ProfitPress Mega CDROM2 …eeware (MSDOS)(1992)(Eng)/ProfitPress-MegaCDROM2.B6I/TEXT/UTILITY/MTRAN12.ZIP/DEMO.ZIP/READ.ME2

Text File | 1991-08-29 | 7.6 KB | 141 lines

08/29/91

Dear Fellow Icon enthusiasts,

     Here's a letter answering some questions that were asked
about the TRAN1 machine translation program.  Perhaps some of the
information here is of general interest.

     First of all, a fundamental principle underlying the design
of this machine translation program is the idea that it is
reasonable to put a good deal of manual analysis into a text that
will be translated into a multitude of target languages.  An
example of such a text is the Bible which still has not been
translated into some 3500 minority languages.  Other suitable
candidates for this type of treatment are owners manuals for
various products and the legislation of the European Community.  A
corollary to this first principle is the notion that any machine
translation program will be more successful if the grammar of the
source text is as limited as possible.  In keeping with this
corollary the syntax of the program's input text has been greatly
simplified.

     A second fundamental principle is that the program attempts
to translate meaning rather than just words.  To that end the
analysis of the source text is based on the theory expounded in
_The Semantic Structure of Written Communication_ (Beekman,
Callow, & Kopesec 1981).  According to the SSWC concepts/meanings
come in four classes: Things, Events, Attributes, and Relations
(1981:49).  In their simplest forms things are represented by
nouns, events by verbs, attributes by adjectives and adverbs, and
relations by function words like conjunctions, sentence adverbs,
and prepositions.  A formidable problem for the translator
presents itself when concepts are not represented in their
simplest forms; this is called lexical skewing.  For instance, in
the sentence, "John gave Mary some help" the word "help" is really
an event.  A simpler/unskewed way to express the same meaning
would be, "John helped Mary."

     In the analysis of the source text included with the program
an attempt was made to eliminate lexical skewing to the fullest
extent possible.  It should be noted that this is not entirely
necessary when translating between closely related languages, but
it becomes critical when translating into minority languages which
may lack abstract nouns for events like "love" or "forgiveness".

     As noted above, an attempt was also made to utilize a very
limited syntax in the analysis of the source text.  Ideally a
sentence should consist of a subject, verb, objects, and
possibly a relative clause.  Passive voice is not permitted
because it does not exist in all languages.  Conjunctions and
sentence adverbs are used in a stylized manner (ie. they always
mean the same thing).

     To facilitate translation of meanings rather than words, a
system utilizing connecting underscores and subscripting digits
was employed.  For instance, "chief_priests1" is treated as a
single concept, and thus contains a connecting underscore.  It is
also followed by the subscripting digit "1" to distinguish this
concept from any others which might possibly be renderable by the
same English words.  The subscripting digits used are somewhat
arbitrary, but in the case of verbs the digits 1 through 3 were
used for first, second, and third person singular verbs, and the
digits 2 through 6 were used for the plural forms.  Thus "know6"
would mean "they know".

     Forms such as "chief_priests1" and "know6" are considered to
be arbitrary symbols for units of meaning.  They could just as
easily have been rendered as "abc1" and "xyx6", but this would
have resulted in an input text that was unreadable.  Nevertheless,
the idea that these symbols are arbitrary is important.  For
example, "chief_priests1" may be rendered fairly literally in one
language (ie. 'sacerdotes principales' in Spanish), but in another
language the translation may sound more like 'honored old men of
ceremonial rites'.  The arbitrary forms used to represent meanings
are called semantic tags in the program.

     Since the program is attempting to translate meanings rather
than words, it uses an invention called a semanticon rather than a
lexicon.  Each semanticon entry begins with a semantic tag as
described above.  The next field in each entry is a morpological
tag.  A morphological tag is basically a part of speech, but it
can contain additional information such as person, number, gender,
tense, and so on.  The morphological tag refers to the target
language rendering of the concept represented by the semantic tag.
This target language rendering may not strictly match the semantic
tag in the traditional sense.  For instance, "sacerdotes
principales" 'priests high' is not a noun in the traditional
sense, but a combination of a noun plus an adjective.  However, it
functions as a single unit, and for this reason the conglomerate
is treated as a noun in the semanticon.  The next field in the
semanticon entry is the target language rendering of the concept
represented by the semantic tag.  It generally contains a single
target language word, but it may contain multiple words.  If the
morphological tag is "n" for noun, the entry consists of an
article followed by one or more words connected by underscores
which loosely represent a noun.  If the morphological tag is one
of those for adjectives, the entry consists of four words: a
masculine and a feminine singular adjective and a masculine and a
feminine plural adjective.

     The source language text to be translated contains braces.
These braces are used to delimit portions of the text which should
be translated as a unit.  For instance, noun phrases and
prepositional phrases should be surrounded by braces, and it's a
good idea to surround the main clause by braces.  The program
translates text in braces as units so if a noun phrase is
surrounded by braces the program will never make the article of
that noun phrase agree with a noun which is outside that noun
phrase.

     To make the program translate into some other language such
as French, it is first necessary to change the semanticon to
contain French renderings for the semantic tags.  (The semanticon
can be changed with a text editor.)  Note that French requires
explicit subject pronouns so the entry for "know6" would contain
two words meaning 'they know' rather than the single Spanish word
'saben'.  After this is done, it will still be necessary to make
some program modifications, but they should not be too formidable
for French.  First of all, the program has some global variables
containing Spanish articles.  These need to be changed to their
French counterparts, but it probably won't be necessary to change
the identifier names.  Second, it will be necessary to modify the
procedure contract().  The rules for contraction will be different
in French.  Likewise, the procedure phono_adj() which makes
phonological adjustments (like "a house" but "an hour") will have
to be modified to follow French rules.  The procedure which moves
object pronouns in front of verbs may or may not need to be
modified.  (I don't know what the rules are for French.)  None of
the required modifications should be too time consuming since the
entire program was written in just fifteen days.

     Translations into Portuguese, Italian, and possibly French,
as well as a Papua New Guinea language called Tigak are planned
for later this year.

Doug Witmer
Internet: [e-mail]
Bitnet:   b912dieg@utarlg
smail:    1102 Enterprise Drive #149, Grand Prairie, Texas  75051