Lifetime Achievement Award

Translating Today into Tomorrow

Sheng Li
Harbin Institute of Technology

Good afternoon, ladies and gentlemen. I am standing here, grateful, excited, and proud.
I see so many friends, my colleagues, students, and many more researchers in this room.
I see that the work we started 50 years ago is now ﬂourishing and is embedded in
people’s everyday lives. I see for the ﬁrst time that the ACL conference is held here
in Beijing, China. And I am deeply honored to be awarded the Lifetime Achievement
Award of 2015.

I want to thank the ACL for giving me the Lifetime Achievement Award of 2015. Es ist
the appreciation of not only my work, but also of the work that my fellow researchers,
my colleagues, and my students have done through all these years. It is an honor for
all of us. As a veteran of NLP research, I am fortunate to witness and be a part of its
long yet inspiring journey in China. So today, to everyone here, my friends, colleagues,
and students, either well-known scientists or young researchers: I’d like to share my
experience and thoughts with you.

1. Early Machine Translation in China

The history of machine translation (MT) in China dates back to 1956. At that time the
new country had immense construction projects to recover what had been ruined in
the war. Jedoch, the government precisely recognized the signiﬁcance of machine
Übersetzung, and started to explore this area, as the fourth country following the United
Zustände, das Vereinigte Königreich, and the Soviet Union. In 1959, Russian–Chinese machine
translation was demonstrated on a Type-104 general-purpose computer made in China.
This ﬁrst MT system had a dictionary of 2,030 entries, Und 29 groups of rules for
lexical analysis. Programmed by machine instructions, the system was able to translate
nine different types of sentences. It used punched tape as the input, and the output
was a special kind of code for Chinese characters, since there was no Chinese char-
acter output device at the time. As the pioneer in Chinese MT, the system touched
the issues of word sense disambiguation, word reordering, and proposed the idea of
predicate-focused sentence analysis and pivot language for multilingual translation.
In the same year, machine translation research at the Harbin Institute of Technol-
Ogy (HIT) was started by Prof. Zhen Wang (and later Prof. Kaizhu Wang), focusing
on the Russian–Chinese MT group. The pursuit for MT has never halted after these
forerunners.

doi:10.1162/COLI a 00240

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
/
C
Ö

l
ich
/

A
R
T
ich
C
e
–
P
D

F
/

4
1
4
7
0
9
1
8
0
7
1
3
1
/
C
Ö

l
ich

_
A
_
0
0
2
4
0
P
D

B
j
G
u
e
S
T

Ö
N
0
8
S
e
P
e
M
B
e
R
2
0
2
3

Computerlinguistik

Volumen 41, Nummer 4

2. The CEMT Series

In 1960, I was admitted to HIT. Five years later, I graduated and became a faculty
member in the computer department of HIT, which was probably the ﬁrst computer
discipline among Chinese universities. I started my research, Jedoch, not from ma-
chine translation but from information retrieval (IR). I was fully occupied by how to
effectively store books and documents on computers, and then retrieve them quickly
and accurately. The start of my research in MT was incidentally caused by IR problems.
Damals, Ming Zhou was my Ph.D. student. He is now the principal researcher
of Natural Language Computing at Microsoft Research Asia (MSRA), and many of
you may be acquainted with him. In 1985, at the beginning of his graduate study, Er
was aiming to address the topic of word extraction for Chinese documents to boost IR
Leistung. For an exhaustive survey, Ming went to Beijing from Harbin alone, Und
buried himself at the National Library for over a month. He came back disappointed,
ﬁnding that the related work was some language-dependent solutions for English.
Eigentlich, many research directions encountered this problem at that time. That’s why
Ming and I decided to develop an MT system through which we could ﬁrst translate
Chinese materials into English, so as to take advantage of the solutions proposed for
English, and ﬁnally translate the results back into Chinese, if necessary.

In those years, the translation from Chinese to other foreign languages was less
studied in China. Everything was hard in the beginning. We had to build everything
from scratch, such as collecting and inputting each entry of the translation dictionary.
Glücklicherweise, we were not alone. I came to know many peer scholars, including Prof.
Weitian Wu, Zhiwei Feng, Prof. Zhendong Dong, Prof. Shiwen Yu, and Prof. Changning
Huang, as well as Dr. Zhaoxiong Chen. Although we didn’t work together, we could
always learn from each other and inspire each other in MT research.

After three years’ effort, we accomplished a rule-based MT system named CEMT-I
(Li et al. 1988). It ran on an IBM PC XT1 and was capable of translating eight kinds
of Chinese sentence patterns with fewer than one thousand rules. It had a dictionary
von 30,000 Chinese-English entries. Simple or even crude as it now seems, it really
encouraged every member of our team. After that, we developed CEMT-II (Zhou et al.
1990) and CEMT-III (Zhao, Li, and Zhang 1995) successively. The CEMT series seemed
to have a special kind of magic. Almost all the students who participated in these
projects devoted themselves to machine translation in their following careers, einschließlich
Ming Zhou, Min Zhang, and Tiejun Zhao.

3. DEAR and BT863

Inspired by the success of the CEMT series, we also developed a computer-aided
translation system called “DEAR.” DEAR was put to market via a software chain store.
Although it did not sell much, it was our ﬁrst effort to commercialize the MT technology.
I still remember how excited I was when I saw DEAR placed on the shelves for the ﬁrst
Zeit. Heute, it still reminds me that research work cannot just stay in the lab.

Also in the 1980s, China’s NLP ﬁeld was marked by a milestone event: the establish-
ment of the Chinese Information Processing Society of China (CIPS). From then on, NLP
researchers throughout the country have been connected and the academic exchange
has been facilitated at the national scale. It was far beyond my imagination then that,

1 https://en.wikipedia.org/wiki/IBM_Personal_Computer_XT.

710

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
/
C
Ö

l
ich
/

A
R
T
ich
C
e
–
P
D

F
/

4
1
4
7
0
9
1
8
0
7
1
3
1
/
C
Ö

l
ich

_
A
_
0
0
2
4
0
P
D

B
j
G
u
e
S
T

Ö
N
0
8
S
e
P
e
M
B
e
R
2
0
2
3

Translating Today into Tomorrow

thirty years later, I would have the honor to be the president of this society, leading
it to keep on contributing to the development of world-level NLP technology.

I usually regard the series of MT systems that we developed as a large family. In
1994, BT863 joined this family with some new features (Zhao, Li, and Wang 1995; Wang
et al. 1997). Erste, BT863 was distinguished as a bi-direction translation between Chinese
and English under a uniform architecture. Zweite, in addition to the rules, es war
augmented with examples and templates learned from a corpus. Endlich, this system
is remembered for its top performance in the early national MT evaluation organized
by the 863 High Tech Program of China.

4. Syntactic and Semantic Parsing

Time passed quickly. The rising of the Internet made communication more convenient,
and our research was gradually connected with international peers. We concentrated
on the mining and accumulation of bilingual and multilingual corpora. We explored
how to integrate rule-based and example-based MT models under a unifying statistical
Rahmen. Jedoch, as more and more work was conducted, I found it more difﬁcult
to go deeper. I began to realize that translation problems cannot rely only on translation
Methoden.

From word segmentation, morphology, word meaning, to named entity, syntax, Und
semantics, every step in this procedure affects the quality of translation. I remember an
interesting story. One day, my student Wanxiang Che input his name into our machine
translation system. The system literally translated his name into ‘thousands of cars
ﬂying in the sky’. This was rated as the joke of the year in my lab, but the underlying
problem is worth pondering.

Traditional Chinese medicine advocates the treatment of both symptoms and root
causes. The same principle applies to MT research, in which models for word alignment,
decoding, reordering, und so weiter, can solve the surface problems of machine transla-
tion, whereas understanding the word sense, sentence structure, and semantics is the
solution to the fundamental problems. We therefore carried out research on syntactic
Analyse, including phrase-structure parsing and dependency parsing.

In those days, dependency parsing on Chinese was not widely studied. There was
no well-accepted annotation or transformed standard. daher, we referred to a large
number of linguistic studies, developed a Chinese syntactic dependency annotation
standard, and annotated a 50,000-sentence Chinese syntactic dependency treebank on
this basis. This is the largest Chinese dependency treebank available. Differently from
those transformed from phrase-structure treebanks, our dependency structure uses
native dependency structure, which can handle a large number of speciﬁc grammatical
phenomena in dependency structures. This treebank has been released by the Linguistic
Data Consortium (LDC) (Che, Li, and Liu 2012). We hope that more researchers can
beneﬁt from it.

Based on syntactic parsing, we hoped to further explore the semantic structure
and the relationship of sentences. daher, we carried out research on semantic role
labeling, and worked on the semantic role labeling methods based on the tree kernel,
including the hybrid convolution tree kernel (Che et al. 2008) and the grammar-driven
tree kernel (Zhang et al. 2007). Zusätzlich, we further broadened our mind and tried to
analyze the semantics of Chinese directly. We proposed semantic dependency parsing
tasks that directly establish semantic-level dependencies between content words, ignor-
ing auxiliaries and prepositions. In der Zwischenzeit, we violated the tree structure constraints,
allowing one word to depend on more than one parent node, so as to form semantic

711

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
/
C
Ö

l
ich
/

A
R
T
ich
C
e
–
P
D

F
/

4
1
4
7
0
9
1
8
0
7
1
3
1
/
C
Ö

l
ich

_
A
_
0
0
2
4
0
P
D

B
j
G
u
e
S
T

Ö
N
0
8
S
e
P
e
M
B
e
R
2
0
2
3

Computerlinguistik

Volumen 41, Nummer 4

Figur 1
Example of syntactic dependency parsing, semantic role labeling, and semantic dependency
parsing in LTP-Cloud.

dependency graph structures. At this point, the semantic dependency treebank that we
have already labeled has reached more than 30,000 Sätze. Much ongoing research
is based on these data. Figur 1 shows an example of syntactic dependency parsing,
semantic role labeling, and semantic dependency parsing for an input sentence “现在 /
她 / 脸色 / 难看 / ， / 好像 / 病了 / 。 [Now she looks terrible, seems to be sick]” .

5. LTP and LTP-Cloud

Every summer, HIT and MSRA would jointly organize a summer school for NLP
research students. We invited domestic and foreign experts to give lectures to Chinese
students engaged in this ﬁeld. Because the summer school was free, students from
all over the country came together every year, listening to lectures and conducting
experiments. When I communicated with these students, I found that many of them
came from labs that lacked fundamental NLP tools, such as word segmentors, Teil-
of-speech taggers, and syntactic parsers. It would have been very difﬁcult for them to
implement their research ideas without these tools. I felt bad when I saw that. Sie sind
all students with dreams and innovative ideas. We must create a level playing ﬁeld for
alle, I thought.

After coming back from the summer school, I met Ting Liu. He is a strong supporter
of the idea of sharing. We decided to release an open-source NLP system: Language
Technology Platform (LTP). This platform integrates several Chinese NLP basic tech-
nologies, including Chinese word segmentation, part-of-speech tagging, named entity
recognition, dependency parsing, and semantic role labeling, which has made great
contributions to the development of further applications.

In den vergangenen Jahren, we realized that cloud computing and the mobile Internet have
brought great opportunities and challenges to the NLP ﬁeld. daher, we developed

712

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
/
C
Ö

l
ich
/

A
R
T
ich
C
e
–
P
D

F
/

4
1
4
7
0
9
1
8
0
7
1
3
1
/
C
Ö

l
ich

_
A
_
0
0
2
4
0
P
D

B
j
G
u
e
S
T

Ö
N
0
8
S
e
P
e
M
B
e
R
2
0
2
3

Translating Today into Tomorrow

LTP-cloud2 in 2013, which provides accurate and fast NLP service via the Internet.
Currently, the number of LTP-cloud registered users has exceeded 3,000, and most of
them are NLP beginners. As I had wished, they no longer need to build an NLP basic
processing system from scratch for their research. Every time I see the thank-you notes
to the LTP and LTP-cloud in the acknowledgments of their papers, I am proud and
grateful.

6. Machine Translation on the Internet

As more and more papers were published in top conferences and journals, our lab
made a name in the academic world. Many people in the lab were satisﬁed, but I felt
differently, since publishing papers should not be the major objective for research. Neu
models and techniques should be applied to solve real-world problems and improve
people’s daily lives. Particularly since we have moved into the era of the Internet. Viele
new concepts and ideas have come into being, such as big data and cloud computing. In
such a new era, machine translation research should no longer be restricted to the labs,
running experiments on a small parallel corpus. Stattdessen, it should embrace the Internet,
and embrace big data. We paid great attention to the cooperation with IT and Internet
Firmen. We established a joint lab with MSRA right after it was founded. Nach
Das, we have also established joint labs with other companies, like IBM, Baidu, Und
Tencent.

My student Haifeng Wang is the vice president of Baidu. He is in charge of NLP
research and development, as well as Web search. We decided to collaborate in MT
shortly after he joined Baidu, since Baidu can provide a huge platform for us to verify
our ideas. Together with Tsinghua University, Zhejiang University, the Institute of Com-
puting Technology, and the Institute of Automation of the Chinese Academy of Science,
we successfully applied for an 863 project titled “Machine Translation on the Internet.”
All the members participating in this project have great passion for MT technologies
and products.

Chinese people accept the principle that “取之于民，用之于民” [what is taken
from the people should be used for the interests of the people]. Internet-based machine
translation also follows this principle, which mines a large volume of translation data
from the Internet, trains the translation model, and then provides high-quality services
for Internet users. In our online translation system, taking Chinese–English translation,
Zum Beispiel, there are hundreds of millions of parallel data for this language pair, welche
were ﬁltered from billions of raw parallel data. We collected a large amount of data from
hundreds of billions of Web pages. So I should say our MT service is actually built upon
the whole Internet.

We have designed various mining models for these heterogeneous Internet data
sources, including bilingual parallel pages, bilingual comparable pages, Web pages
containing aligned sentence pairs, as well as plain texts containing entity and termi-
nology translations. The mined translation data are ﬁltered and reﬁned. We set different
updating frequencies for different Web sites, so as to guarantee that the latest data can be
enthalten. I often observe the mined translation data by myself, and I can ﬁnd plenty of
wonderful translations generated by ordinary Internet users. Their wisdom is perfectly
integrated into the translation system. Jedoch, how to make use of such a big corpus?

2 http://www.ltp-cloud.com/demo/.

713

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
/
C
Ö

l
ich
/

A
R
T
ich
C
e
–
P
D

F
/

4
1
4
7
0
9
1
8
0
7
1
3
1
/
C
Ö

l
ich

_
A
_
0
0
2
4
0
P
D

B
j
G
u
e
S
T

Ö
N
0
8
S
e
P
e
M
B
e
R
2
0
2
3

Computerlinguistik

Volumen 41, Nummer 4

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
/
C
Ö

l
ich
/

A
R
T
ich
C
e
–
P
D

F
/

4
1
4
7
0
9
1
8
0
7
1
3
1
/
C
Ö

Figur 2
Examples of the Baidu online machine translation service.

This is a sweet annoyance. To handle big data, we have developed fast training and
parallel decoding techniques in our project.

With such big data and frequent updates, even Internet buzzwords can be correctly
übersetzt. My students often post the so-called “magic translation” on microblogs.
After the machine translation service came online, I began to realize that it would not
only inﬂuence those Ph.D. students who are reading and writing research papers, oder
those businessmen who are studying materials from foreign countries. It also makes a
huge difference to ordinary people’s lives. Figur 2 shows some examples of Chinese–
English machine translation from the Baidu online translation service,3 which integrates
the research work of the 863 project “Machine Translation on the Internet.”

I once met a 50-year-old Chinese lady on a ﬂight to Japan. She could not speak
Japanese, but she had ﬁnally decided to marry her Japanese husband, with whom she
had chatted online using machine translation. Another story comes from my neighbors,
who are a couple my age. Their children have lived in Germany for years. Der Erste

l
ich

_
A
_
0
0
2
4
0
P
D

B
j
G
u
e
S
T

Ö
N
0
8
S
e
P
e
M
B
e
R
2
0
2
3

3 http://fanyi.baidu.com/.

714

Translating Today into Tomorrow

Figur 3
Integration of MT models.

time the old couple met their grandson when their family came back to China, Sie
were thrilled. Jedoch, on meeting their grandson, who can only speak German, Sie
had no way to express their love, which made them sad. The grandma blamed herself
and even wept when she was alone. With my recommendation, they started to use the
online speech translation app in their smart phone. Jetzt, they can ﬁnally talk to their
grandson.

7. Integration of MT Models

I have been working in machine translation for several decades, going through almost
all the streams of technologies, from rule-based MT (RBMT) models at the very begin-
ning, example-based MT (EBMT) Methoden, to statistical MT (SMT) Methoden, sowie
the research hotspot today—neural network machine translation (NMT). Eigentlich, Wir
tried the neural network–based models in NLP tasks, such as dialogue act analysis and
word sense disambiguation, mehr als 15 years ago (Wang, Gao, and Li 1999a, 1999B).
It is big data and computing power today that help neural network–based models
signiﬁcantly outperform traditional ones. I know that every method has its advantages
and disadvantages. Although the new model and its methodology surpasses the old
ones overall, it does not mean that the old methods are useless. There’s an old saying
in Chinese, “the silly bear keeps picking corn,” which describes that when a bear is
stealing corn from a peasant’s ﬁeld, it would always throw away the old one in its hand
when it picked a new one; the silly bear would always end up with only one corn in
his hand. I hoped that my team and I wouldn’t become the “silly bears.” Therefore,
when we decided to develop an Internet MT system, we all agreed on the idea that we
needed a hybrid approach, with which we could integrate all translation models and
subsystems, on each of which we have all spent great effort. It is just like an orchestra,
in which all instruments, such as piano, violin, cello, trumpet, und so weiter, are arranged
perfectly together. Only in this way can the orchestra present a wonderful perfor-
Mance. As shown in Figure 3, in our MT system today, different models work together
perfectly.

The rule-based method is used to translate expressions like date, Zeit, and num-
ber. The example-based method is applied to translate buzzwords, especially the new
emerging Internet expressions. Andererseits, those complicated long sentences
are translated using the syntax-based statistical model, while those sentences that can
be covered by a predeﬁned vocabulary are translated with an NMT model. Endlich, Die

715

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
/
C
Ö

l
ich
/

A
R
T
ich
C
e
–
P
D

F
/

4
1
4
7
0
9
1
8
0
7
1
3
1
/
C
Ö

l
ich

_
A
_
0
0
2
4
0
P
D

B
j
G
u
e
S
T

Ö
N
0
8
S
e
P
e
M
B
e
R
2
0
2
3

Computerlinguistik

Volumen 41, Nummer 4

sentences left are all translated with a classical SMT model. The conductor of such an
orchestra is a discriminative distributing module, which decides what subsystem an
input sentence should be distributed to, based on a variety of statistical and linguistic
Merkmale.

8. Translation for Resource-Poor Languages

Shortly after the release of Chinese–English and English–Chinese translation services,
we also released translation services between Chinese and Japanese, Koreanisch, and other
daily-used foreign languages. Jedoch, with translation directions expanded, users’
expectations for the translation between the resource-poor languages became higher
and higher. Especially in recent years, China has been doing business more frequently
with many countries, such as Thailand and Portugal, unter anderen, and the destina-
tions for Chinese tourists have become more diverse. One of my friends told me a story
after he came back from a tour in Southeast Asia. He ordered three kinds of salads in
a restaurant, since he did not understand or speak the local language. He could not
communicate with the waiters or even read the menu. These incidents told us that
solving translation problems for these resource-poor languages is urgent. daher, Wir
have successively released translation services between Chinese and over 20 foreign
languages. Jetzt, we have covered languages in eight of the top ten destinations for
Chinese tourists, and all the top ten foreign cities where Chinese tourists spend the
most money.

On this basis, we took a further step. We built translation systems between any two
languages using the pivot approach (Wang, Wu, and Liu 2006; Wu and Wang 2007). Für
resource-poor language pairs, we use English or Chinese as the pivot language. Trans-
lation models are trained for source-pivot and pivot-target, jeweils, which are then
combined to form the translation model from the source to the target language. Using
this model, Baidu online translation services successfully realized pairwise translation
between any two of 27 languages; in Summe, 702 translation directions.

9. MT Methodology for Other Areas

“他山之石，可以攻玉” [Stones from other hills may serve to polish the jade at hand].
This is a Chinese old saying from “《诗经》” [The Book of Songs], which was written
2,500 years ago. It suggests that one may beneﬁt from other people’s opinions and
methods for their task. Machine translation technology is now a “stone from another
hill,” which has been used in many other areas. Zum Beispiel, some researchers recast
paraphrasing as a monolingual translation problem and use MT models to generate
paraphrases of the input sentences (Zhao et al. 2009, 2010). There are also researchers
who regard query reformulation as the translation from the original query to the rewrit-
ten one (Riezler and Liu 2010). Jedoch, what interests me the most is the encounter
between translation technology and Chinese traditional culture. Zum Beispiel, MSRA
uses the translation model to automatically generate couplets (Jiang and Zhou 2008),
which are posted on the doors of every house during Chinese New Year. Baidu applies
translation methods to compose poems. Given a picture and the ﬁrst line of a poem,
the system can generate another three lines of the poem that describe the content of the
picture. Zusätzlich, I have heard recently that both Microsoft and Baidu have released
their chatting robots, which are named Microsoft XiaoIce and Baidu Xiaodu, bzw-
aktiv. They both use translation techniques in the searching and generation of chatting
responses. It is fair to say that machine translation has become more than a speciﬁc

716

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
/
C
Ö

l
ich
/

A
R
T
ich
C
e
–
P
D

F
/

4
1
4
7
0
9
1
8
0
7
1
3
1
/
C
Ö

l
ich

_
A
_
0
0
2
4
0
P
D

B
j
G
u
e
S
T

Ö
N
0
8
S
e
P
e
M
B
e
R
2
0
2
3

Translating Today into Tomorrow

method. Stattdessen, it has evolved into a methodology and could make a contribution to
other similar or related areas.

10. Abschluss

There is an ancient story in China called “愚公移山” [Yugong moves the mountain]. In
the story, an old man called Yugong—meaning an unwise man—lived in a mountain
Bereich. He decided to build a road to the outside world by moving two huge mountains
weg. Other people all thought it was impossible and laughed at him. Jedoch, Yugong
said to the people calmly: “Even if I die, I have children; and my children would have
children in the future. As the mountain wouldn’t grow, we would move the mountain
away eventually.” Today, when facing the ambitious goal of automatic high-quality
maschinelle Übersetzung, and even the whole NLP ﬁeld, I cannot help thinking of Yugong’s
spirit. I have been, and I still am, trying to solve the questions and obstacles along the
Weg. Even if one day I will no longer be able to keep exploring MT, I believe that the
younger generations will keep on going until the dream of making a computer truly
understand languages eventually comes true.

My friends, especially the young ones, to share what I have learned from my career,
I’d like to say: Make yourself a good translation system: Input diligence today, und es
will deﬁnitely translate into an amazing tomorrow!

Verweise
Che, Wanxiang, Zhenghua Li, and Ting Liu.
2012. Chinese dependency treebank 1.0
LDC2012T05. Web Download. Philadelphia:
Linguistic Data Consortium, 2012.
Che, Wanxiang, Min Zhang, AiTi Aw,

ChewLim Tan, Ting Liu, and Sheng Li.
2008. Using a hybrid convolution tree
kernel for semantic role labeling. ACM
Transactions on Asian Language Information
Processing (TALIP), 7(4):13.

Jiang, Long and Ming Zhou. 2008.

Generating Chinese couplets using a
statistical MT approach. In Proceedings of
COLING, pages 377–384, Manchester.

Li, Sheng, Ming Zhou, Miao Shi, and Weitian
Wu. 1988. A Chinese–English machine
translation system: CEMT-I. Journal of the
China Society for Scientiﬁc and Technical
Information, 7(6):409–416.

Riezler, Stefan and Yi Liu. 2010. Query

rewriting using monolingual statistical
maschinelle Übersetzung. Rechnerisch
Linguistik, 36(3):569–582.

Wang, Haifeng, Wen Gao, and Sheng Li.
1999A. Dialog act analysis of spoken
Chinese based on neural networks. Chinese
Journal of Computers, 22(10):1014–1018.
Wang, Haifeng, Wen Gao, and Sheng Li.
1999B. Word sense disambiguation of
spoken Chinese using neural network.
Journal of Software, 10(12):1279–1283.
Wang, Haifeng, Sheng Li, Tiejun Zhao, Yan

Yang, Endong Xun, and Min Zhang. 1997.

The research and implementation of a
bilingual machine translation system
(BT863) for Chinese and English. Zeitschrift für
the China Society for Scientiﬁc and Technical
Information, 16(5):360–369.

Wang, Haifeng, Hua Wu, and Zhanyi Liu.

2006. Word alignment for languages with
scarce resources using bilingual corpora of
other language pairs. In Proceedings of
COLING/ACL, pages 874–881,
Sydney.

Wu, Hua and Haifeng Wang. 2007. Pivot
language approach for phrase-based
statistische maschinelle Übersetzung. In
Proceedings of the ACL, pages 856–863,
Prague.

Zhang, Min, Wanxiang Che, Aiti Aw,

Chew Lim Tan, Guodong Zhou, Ting Liu,
and Sheng Li. 2007. A grammar-driven
convolution tree kernel for semantic role
classiﬁcation. In Proceedings of the ACL,
pages 200–207, Prague.

Zhao, Shiqi, Xiang Lan, Ting Liu, and Sheng
Li. 2009. Application-driven statistical
paraphrase generation. In Proceedings of the
ACL/IJCNLP, pages 834–842, Suntec.

Zhao, Shiqi, Haifeng Wang, Xiang Lan, Und
Ting Liu. 2010. Leveraging multiple MT
engines for paraphrase generation. In
Proceedings of COLING, pages 1326–1334,
Peking.

Zhao, Tiejun, Sheng Li, and Haifeng Wang.
1995. Pattern-based machine translation:
Accomplishment of BT863 system. In

717

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
/
C
Ö

l
ich
/

A
R
T
ich
C
e
–
P
D

F
/

4
1
4
7
0
9
1
8
0
7
1
3
1
/
C
Ö

l
ich

_
A
_
0
0
2
4
0
P
D

B
j
G
u
e
S
T

Ö
N
0
8
S
e
P
e
M
B
e
R
2
0
2
3

Computerlinguistik

Volumen 41, Nummer 4

Proceedings of the NLPPRS, pages 371–376,
Seoul.

Zhao, Tiejun, Sheng Li, and Min Zhang. 1995.

CEMT-III: A fully automatic
Chinese–English MT system. In Proceedings
of International Conference for Chinese
Computing, pages 8–14, Singapur.

Zhou, Ming, Sheng Li, Mingzeng Hu,
and Shi Miao. 1990. An interactive
Chinese–English machine translation
System: CEMT-II. Journal of the
China Society for Scientiﬁc and
Technical Information,
9(2):151–154.

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
/
C
Ö

l
ich
/

A
R
T
ich
C
e
–
P
D

F
/

4
1
4
7
0
9
1
8
0
7
1
3
1
/
C
Ö

l
ich

_
A
_
0
0
2
4
0
P
D

B
j
G
u
e
S
T

Ö
N
0
8
S
e
P
e
M
B
e
R
2
0
2
3

718 Lifetime Achievement Award image

PDF Herunterladen