MACHINE TRANSLATION IN EUROPE 
S. Warwick-Armstrong 
ISSCO 
University of Geneva 
54, Rte. des Acacias 
1227 Geneva, SWITZERLAND 
INTRODUCTION 
Whereas in the United States work in machine translation 
(MT) has only recently been reinstated as a 'respectable' natural 
language processing (NLP) application, it has long been 
considered a worthwhile and interesting topic for research and 
development in both Europe and Japan. In terms of number of 
projects in one sub-field of computational linguistics, MT is 
currently perhaps the most important application. 1 One 
obvious reason for this is simply the daily awareness that 
people communicate in languages other than English, a 
situation that naturally encourages an interest in translation. 
On a practical level, for example, every television cable 
system in Europe broadcasts stations from numerous countries, 
and on the political level, the European Community (EC) is 
committed to protecting the language of each of the Member 
States, which implies providing numerous translation services. 
From an economic viewpoint, every company knows that in 
order to market its products, the documentation must be in the 
language of the target country. And a last motivation for 
interest in MT, which was also the origin of MT activities in 
the US and an important concern for Japan, is the desire for 
better access to information--important documents often exist 
in some foreign language. 
Yet MT in Europe is not viewed as just a matter of 
developing working MT systems for commercial and practical 
needs--it is also accepted as a legitimate topic of research. The 
view of MT as a test bed for NLP work has long been defended 
in the United States (Kay,1980). Reasons why this position 
has only recently gained favor can be attributed to Bar-Hillel's 
strong view on the impossibility of high-quality MT coupled 
with the far-reaching effects the ALPAC report (1966) had on 
funding in the US. All direct funding for translation was 
withdrawn and redirected to more basic research and thus 
linguistics and AI work prospered. Though practical work 
continued, as well as a real need for translation, 2 MT fell into 
disrepute as an academically respectable enterprise. While 
there is consensus that fully automatic high quality MT of 
unrestricted text is impossible, it is nevertheless an attractive 
long-term goal, similar to pursuits in artificial intelligence. In 
Europe, a growing number of researchers in computational 
linguistics regard translation as a challenging field of 
application. Eased on developments in the field such as a more 
rigorous formalization of semantics (e.g., Montague 
At the two most recent Coling conferences, for example, the 
number of papers devoted to issues in MT constituted the largest 
single topic; and this figure does not take into account all the 
general NLP papers presented by the MT projects. 
Ironically, the Georgetown system, on which the ALPAC report 
was based, continued to be used in Europe, until well into the 70s 
and Systran, a direct descendant, is still the most widely used 
commercial MT system. 
grammar), the attention paid to formal and computational 
properties of linguistic theories (e.g., LFG and GPSG) and the 
definition and implementation of linguistically problem- 
oriented computational methods (e.g., unification), it is quite 
natural that attempts are being made to test their adequacy with 
regard to problems of translation. 
The multilingual setting of Europe, where translation is a 
fact of life, along with its varied and decentralized funding 
agencies (including EC, national and regional programs), as 
opposed to the more centralized nature of US federal agencies, 
helps explain why the ALPAC report had less of an impact 
overseas. Machine translation has a long and relatively stable 
tradition in Europe. Similar to the early work with computers 
and language in the United States where CL and MT were 
synonymous, MT projects in Europe have served as a vehicle 
for developing expertise in computational linguistics in 
centers which had little experience in the field. This latter 
point is particularly true in the Eurotra project; Greece, for 
example, had no tradition in computational linguistics. 
The historical and socio-political references have been 
introduced as background material, given the rather strong 
positions taken up by members in and out of the community 
over the last decades. The distinction between research and 
development or theoretical vs. practical, though somewhat 
artificial (and definitely a touchy issue in the community), 
serves as a means of clarifying and motivating what people are 
working on and why. The extreme view repeatedly put forward 
by M. Kay that "all machine translation of natural languages is 
experimental ..." (Kay, 1984:75) is, in my view, correct. There 
are nevertheless things that we can accomplish, albeit 
imperfectly, and from which we can learn both about language 
and about translafion--a situation similar to all NLP work. My 
purpose here is to distinguish major topics currently popular in 
MT work and to identify the projects and centers active in the 
field. 
WHAT IS SPECIFIC TO MACHINE 
TRANSLATION 
Bar-Hillel (1964:212), in one of his numerous papers on 
translation, identified the following five prerequisites for high 
quality human translation: 
(1) competent mastery of the source language, 
(2) competent mastery of the target language, 
(3) good general background knowledge, 
(4) expertness in the field, 
(5) intelligence (know-how). 
28 
For MT, the first four are obviously necessary and 
moreover, remain research topics for NLP in general. The last 
point could simply be replaced by 'the ability to establish a 
correspondence between the source and target language.' For 
humans, it is well-known that bilinguals are not necessarily 
good translators, and discussing intelligence in the context of 
MT (given the lack of any theory of translation and the current 
relatively undeveloped state of the art) would only lead to 
philosophical speculation. Perspectives on combining 
Artificial Intelligence (A.I) and MT can be found in the 
numerous discussions by Wilks (e.g., Wilks, 1973), mentioned 
here in view of his long history in working on this topic both 
in the US and in Europe. 
The major portion of work in any MT project is 
concentrated on points (1) and (2) and hence does not differ 
from any other NLP project except in so far as it involves 
descriptions of two languages. Limiting the application to a 
well defined semantic domain or specific corpus reflects the 
concern for points (3) and (4). One proposal addressing (4) 
explicitly is to include expert system modules in addition to 
linguistic rules (Boitet & Gerber, 1984) or to divide the system 
into expert tasks (Johnson & Whitelock, 1985). In this 
perspective, MT can thus be viewed as a sub-field of NLP which 
in some cases, also means incorporating general AI 
techniques. 
A number of topics specific to MT can be identified, though 
some of them may be shared by a portion of the CL 
community, albeit for different reasons. For example, the 
adequate level(s) of representation, will be determined in MT by 
the ability to express the relevant facts about two natural 
languages and to state the translation relation between them; 
similarly, in a database query system, the concern is to map 
between two representations where one is an abstraction of the 
natural language expression but the other is an expression in a 
formal query language (which has already been def'med). 
Current issues which often figure in the literature and which 
we will look at in somewhat more detail are: 
• bilingual lexicography (describing words and their 
translations) 
• bilingual concordancing (using texts and their 
translations) 
• level(s) of representation (the types of information and 
their notation) 
• transfer mechanisms (mapping between representations) 
• reversibility (of grammars and of the translation 
relation) 
• compositionality (decomposing the problem, giving a 
declarative definition) 
• interlingual representation (abstracting away from 
natural language phenomena) 
This list is by no means exhaustive, but every MT 
researcher will have at least one view on most of these topics. 
Whereas in monolingual lexicography for computational 
applications, progress has been made on at least a subset of the 
basic information necessary, this is not the case in the field of 
bilingual lexicography (Warwick, 1987). In dictionary 
publishing houses (of interest as a starting point for building 
machine tractable dictionaries) bilingual lexicographers are 
seen as the poor cousins, and across any two dictionaries there 
is essentially no consensus on which translations should be 
included nor on how to code them. Each project or product has a 
notation so specific to the system in which it is used, that it is 
of little use to others. It is notable that almost all work on 
using machine readable dictionaries has concentrated on 
monolingual dictionaries, and for the most part only on 
English; the two European languages which have received some 
attention are Italian (by the center in Pisa) and German (by the 
Institute for the German language, IDS, Mannbeim, and the IKP 
at the University of Bonn). 
In light of this situation and given the crucial role that the 
lexicon plays in any system, this topic has been identified as a 
field in its own right. Two European initiatives, EUROTRA-7 
and MULTILEX, are currently underway under the title of 
'reusability of lexical resources' (McNaught, 1990). The 
EUROTRA-7 project (ET-7, 1990) is currently conducting a 
broad survey on what resources are available with a view to 
developing standards for mono-, bi-, and multi-lingual lexical 
descriptions. 3 
Another project arising from work in EUROTRA, is the 
EUROTRA-Lexic project whose aim is to build one bilingual 
dictionary adequate for human and machine needs, involving 
partners from the publishing, private and academic sector 
(Eurotra-Lexic, 1989). MULTILEX is an ESPRIT project whose 
aims are to develop a European multilingual and multifunctional 
lexicon which will be tested in prototypical applications. The 
Acquilex project, also funded under ESPRIT, is another project 
working on standards and a prototype implementation for 
acquiring and coding mono- and bilingual lexical information. 
Bilingual concordancing is a relatively new topic which 
will most likely grow in importance, in parallel with the 
current trend to make use of large corpora. Instead of building 
an MT system based solely on a corpus and its translation, as 
reported on in Brown, et al. (1988), 4 emphasis in Europe has 
been on developing tools to navigate through texts as an aid 
for the linguist or lexicographer working on the problem of 
characterizing the context for the translation of words (cf. 
Picchi & Calzolari, 1986 and Warwick, et al., 1990). In 
Czechoslovakia, at the Charles University, Prague, a project 
has just begun to build a bilingual concordance environment for 
Czech and English as a first step in work on a new machine 
translation project (personal communication). A somewhat 
related project, which plans to make use of structured texts and 
their translations is the BSO Bilingual Knowledge Bank system 
(Sadler & Vendelrnans, 1990). Projects in MT using statistical 
methods are just beginning in a number of centers, but 
information about these activities has not yet reached the 
public domain. 5 
The result of this survey will be made available to the general 
public. Contact: Mr. R. Cenconi, CEC, B410Os, Jean Monnet 
Bldg., 2920 Luxembourg. 
Other European IBM centers may also begin projects with similar 
methods and goals (personal communication). 
Two centers which have reported on such plans are the University 
of Stuttgart where work on alignment of texts, in view of linking 
not only words but also phrases, is planned, and the Rosetta 
project at Philips, which is considering collecting knowledge of 
the world for a separate semantic component by statistical 
methods (personal communication). 
29 
Representation issues have been at the core of machine 
translation since its very beginning. One of the current trends 
is to use existing linguistic theories as the basis for 
translation. One project in Stuttgart has been exploring the use 
of an extended LFG representation as the basis for translation 
(of, Kaplan et al. (1989), also Sadler et al., 1990) whereas a 
project in Berlin, has taken GPSG syntactic representations as 
the starting point for adding additional levels (Busemarm & 
Hauenschild, 1988). 6 
Other examples of basing MT on state of the art CL methods 
and theories include the use of situation schemata as the basis 
for translation Rupp (1989), defining transfer over 'quasi 
logical forms' developed at SRI, Cambridge (Alshawi et al., 
1991) and derivation trees of a Montague style (Landsbergen, 
1987 & Appelo, et al., 1989). The Eurotra MT project bases its 
work on a number of levels essentially corresponding to 
traditional linguistic categories, i.e., morphology, syntax, 
and semantic relations plus a special level for transfer known 
as the interface structure (Arnold, et al., 1985). These are 
explicit levels and a transfer mechanism allows a mapping 
between them (Arnold, 1987, Bech& Nygaard, 1988). 7 
The search for the ideal level of representation for 
expressing a translation relation raises the well known issue of 
transfer vs. interlingua. Almost all projects currently underway 
in Europe essentially rely on two independent levels, one per 
language, with an explicit mapping between the two. One 
exception is the DLT project which uses Esperanto as a pseudo 
interlingua (Witkam, 1988); a choice of representation which 
has "aroused a lot of skepticism" in the community (op cit., 
p.756). The one project theoretically committed to an 
interlingua is the Rosetta system, a project noteworthy for its 
theoretical commitment and steady development over the past 
ten years (Landsbergen, 1989). The work on multilingual 
generation based on conceptual hierarchies in the project 
Polygloss (Emele et al., 1990) may also be considered a type 
of interlingua system. 
A very practical reason for the popularity of the transfer 
model, especially for systems to treat more than one language 
pair, stems from the inherent difficulty of defining a 
representation adequate for more than one natural language, 
especially when the competent people who might work on 
such an interlingua cannot work together in one place (as in the 
Eurotra project which is spread all over Europe). To define an 
interlingua for translation requires expertise in linguistics 
(applied to the languages in question), plus a large range of 
issues often labelled 'extra-linguistic,' knowledge of 
translation (to ensure that a mapping is possible) as well as 
familiarity with formalisms for representing the information 
(as found in much of the work in AI). 
The German government has demonstrated an important 
commitment to the field of MT as well as NLP in the numerous 
projects and positions it has financed. The two projects are 
supported by the government under a program known as Eumtra 
related research projects (Eurotra Begleifforschung). 
The original motivation for separate levels in the monolingual 
portion came in part from practical concerns that for each 
language some progress could be measured (e.g., each language 
had accounted for molphology, syntax, etc.). For the bilingual 
portion, this choice had a theoretical motivation, i.e., transfer as 
the model for translation, and the mechanism for mapping 
between levels was extended to distinct monolingual levels. 
Two topics which have gained importance as a result of 
adopting a transfer model are the formalization of the transfer 
component and the issue of reversibility of grammars (cf. 
Isabelle, 1988). Reversibility of a grammatical description 
ensures that all necessary information has been accounted for 
in the representation for both parsing and generation and also 
defines what the output of ~ansfer from one language to another 
must be. If the representation from analysis is underspecified, 
in a reversible description this will become apparent as 
overgeneration. For translation, the notion of reversibility 
helps to test whether the relation is symmetric, an attractive 
working hypothesis for a theory of translation. 
The transfer mechanism in earlier work, as in older systems 
such as the different versions of ARIANE (Boitet, 1988), a 
system developed in Grenoble at one of the oldest European 
centers for machine translation; METAL (White, 1985), the 
Siemens German-English system initially developed in the 
States; 8 and the SUSY system (Maas, 1988), a system 
developed in the 1970s in Saarbruecken, was an arbitrary tree- 
to-tree transformation. Compositionality and declarativity 
have since become basic tenets as a means of overcoming the 
ad hoc and procedural mechanisms those systems employed (cL 
Landsbergen, et al., 1989 on compesitionality in the Rosetta 
system and des Tombe, et al., 1985 for a discussion of "relaxed 
compositionality" in the Eurotra framework). Current work 
concentrates on constraining the transfer mechanism within a 
well defined computational model, e.g., transfer rules are 
defined between feature structures and the mechanism is based 
on unification (cL van Noord, et al., 1990, Russell et al., 1991 
and Wedekind, 1988). Unification as the basis for MT systems 
serves as a basis for quite a number of MT projects in Europe 
(in addition to the above mentioned el. also Carlson & 
Vilkuna, 1990 and Zajac, 1989); its advantages are the well 
understood formal aspects and the declarative nature of the rule 
schema for a given implementation. 
As a conclusion to this section, let me mention a few 
outstanding topics that are under investigation in the CL 
literature but are noticeably absent in the MT literature in 
Europe. The approach to translation as more of an AI problem 
(cL numerous papers by Nirenburg and Wilks) has not received 
much attention in Europe. This is perhaps due to the fact that 
MT projects are more often found in (computational) linguistic 
departments than computer science and AI labs. The generation 
work in MT has mainly concerned itself with reversibility 
issues and has hardly taken into account any of the work on 
planning, discourse, etc. I attribute this fact to the as yet ill- 
understood process of translation and, thus, the difficulty in 
defining a basis from which to generate. MT is still struggling 
with word, phrase and sentence translation (at best) and has 
therefore perhaps considered it premature to look at discourse 
problems. The one well-clef'reed problem, and in many ways the 
most concrete, is the lexicon. Although lexical descriptions 
imply everything else, there is a feeling that word descriptions 
and their mapping to other languages can be improved 
gradually. 
The system is now essentially worked on in Europe and is being 
extended to other European languages including French, Spanish 
and Dutch. 
30 
PARTIALLY AUTOMATING THE 
TRANSLATION PROCESS 
As automation increases and, with it, access to more and 
more information, the demand for translation increases. Since 
high-quality machine translation of unrestricted text is no 
solution to this problem in any foreseeable future, there is a 
growing trend to look for partial solutions. One option is to 
build yet another complete MT system such as SYSTRAN, 
LOGOS, or METAL (the only three viable commercial systems) 
with full knowledge that the output will be comprehensible, at 
best. These systems are useful once the lexicon has been 
developed and tuned for a given corpus; however, given the 
long development time for building such a system, they will, 
by definition, be based on out-dated technology. The other 
solution is to concentrate on those parts of the translation 
process that can be automated. 
The topic of automating only some parts in view of using a 
machine to aid in the translation process has been around for a 
long time (Kay, 1973), often under the name machine or human 
assisted translation; however, concrete projects addressing a 
specific aspect are, for the most part, relatively recent. The 
major aspects currently identified within the space of what can 
be usefully automated are when and where to use human 
interaction, identifying classes of restrictions on the input 
language (lexical, syntactic and semantic), separating the task 
into sub-tasks (monolingual vs. bilingual and further breaking 
these down along traditional linguistic lines and according to 
document preparation criteria). 9 
Identifying those aspects which can be automated and 
working towards a solution has found interest not only from a 
practical point of view, but also as a theoretical exercise. 
Ambiguity, for example, is an important problem for any 
language description task. For translation work this problem 
is compounded in that it may arise not only during parsing, 10 
but also during translation and in generation. In generation, 
the problem is well-known in the CL literature as the problem 
of natural language paraphrases arising from a given 'meaning' 
representation; in the context of translation, a system that 
produces paraphrases is not very useful without some 
refinement on how the paraphrases differ. Though no 
formalization of this exists, there is general agreement that 
paraphrases in a target language often represent different 
translations w.r.t, a given source text. Another problem for 
generation in MT and shared with the CL community is that of 
lexical choice ff the representation abstracts away from words, 
Seen from a practical viewpoint, the question of automating the 
process of translation must also take into account the actual 
working conditions. For example, many translation services work 
from printed sources rather than the electronic version. And in the 
larger centers, such as the EC translation services, much of the 
translation is done via dictaphone and typed by secretaries. In 
both of these cases, there is no place for interaction unless the 
entire working pattern is first changed. 
10 In a recent demonstration I attended of a commercial MT system, it 
became clear to me that one of the reasons why the output of 
current systems is so bad, is not that the correct parse couldn't be 
found among the numerous possible ones, nor that it couldn't be 
translated, but rather that the system could only choose one 
parse, and often this was the wrong one. 
representing them as concepts or a set of features. This 
problem will be apparent in the bilingual component in a 
transfer system and in generation in an interlingua system. 
One method of controlling the analysis is by limiting the 
input; one very simple and successful example is the Titus 
system which has basically a fixed number of templates which 
define the syntax of the input (Ducrot, 1982). This system, 
which is actually a database for the textile industry that permits 
natural language input and provides multilingual output, is also 
representative of another restriction common in most NLP 
applications, namely, limiting the application domain. 
Limiting the semantic domain is common practice in the MT 
community. Eurotra~ for example, works on a limited corpus in 
the domain of telecommunications and the project reported on 
in Alshawi, et al., 1991, is developing a lexicon for the ear 
industry. At ISSCO, work is underway on a sublanguage 
consisting of avalanche bulletins, somewhat similar to the 
exemplary TAUM-METEO system for weather reports. 
Another means of automating the translation stages, while 
still controlling the process, is by allowing for interaction 
during the various phases (Johnson & Whitelock, 1985). 
Interaction may be limited to the monolingual component 
where questions are only asked about the source text 
(Whitelock et al., 1986). The interest in developing authoring 
systems (i.e., systems where an individual writes a text in the 
source language with a 'guarantee' that the translation will be 
correct) is an attempt to assure that the analysis of the text is 
not ambiguous and does have a translation (McGee Wood & 
Chandler, 1988). Or the interaction may be included in the 
bilingual component, where the user is asked to choose the 
correct translation. 
The simplest example of the latter can be found in the 
bilingual dictionaries offered with some word processors, often 
referred to as translator's workstations. Such simple tools as 
on-line access to both monolingual and bilingual dictionaries, 
editors that support multiple scrolling screens, or hyphenation 
and spelling checkers for more than one language are by no 
means a standard in normal office settings. Development of 
very simple tools and a basic environment may provide a basis 
for adding more sophisticated components incrementally. 
Work in MT proper vs. work on environments for translators 
are essentially carried out in two different eornmunities. Only 
the commercial systems have up to present taken the latter 
topic seriously; this situation is changing as more of the 
funding for research moves to the private sector. 
CONCLUSION 
In presenting major themes in current MT work, a number of 
programs and activities have not received adequate attention. 
In particular the European activities planned as a follow-up to 
the Eurotra project, especially since the major portion of EC 
funding for MT has gone to this project which will end in 1992. 
For this phase, a number of sub-projects are currently under 
way, including the definition of a new formalism (that will be 
closer to standard unification systems) and tools for a better 
computational linguistic research environment. Plans or 
follow-up work have recognized the need for more basic 
research in all topics known to the CL community, but with 
emphasis on considering solutions in terms of multilingual 
needs. The problems specific to translation have essentially 
been mentioned above. Aside from the numerous lexical 
31 
projects (for which there will certainly be European and 
national initiatives), we can add a number of corpus initiatives 
(two of which are already under way in England). Education is 
also mentioned as a topic in its own right. 
Some of the activities in purely academic centers have been 
overlooked, either because I didn't know about them or because 
they have not had any impact on the community. As to 
activities in the private sector, it is simply more difficult to 
obtain information. Many of the larger companies, such as 
Philips, Siemens or IBM, have shown a long-standing 
commitment to both research and development of MT. IBM, 
for example, has sponsored a number of workshops in the past 
years, inviting representatives from all of the well known 
centers in the world (of. Lippman, 1986). Smaller workshops 
on topics such as unification and translation (ISSCO, 1989) 
have taken place all over Europe on an ad hoc basis. 
One last outstanding topic to be mentioned in the context of 
MT is that of evaluation. Its absence in this review is due to its 
general absence as a recognized theme and its lack of direction 
in the field (Falkedal, 1990). Though numerous individual 
efforts have been undertaken (King & Falkedal, 1990), the 
results of this work often remain private. 11 
Simlar to developments in NLP, the topic has gained 
importance in the last few years and recently, a working group 
was formed headed by M. King and G. Magnusdottir. One other 
center active in this area is the University of Stuttgart (U. 
Heid). A first forum on Evaluation and MT will be held in 
Switzerland in April, including participants from the academic 
and private sectors. 
ACKNOWLEDGEMENTS 
I would like to thank Louis des Tombe for helpful discussion 
in preparing this survey. 
REFERENCES 
ALPAC (1966) Report of the Automatic Language Processing 
Advisory Committee, division of Behavioral Science, 
National Academy of Sciences, National Research Council 
Publication 1416, Washington, D.C. 
Alshawi, H., H. Boloch, D. Carter, R. Hunze, B. Gambaeck, 
P.Peng, M. Rayner, S. Sachachtl, L. Schmid (1991) 
Multilingual Communication Using Quasi Logical Forms. 
ms. 
Appelo, L., C. Fellinger & J. Landsbergen (1989) 
Subgrammars, Rule Classes and Control in the Rosetta 
Translation System. Proceedings of the EACL, 
Copenhagen, 1987. 
Bech, A. & A. Nygaard (1988) The E-framework: A formalism 
for natural language processing. Coling '88, Budapest, pp. 
36-39. 
D. Arnold, L. Jaspaert, L. des Tombe (1985) Eurotra Linguistic 
Specifications. ELS-3, internal Eurotra report, Luxembourg. 
11 One exception to this is a report that may be obtained from the 
Canadian Government on evaluation, Bourbeau (1990). 
Boitet, C. & R. Gerber (1984) Expert systems and other new 
techniques. Coling '84, Stanford. 
Boitet, C. (1987) Research and development on MT and related 
techniques at Grenoble University (GETA). In: M. King 
(ed.) Machine Translation Today: The State of the Art, 
Edinburgh University Press, Edinburgh, pp.133-153. 
Bourbeau, L. (1990) Ealaboration et raise au point d'une 
mithodologie d'evaluation linguistique de systhmes de 
t~aduetion assistie par ordinateur. Sec. of the Canadian 
Government, Quibec. 
Brown, P., J. Cocke, S. Della Pietra, V. Della Pietra, F. Jelinek, 
R. Mercer, & P. Roossin (1988) A statistical approach to 
language translation. Coling '88, Budapest, pp.71-76. 
Busemann, S. & C. Hauenschild (1988) A constructive view of 
GPSG or how to make it work. Coling, Budapest, pp. 77-82. 
Ducrot, J.-M. (1982) TITUS IV System: systhrae de traduetion 
automatique et simultanie en quatre langues. In: P. L Taylor 
& b. Cronin (eds.) Information Management Research in 
Europe: Proceedings of the EURIM 5 Conference, 
Versailles, Aslib, London. 
Eurotra-Lexic (1989) The development of Spanish-Dutch 
dictionaries for machine translation purposes: Project 
Definition. Stichting Taaltechnologie, Van Dale 
Lexicografie, Phillips Research, Vakgroep Romaanse 
Talen, Utrecht. 
ET-7(1990) EUROTRA-7: Feasibility and Project Definition 
Study on the Reusability of Lexical and Terminological 
Resources in Computerised Applications--Project 
Overview, Commission of the European Communities, 
Luxembourg. 
Falkedal, K. (1990) Evaluation Methods for Machine 
Translation Systems--And Isabelle, P. (1988) Reversible 
Logic Grammars for Machine Translation. The 2nd 
International Conference on Theoretical and 
Methodological Issues in Machine Translation of Natural 
Languages, Pittsburgh. 
Johnson, R. & P. Whitelock (1985) Machine Translation as an 
Expert Task. The 1st International Conference on 
Theoretical and Methodological Issues in Machine 
Translation of Natural Languages, Hamilton, pp. 145-153. 
Kay, M. (1973) The MIND System. In: R. Rustin (ed.) Natural 
Language Processing, Algorithmics Press, New York, 
pp.155-188. 
Kay, M. (1980) On the Proper Place of Men and Machines in 
Language Translation. Xerox PARC report CSL-80-11, Pale 
Alto. 
Kay, M. (1984) Functional Unification Grammar: A Formalism 
for Machine Translation. Coling '87, Stanford. 
King, M, & K. Falkedal (1990) Using Test Suites in Evaluation. 
Coling '90, pp. 211-216. 
32 
Landsbergen, J. (1987) Montague grammar and machine 
translation. In: P. Whiteloek, M. McGee Wood, H. somers, 
R. Johnson and P. Bennett (eds.) Linguistic Theory and 
Computer Applications, Aeadernic Press, London. 
Landsbergen, J. (1989) The Rosetta Project. In: Proceedings of 
the Machine Translation Summit II, Munich. 
Lippmann, E.O. (1986) ELS Conference Translation 
Mechanization. IBM Research Report European Language 
Services in cooperation with the University of 
Copenhagen, Copenhagen. 
Maas, D. (1988) The Machine Translation SUSY system. In: In: 
M. King (ed.) Machine Translation Today: the State of the 
Art, Edinburgh University Press, Edinburgh, pp.209-246. 
McGee Wood, M. & B. Chandler (1988), Machine Translation 
for Monolinguals. Coling '88, pp. 760-763. 
McNaught, J. (1990) Reusability of Lexical and Terminological 
Resources: Steps towards Independence. Proceedings of the 
International Workshop on Electronic Dictionaries, Oiso. 
van Noord, G., J. Dorrepaal, P. van der Eijk, M. Florenza, & L. 
des Tombe (1990) The MiMo2 Research System. The 3rd 
International Conference on Theoretical and 
Methodological Issues in Machine Translation of Natural 
Languages, Austin. 
van Noord, G. (1989) Bottom-Up Generation in Unification 
Based Formalisms. Proceedings of the 2nd European 
Workshop on Natural Language Generation, Edinburgh, pp. 
53-59. 
Picchi, E. & N. Calzolari (1986) Textual perspectives through 
an automatized lexicon. Proceedings of the XII ALLC 
Conference, Slat.kine: Geneva, 1986. 
Bar-Hillel, Y. (1964) Four Lectures on Algebraic Linguistics 
and Machine Translation. In: Y. Bar-Hillel (ed)Language and 
Information, 
Sadler, V. & R. Vendelrnans (1990) Pilot Implementation of a 
Bilingual Knowledge Bank. Coling '90, Helsinki, pp. 449- 
451. 
Sadler, L., I. Crookston, & D. Arnold (1990) LFG and 
Translation. The 3rd International Conference on 
Theoretical and Methodological Issues in Machine 
Translation of Natural Languages, Austin. 
Kaplan, R., K. Netter, J. Wedekind & A. Zaenen (1989) 
Translation by structural correspondences. EACL '89, 
Manchester, pp.272-281. 
Russell, G., A. Ballim, D. Estival, S. Warwick (1991) A 
Language for the Statement of Binary Relations over Feature 
Structures. EACL '91, Berlin. 
Rupp, C.J. (1989) Situation semantics and machine 
translation. EACL '89, Manchester, pp. 308-318. xs des 
Tombe, L., D.Arnold, L. Jaspaert, R. Johnson, S. Kranwer, 
M. Rosner, N. Varile, S. Warwick (1985) A Preliminary 
Linguistic Framework for EUROTRA. The 1st International 
Conference on Theoretical and Methodological Issues in 
Machine Translation of Natural Languages, Hamilton, 
pp.283-288. 
Warwick, S. (1987) Automated Lexical Resources in Europe: a 
survey. Paper prepared for the workshop Automating the 
Lexicon: Research and Practice in a Multilingual 
Environment, Grosseto. 
Wedekind, J. (1988) Generation as Structure-driven Generation. 
Coling '88, pp. 732-737. 
White, J. (1985) Characteristics of the METAL Machine 
Translation System at Production Stage. The 1st 
International Conference on Theoretical and 
Methodological Issues in Machine Translation of Natural 
Languages, Hamilton, pp. 359-369. 
Whitelock, P., M. McGee Wood, R. J. Chandler, N. Holden, 
H.J. HorsfaU (1986) Strategies for Interactive Machine 
Translation: the experience and irnplieations of the UMIST 
Japanese project, Coling '86, pp.325-329. 
Wilks, Y. (1973) An Artificial Intelligence Approach to 
Machine Translation. In: R. Schank & K.M. Colby (eds.) 
Computer Models of Thought and Language, San Francisco. 
Witkam, T. (1988) DLT--An Industrial R & D Project for 
Multilingual Machine Translation. Coling '88, Budapest, 
pp.756-759. 
Zajac, R. (1989) A Transfer Model Using a Typed Feature 
Structure Rewriting System with Inheritance. Coling '89, 
Vancouver. 
33 
