rate
of erroneous sentence translation rules to the
acquired sentence translation rules was 38.2%.
However, such erroneous translation rules are
automatically decided as being erroneous trans-
lation rules in the feedbackprocess resulting
from the ineﬀective translation results.
6 Conclusion
In existing Example-Based MT systems based
on learning algorithms, similar translationpairs
must exist to acquire high-quality translation
rules. This means that the systems require
large amounts of translation examples to ac-
quire high-quality translation rules. On the
other hand, a system with RCL can acquire
many new translation rules from sparse trans-
lation examples because it uses other already
acquired translation rules based on the learn-
ing algorithms described in section 2. As a re-
sult, the quality of the translation and the ef-
fective translation rate of our system is higher
than other Rule-Based MT systems. However,
our system still does not reach the level of a
practical MT system and requires more transla-
tion rules to realize the goal of a practical MT
system. Although our system is not a practical
enough MT system, the system can eﬀectively
acquire the translation rules from sparse data
by using RCL. Therefore, we consider that the
quality of translation improves only by adding
new translation examples without the diﬃculty
ofRule-BasedMT systemsin which adeveloper
mustcompletelydescribelarge-scaleknowledge.
In the future, we plan to add a mechanism
that eﬀectively combines the acquired transla-
tion rules so that the system realizes the trans-
lation of practical SL sentences.
7 Acknowledgements
This workwas partially supported by the
Grants from the High-Tech Research Cen-
ter of Hokkai-Gakuen University and a Gov-
ernment subsidy for aiding scientiﬁc research
(No.14658097) of the Ministry of Education,
Culture, Sports, Science and Technology of
Japan.

References

Hutchins, W. J and H. L. Somers. 1992. An
Introduction to Machine Translation. ACA-
DEMIC PRESS.

Sato, S and M. Nagao. 1990. Toward Memory-
based Translation. In proceedings of the Col-
ing’90.

Brown, P., J. Cocke, S. Della Pietra, V. J. Della
Pietra, F. Jelinek, J. D. Laﬀerty, R. L. Mer-
cer and P. S. Roossin. 1990. A Statistical
Approach to Machine Translation. Computa-
tional Linguistics Vol.16, No.2.

Watanabe, H and K. Takeda. 1998. A Pattern-
based Machine Translation System Extended
by Example-based Processing. In proceedings
of the Coling-ACL’98.

Brown, R.D. 2001. Transfer-Rule Induction
for Example-Based Translation. In proceed-
ings of the Workshop on EBMT, MT Summit
VIII.

Carl,M. 2001. InducingTranslationGrammars
fromBracketedAlignments. In proceedings of
the Workshop on EBMT, MT Summit VIII.

Malavazos, C and S. Piperidis. 2000. Appli-
cation of Analogical Modelling to Example
BasedMachine Translation. In proceedings of
the Coling2000.

G¨uvenir, H.A and I. Cicekli. 1998. Learning
TranslationTemplatesfromExamples. Infor-
mation Systems Vol.23, No.6.

McTait, K. 2001. Linguistic Knowledge and
Complexity in an EBMT System Based on
Translation Patterns. In proceedings of the
Workshop on EBMT, MT Summit VIII.

Echizen-ya, H., K. Araki, Y. Momouchi and K.
Tochinai. 1996. MachineTranslationMethod
using Inductive Learning with Genetic Algo-
rithms. In proceedings of the Coling’96.

Goldberg, D. E. 1989. Genetic Algorithms in
Search, Optimization,andMachineLearning.
Addison-Wesley.

Araki, K., Y.Momouchi andK. Tochinai. 1995.
Evaluation for Adaptability of Kana-kanji
TranslationofNon-segmentedJapaneseKana
Sentences using Inductive Learning. In pro-
ceedings of the PACLING’95.

Echizen-ya, H., K. Araki, Y. Momouchi and
K. Tochinai. 2000 Eﬀectiveness of Layering
Translation Rules based on Transition Net-
worksinMachineTranslationusingInductive
Learning with Genetic Algorithms. In pro-
ceedings of the MT and Multilingual Applica-
tions in the New Millennium.

Nihon-Kyozai(1). 2001. One World English
Course 1 new edition. Tokyo.

Nihon-Kyozai(2). 2001. One World English
Course 2 new edition. Tokyo.

Hoyu Shuppan. 2001. System English Course 2
new edition. Tokyo.

Bunri. 2001. WorkEnglish Course 2 new edi-
tion. Tokyo.

Sinko Shuppan 2001. Training English Course
2 new edition. Osaka.
