COLING 82, Z Horecl~ (ed. } 
North-Holland Publishing Company 
© Academia, 1982 
MULTI-LEVEL TRANSLATION AIDS IN A 
DISTRIBUTED SYSTEM 
Alan K. Melby 
Linguistics Department 
Brigham Young University 
Provo, Utah 84602 U.S.A. 
At COLING80, we reported on an Interactive Translation System 
called ITS. We will discuss three problems in the design of the 
first version of ITS: (1) human factors, (2) the "all or nothing" 
syndrome, and (3) traditional centralized processing. We will also 
discuss a new version of ITS, which is now being programmed. 
This new version will hopefully overcome these problems by 
placing the translator in control, providing multiple levels of aid, 
and distributing the processlng. 
OVERVIEW 
At COLING80, we reported on an Interactive Translation System ealled ITS. We will 
consider three problems in the first version of ITS: (1) human factors, (2) the 'Wall or 
nothing" syndrome, and (3) traditional centralized processing. 
The first problem (human factors) is the problem of keeping human translators and 
revisors happy. Humans naturally want to feel that they are doing useful, interesting 
work and that they are using the machine instead of it using them. However, the 
first version of ITS forced them to answer many uninteresting questions and to revise 
many sentences they thought should be retranslated. 
The "el! or nothing" syndrome is a name for the attitude that the machine must 
translate every sentence or it is not worth using a machine at all The problem is 
that a system based on this approach is likely to be hard to adjust into a useful form 
if it does not attain the desired level of performance. 
The problem with traditional centralized processing is that it does not provide 
consistent, reliable response time to e~ch user and requires physical proximity or 
high-speed telecommunications. And a eentralized system may be hard to 
decentralize after it has been designed. 
The first version of ITS had all three of the above problems. These problems would 
disappear if we had FAI-IQT (Fully Automatic, High Quality Translation -- Bar- 
llillel,1960). In that case a source text would be presented to the computer, which 
would promptly produce a poIished translation, typeset and ready to be published 
without revision. That would solve the human problems because no human translators 
would be involved. The "all or nothing" question would be irrelevant because we 
would have it all. And centralized processing would not be a problem because there 
would be no interactive processing. This paper assumes that FAllQT of general text is 
not on the visible horizon and proposes a design which answers these problems. 
In the new version of ITS, each translator works at a microcomputer instead of a 
conventional terminal. The microcomputers are part of a distributed network but can 
function without being on-line. The translator uses the microcomputer as a tool for 
getting the translation done and is in control of the translation process. There are 
three levels of aid available to the translator, ranging from simple text processing to 
215 
216 A.K. MELBY 
terminology aids to full machine transtation. All three levels are fully integrated and 
the translator can quickly switch from one level to another even within the 
translation of a single sentence. This means that the translation process can continue 
smoothly regardless of how many sentences fail to receive a full analysis and a good 
machine translation. This in turn means that the actual machine translation 
component can be "pure" in the sense that no compromises need be made to ensure 
some kind of output even on sentences that are not analyzable v~ith the current 
parser and model of language. 
It is hoped that the above design will solve the three problems under discussion. 
Placing the translators in control of the operation of the system should improve their 
attitude. Using multiple levels of aid should overcome the dangers of the "all or 
nothing" approach. And replacing conventional terminals with microcomputers should 
overcome some of the problems of centralized processing. Solving these user-oriented 
problems is important from a theoretical viewpoint because even a research 
translation system desperately needs user feedback from real translators. And real 
translators will not give the needed feedback unless the system is practical and 
user-friendly. 
The rest of the paper will elaborate on each of the three problems and their 
proposed solution in the new version of ITS. 
PROBLEM ONE: HUMAN FACTORS 
Lacking FAHQT, human translators and revisors are still needed in a computerized 
translation system. In ITS version one, translating a text involved asking questions 
about each sentence of the text before the translation of the first sentence appeared. 
When the translated sentences finally did appear, the translator/revisor was expected 
to examine and then revise them as needed but not to retranslate them from the 
source text. After all, this was a human-assisted MACHINE translation system and 
we had already invested considerable interaction time and machine time in the 
translation of each sentence. The translator/revisor was to remove the errors from 
the machine's translation and no more. Understandably, the human translator/revisor 
often felt more like a "garbage collector" than a translator. 
Having an unhappy translator is a serious problem. It should be remedied, if possible, 
for two reasons: (I) We should be concerned for the translator as a person. (2) An 
unhappy translator will fight the system. Consider the following statement by a 
human translator: 
During my years with JPRS . . . I had occasion to do some 
post-editing of machine translations, in addition to my normal 
assignments .... Monetary considerations aside, the work was 
odious. To post-edit, a conscientious translator had to literally 
retranslate every sentence in the original, compare it word for 
word with the clumsy machine attempts, and' then laboriously 
print in corrections between the lines of the printout. It would 
have been much faster--and less tedious--just to translate "from 
scratch" and dictate the translation on tape, as I normally do. 
And I am sure the product would have been better. It was thus 
my impression that post-editing of machine translations is 
translation work at coolie wages. I can't imagine anyone wanting 
to do it unless the alternative was starvation. (Silverstein,1981) 
Seppanen (1979) claims that relatively little attention has been paid to the pragmatic 
aspects of man/machine dialogues. He claims that human factors in man/machine 
interfaces have not attracted the interest of either computer scientists or 
psychologists. Perhaps, then, human factors in computerized translation systems are 
an appropriate area of interest for computational linguists, and this view seems to be 
MULTI-LEVEL TRANSLATION AIDS IN A DISTRIBUTED SYSTEM 217 
gaining momentum from within the field. Researchers at the Grenoble project have 
concluded: 
The human and social aspects should not be neglected. To force 
a rigid system on revisors and translators is a guarantee of 
failure. It must be realized that AT (Automatized Translation) 
can only be introduced step by step into some preexisting 
organizational structure. The translators and revisors of the EC 
did not only reject Systran because of its poor quality but also 
because they felt themselves becoming "slaves of the machine", 
and condemned to a repetitive and frustrating kind of work. 
(Boitet et ai,1980) 
Our answer to the problem of human factors is to place the translator in control. 
The translator uses human judgment to decide when to post-edit and when to 
translate. Nothing is forced upon the translator. This approach is strongly argued 
for by Kay (1980) when he states: "The kind of translation device I am proposing will 
always be under the tight control of a human translator". And Lippman (1977) 
describes a successful terminology aids experiment in Mannheim and concludes: "The 
fact that quality was improved, rather than degraded as in the ease of MT, appears 
to support the soundness of an approach where the translator retains full control of 
the translation process." 
PROBLEM TWO: THE "ALL OR NOTHING s' SYNDROME 
Originally, FAHQT was the only goal of research in machine translation. Until 
recently, there seemed to be a widely shared assumption that the only excuse for the 
inclusion of a human translator in a machine translation system was as a temporary, 
unwanted appendage to be eliminated as soon as research progressed a little further. 
This "all or nothing" syndrome drove early machine translation researchers to aim for 
FAHQT or nothing at all. It is now quite respectable in computational linguistics to 
develop a computer system which is a TOOL used by a human expert to access 
information helpful in arriving at a diagnosis or other conclusion. Perhaps, then, it is 
time to entertain the possibility that it is also respectable to develop a machine 
'-anslation system which includes sophisticated linguistic processing yet is designed to 
used as a tool for the human translator. 
h you expect each sentence of the final translation to be a straight machine 
translation or at worst a slight revision of a machine translated sentence, then you 
are setting yourself up for a fall. Remember Brinkmann's conclusion that "the 
post-editing effort required to provide texts having a correctness rate of 75 or even 
80 percent with the corrections necessary to reach an acceptable standard of quality 
is unjustifiable as far as expenditure of money and manpower is concerned" 
(Brinkmann,1980). Thus, a strict post-edit approach must be nearly perfect or it is 
almost useless. Many projects start out with high goals, assuming that post-editing 
can surely rescue them if their original goals are not achieved. Even post-editing may 
not make the system viable. 
The proposed solution to this problem is to anticipate from the beginning that not 
every sentence of every text will be translated by computer and find its way to the 
target text with little or no revision. Then an effort can be made from the 
beginning to provide for a smooth integration of human and machine translations. ITS 
version two will have three integrated levels of aid under the control of the 
translator. We will now describe the three levels of translator aids. 
Level one translator aids can be used immediately even without the source text being 
in machine-readable form. In other words, the translator can sit down with a source 
text on paper and begin translating much as if at a typewriter. Level one includes a 
text processor with integrated terminology aids. For familiar terms that recur there 
218 A.K. MELBY 
is a monolingual expansion code table which allows the user to insert user-defined 
abbreviations in the text and let the machine expand them. This feature is akin to 
the "macro" capability on sortie word processors. The key can be several characters 
long instead of a single control character, so the number of expansion codes available 
is limited principally by the desire of the translator. Level one also provides access 
to a bilingual terminology data bank. There is a term file in the microcomputer 
itself under the control of the individual translator. The translator also has access to 
a larger, shared term bank (through telecommunications or local network). Level one 
is similar to a translator aid being developed by Leland Wright, chairman of the 
Terminology Committee of the American Translator's Association. Ideally, the 
translator would also have access to a data base of texts (both original and 
translated) which may be useful as research tools. 
Level two translator aids require the source text to be in machine-readable form. 
Ineluded in level two are utilities to process the source text according to the desires 
of the translator. For example, the translator may ran aceross an unusual term and 
request a list of all occurrences of that term in that text. Level two also includes a 
"suggestion box" option (Melby,1981) which the translator can invoke. This feature 
causes each word of the current text segment to be automatieally looked up in the 
term file and displays any matches in a field of the screen called the suggestion box. 
If the translator opts to use the suggested translation of a term, a keystroke or two 
will insert it into the text at the point specified by the translator. If the translator 
desires, a morphological routine can be activated to inflect the term according to 
evidence available in the source and target segments. 
Level three translator aids integrate the translator work station with a full-blown MT 
system. The MT component can be any machine translation system that includes a 
self-evaluation metric. The system uses that metric to asssign to each of the 
translated sentences a quality rating (e.g. "A" means probable human quality, "B" 
means some uncertainty about parsing or semantic choices made, "C" means probable 
flaw, and "D" is severely deficient). On any segment, the translator may request to 
see the machine translation of that segment. If it looks good, the translator can pull 
it down into the work area, revise it as needed, and thus incorporate it into the 
translation being produced by the translator. Or the translator may request to see 
only those sentences that have a rating above a specified threshold (e.g. above "C"). 
Of course, the translator is NEVER obliged to use the machine translation unless the 
translator feels it is more efficient to use it than to translate manually. No pressure 
is needed other than the pressure to produce rapid, high--quality translations. If using 
the machine translations make the translation process go faster and better, then the 
translator will naturally use them. 
The successful METEO system by TAUM (Montreal) expresses the essence of this 
approach. All sentences go into the MT system. The system evaluates its own 
output and accepts about 80 percent of the sentences. Those sentences are used 
without post--editing. The other 20 percent are translated by a human and integrated 
into the machine-translated sentences. This application differs from ours in that 
human translators do not see any machine translations at all--goed or bad. But the 
basic level three approach is there. 
One positive aspect of this three level approach is that while level three is 
dramatically more complex linguistically and computationaliy than level two, level 
three appears to the translator to be very similar to level two. Level two presents 
key terms in the sentence; level three presents whole sentences. When good level 
three segments are available, it can speed up the translation considerably but their 
absence does not stop the translation process. Thus, a multi-level system can be put 
into production much sooner than a conventional post-edit system. And the sooner a 
system is put into production, the sooner useful feedback is obtained from the users. 
MULTI-LEVEL TRANSLATION AIDS IN A DISTRIBUTED SYSTEM 219 
The multi-level approach is designed to please (a) the sponsors (because the system .is 
useful early in the project and becomes more useful with time), (b) the users (because 
they are in control and choose the level of aid), and (c) the linguists and 
programmers (because they are not pressured to make compromises just to get 
automatic translation on every sentence). 
PROBLEM THREE: TRADITIONAL CENTRALIZED PROCESSING 
Machine translation began in the 1950's when the cost of a CPU prohibited the 
thought of distributed processing in which each user has a personal CPU. Interactive 
time-shared computing (where each user has a dumb terminal connected to a shared 
CPU) can give the impression that each user has a personal computer--so long as the 
system is not loaded down. Unfortunately, systems tend to get loaded down. Highly 
interactive work such as word processing is not suited to an environment where 
keystroke response times vary. Also, centralized processing requires either physical 
proximity to the main CPU or telecommunications lines. High speed 
telecommunications can be vary costly, and low speed telecommunications are not 
user-fr!endly. A costly solution is to obtain a dedicated mainframe and never load it 
down. A more cost-effective solution in terms of today's computer systems is a 
distributed system in which each translator has a microcomputer tied into a loose 
network to share resources such as large dictionaries. 
The individual translator work station would be a microcomputer with approximately 
256K of main memory, dual diskette drives, CRT, keyboard, small printer, and 
communications port. Such systems are available at relatively low cost (under 5 000 
U.S. dollars). Additional storage for term files and text files can be obtained at 
reasonable cost by adding a Winchester-type disk. If several translators are in the 
same building, a local network can be set up to share terminology and document data 
bases and even inter-translator messages. The capabilities of the work station would 
include rapid, responsive word processing and access to internal dictionaries and to 
shared translator data bases (i.e. level one and level two processing). The internal 
dictionaries would include an expansion file and a terminology file under the control 
of the translator. Of course, the translator could load internal files appropriate to 
t'~. subject matter of the document by inserting the appropriate diskettes. Access to 
s, .rce texts, document-specific dictionaries, and level three machine translations 
c~ I be granted through a local network, a telecommunications network, or through 
the mails on diskette. Ideally, part of the machine translation would be done on the 
translator work station in order to allow the translator to repair level three 
dictionary problems before they cause rep.eated errors throughout a text. A minimal 
capability m the work statlon would be a translator defined replacement table to 
correct some improper word choices that cause repeated errors in the machine 
translated sentences. Ultimately, microcomputers will be powerful enough to allow 
source text to be presented to a work station which contains full level three 
software. In the meantime, the raw machine translation part of level three can be 
done remotely on any suitable mainframe and then transmitted to a microcomputer 
translator work station for integration into the translation process as level three aids. 
CONCLUSION 
The system described is not, of course, entirely original. It draws on ideas from 
University colleagues and others such as Kay, Boitet, Lippman, Andreyewski, Wright, 
and Brinkmann. But it does represent an important ~hift in direction from past years 
of research on ITS at Brigham Young University . It is an integration of a 
machine-translation system and a terminology aid system, with the final translated 
text being produced on a microcomputer in a distributed network. 
220 AX. MELBY 
The author's major motivations for pursuing this system are to provide a useful 
translator aids system and to create an appropriate vehicle for machine translation 
research. Fortunately, given the framework of this paper, those two goals are 
Compatible. A significant additional advantage is that the usefulness of the translator 
aids component (levels one and two) will facilitate obtaining serious user feedback 
during the development of the machine translation component (level three). 
1There are three groups doing work on machine-assisted translation in Prove, Utah, 
U.S.A. Two are commercial endeavors (Weidner and ALPS), and the third, the one 
described in this paper, is an academic research project at Brigham Young University. 
All three groups include researchers who participated in the development of ITS 
version one, yet a11 three are independent organizations. 

REFERENCES 

(1) Andreyewski , Alexander, Translation: Aids, Robots, and Automation, META 
Vol. 26, No. 1 (March 1981) 57-66. 

(2) Bar-Hillel, J., The Present Status of Automatic Translation of Languages, 
Advananees in Computers, Vol. 1 (Academic Press, New York, 1960) 158. 

(3) Baudot, Jean, Andre Clas, and Irene Gross, Un modele de mini-banque de 
terminologie bilingue, META, eel 26, No. 4 (1981) 315-331. 

(4) Boitet, Ch., P. Chatelin, P. Daun Fraga, Present and Future Paradigms in the 
Automatized Translation of Natural Languages, in: COLINGS0 (Tokyo, 1980). 

(5) Brinkmann, Karl-Heinz, Terminology Data Banks as a Basis for High-Quality 
Translation, in: COLING80 (Tokyo, 1980). 

(6) Kay, Martin, The Proper Place of Men and Machines in Language Translation, 
Xerox Pale Alto Research Center Report (October 1980). 

(7) Lippman, Erhardt, Computer Aids for the Human Translator, Report presented at 
the VIII World Congress of FIT, Montreal (1977). 

(8) Melby, Alan K., Melvin R. Smith, and Jill Peterson, ITS: Interactive Translation 
System, in: COLINGS0 (Tokyo, 1980). 

(9) Melby, Alan K., Linguistics and Maehine Translation, in: James Copeland and 
Philip Davis (eds.), The Seventh LACUS Forum 1980 (Hornbeam Press, Columbia, 
SC, 1981). 

(10) Melby, Alan K., A Suggestion Box Translator Aid, in: Proceedings of the annual 
symposium of the Deseret Language and Linguistic Society, (Brigham Young 
University, Prove, Utah, 1981). 

(11) 8eppunan, Jouko, Pragmatic Aspects of Man/Computer Dialogues, in: Helsinki 
University of Technology Computer Center, Research Report No. 12 (1979). 

(12) Silverstein, Virginia, Letter to the editor, ATA Clroniele (November 1991)
