Abstract
The purpose of this research is developing an Interlinguabased technique of the natural language numeral processing and translation. We propose a threelevel generalized numeral model as Interlinguarepresentation. The model formal grammar describes the natural language numeral structure. The first level grammar rules define that a numeral consists of sign, integer part, separation symbol, and fractional part. The second level decribes numeral integer part as a triad sequence. The third level defines the triad structure. We developed numberintonumeral, numeralintonumber, and translating algorithms based on the model. The algorithms are implemented in the Markov normal algorithms. We realized the model and the algorithms in webapplication in the Internet. The webapplication has a knowledgetesting function. The function allows to users test numeral convering and translating knowledge. Users from more than 100 countries visit webapplication and convert numerals. The largest number of users resides in the US and the Russian Federation. The webapplication log contains more than 200,000 records. The largest number of user requests related to the conversion of cardinal numerals of Spanish. The webapplication is integrated in toolbox of a complex linguistic webportal for translators as well. We conclude the Interlguabased technique is effective for numeral processing and translation and realization in webapplications.
Keywords: Natural Language ProcessingNumeral TranslationMarkov Normal AlgorithmsLinguistic WebApplication
Introduction
We use the following terms in this paper. A numeral is a cardinal numeral having symbolic notation in the text, e.g. «three hundred fifty two». A number is a cardinal numeral having digital notation, e.g. «352».
In the process of text translation program application also converts numerals of the source language into numerals of the target language. However, the numeral translation rules aren’t the same to the languageintolanguage text translation rules. Also there are numberintonumeral and numeralintonumber converting tasks in the text processing.
In this paper we describe how to process numbers and numerals in the text using the Interlingua representation. We present a webapplication for numeral converting and translation, user request statistics. The webapplication can be used in the natural language learning as a knowledgetesting system.
Problem Statement
Machine translation is used by many users especially in the Internet. Popular webtranslators have many language directions of text translation and demonstrate quality result.
There are two basic text translating technique:
1) translation with rules and small bank of translating equivalents
2) memory translation (or translation memory) (Planas & Fruse, 1999; Dillon & Fraser, 2006) with only huge bank of translating equivalents.
However, no one of techniques can’t get the text meaning and translates numerals perfect. The process of numeral translation has differences from language to language and isn’t similar to text translation. So it is necessary additional tools for numeral translation.
We try to solve a problem of numeral translation using the Interlinguabased technique.
Interlinguabased translation
The Interlingua is an intermediate representation of translating text (Dorr, Hovy & Levin, 2004; Lampert, 2004; Lee & Seneff, 2005). There are two steps in the Interlinguabased translation: 1) converting the source language text into the Interlingua; 2) converting the Interlingua into the target language text. The translation is easyextending. To add new language in multilingual translating system you need to develop the languageInterlingua converting algorithms.
We use such Interlinguabased translation to process numerals in the text. We describe the Interlingua representation with the formal grammar.
G. Hardegree grammars
Gary Hardegree proposed grammars (Hardegree, 1999) for representation of the numeral structure and number transformation into English numerals. The grammars can be intended only for numeral building and used only in English. The grammars also describe the rules of building only for integer parts of numerals, but don’t consider numeral case inflection as there is no case grammatical category in English.
Research Questions
The following research questions guide the current study:
Question 1: Is the Interlinguabased technique effective for the numeral processing and translating?
Question 2: What structure has the Interlingua representation for the numeral processing and translating?
Question 3: How realize the Interlinguabased numeral processing and translating in application accessible for users in countries of the World?
Purpose of the Study
The purpose of this study is to describe an Interlingua representation for the numeral processing and translating using the formal grammar and develop a webapplication realized this representation.
Research Methods
Our research has the following stages:
Findings
In the result of our research we have got the following findings.
Threelevel generalized numeral model
To describe a generalized numeral structure for the Interlingua representation by the formal grammar, we use the following terms.
Number terms are:
The numeral terms are:
Example 1. In this terms, the number
1 000 400 973 =
presents as:
The terms are necessary for model generalization and language independence.
We analyze the natural languages numeral building rules and develop a threelevel generalized numeral model (or
Level 1 renders numeral sign and integer and fractional parts. Part delimiters are patch words «
Level 2 renders threedigit ingredients (triads). Each part is divided into threedigit ingredients beginning with integer and fractional parts separating char. Threedigit ingredients part delimiters are patch words «
Level 3 renders threedigit ingredients items. Part delimiters are patch words «
Example 2. Figure
The model grammar rules are shown below.
Level 1:
Level 2:
...
...
Level 3:
The model is a generalized numeral structure using in programming of numberintonumeral, numeralintonumber, and translating algorithms.
Converting algorithms
We use Markov normal algorithms (Markov, 1954) to implement converting algorithms.
We add new operations and symbols to simplify the algorithm normal scheme:
→ + $$ – to add symbol $$ at the end of the word;
→ $$+ – to add symbol $$ at the beginning of the word;
[
_ (underlining) – space symbol.
In this section we present some basic converting algorithms.
Numberintomodel integer part converting algorithm replaces digits by numeral terms.
1)
2)
3)
4)
5)
6)
7)
8)
${\gamma}_{2}^{0}$
9)
10)
${\gamma}_{i}^{j}$
11)
12)→ +
${\gamma}_{1}^{0}$
An index symbol marks processed symbol in the number.
Modelintonumber integer part converting algorithm transforms a numeral integer part into a number integer part.
1)
2)
3)
4)
5)
6)
7)
8)
9)
10)
11)
12)
The algorithm also use the index symbol .
The algorithm using the model checks numeral for errors as well. 69 replacements execution is a correct algorithm ending. None of the replacements execution means that a numeral contains an error.
Numberintomodel fractional part converting algorithm is shown below.
1)
2) →
3)
In this algorithm the index symbol is a Greek alphabet letter.
Modelintonumber fractional part converting algorithm replaces numeral terms while all terms will processed.
1)
2)
3)
4)
Numeral translation order
The model terms have general nature. In each language, they have unique types. For example, in the Russian language
In some languages, numerals are formed by the rules that are different from the model rules. In this case, numeral is converted by algorithms. Two algorithms are necessary:
1) numeralintomodel converting algorithm transforming a numeral in the model representation into a numeral of the target language;
2) modelintonumeral converting algorithm transforming a numeral of the source language into a model numeral.
These algorithms carry out the opposite actions.
Numberintonumeral converting includes four steps:
1) to execute the numberintomodel integer part converting algorithm;
2) to execute the numberintomodel fractional part converting algorithm;
3) to execute the modelintonumeral converting algorithm if it exists;
4) to replace model terms by language symbols in required case.
Numeralintonumber converting consists of the following steps:
1) to replace language symbols by model terms;
2) to execute the numeralintomodel converting algorithm if it exists;
3) to execute the modelintonumber fractional part converting algorithm;
4) to execute the modelintonumber integer part converting algorithm.
Using the model, we can translate numerals. Translation of a numeral from the L1language into the L2language includes four steps:
1) to replace the L1language symbols by the model terms;
2) to execute numeralintomodel converting algorithm if it exists for the L1language;
3) to execute modelintonumeral converting algorithm if it exists for the L2language;
4) to replace the model terms by the L2language symbols in required case.
All algorithms in this paper are implemented in webapplication.
Webapplication with knowledgetesting function
In 2012 we have developed (with Dmitriy Tsybulko) a webapplication for processing of the natural language cardinal numerals. The webapplication is available to users of the Internet at http://prutzkow.com/enus/numbers/ (the Englishlanguage version) or http://prutzkow.com/ruru/numbers/ (the Russianlanguage version).
The webapplication has the following functions:
1) translation of numerals of Russian, English, German, Spanish and Finnish languages in any direction (because of the Interlinguabased technique);
2) numberintonumeral and numeralintonumber converting;
3) declination of numerals of the Russian language;
4) numerals converting and translating knowledge testing.
The webapplication was integrated in the toolkit of the MyPolyglot.com expert network for translators.
User request statistics
Each request to the webapplication is recorded in the log. The log uses for webapplication debugging and analyzing of request statistics. A record of the log includes the following request data:
There are more than 200,000 records in the log in this moment.
We analyzed the log and present numeral translating direction statistics in Table
In Table
The most of users of the webapplication reside in the US and Russia (Table
Conclusion
In the result of this research, we have got the following answers to research questions:
1. The Interlinguabased technique is effective for the numeral processing and translating. The technique allows adding numerals of the new natural language easy writing two converting algorithms: numeral into the Interlgua and the Interlingua into numeral.
2. The Interlingua representation for the numeral processing and translating has a numerallike structure. We have developed the threelevel generalized numeral model describing the Interlingua representation structure.
3. To make practical results of our research accessible for users in countries of the World we have developed the webapplication for numeral processing and translation with knowledgetesting function. The webapplication is based on the model as the Interlingua representation.We have received many good comments from users of our webapplication. The webapplication was integrated in a complex linguistic webportal for translators.
We have published the result of this research in Russian scientific journals as well.
Acknowledgments
We are grateful to our coauthor Dmitriy Tsybulko for collaboration in this research.
References
 Dillon, S., Fraser, J. (2006). Translators and TM: An Investigation of Translators’ Perceptions of Translation Memory Adoption. Machine Translation, 20 (2), pp 6779.
 Dorr, B. J., Hovy, E., Levin, L. (2004). Machine Translation: Interlingual Methods, Encyclopedia of Language and Linguistics. 2nd ed., Brown, Keith (ed.).
 Hardegree, G. (1999). Symbolic Logic, First Course, 3rd ed. McGrawHill.
 Lampert, A. (2004). Interlingua in Machine Translation, Technical Report.
 Lee, J., Seneff, S. (2005). InterlinguaBased Translation for Language Learning Systems. In Proc. of ASRU, Cancun, Mexico.
 Markov, A. A. (1954). Theory of algorithms (in Russian). Akad. Nauk SSSR (English trans. published by the Israel Program for Scientific Translation, Jerusalem, Vol. XLII, 1962).
 Planas, E., Furuse, O. (1999). Formalizing Translation Memories. In Proc. of MT Summit VII, Singapore, September 1317, 1999, pp. 331339.
Copyright information
This work is licensed under a Creative Commons AttributionNonCommercialNoDerivatives 4.0 International License.
About this article
Publication Date
13 December 2017
Article Doi
eBook ISBN
9781802960327
Publisher
Future Academy
Volume
33
Print ISBN (optional)

Edition Number
1st Edition
Pages
1481
Subjects
Cognitive theory, educational equipment, educational technology, computeraided learning (CAL), psycholinguistics
Cite this article as:
Prutzkow, A. (2017). InterlinguaBased Numeral Translation In WebApplication With KnowledgeTesting. In S. B. Malykh, & E. V. Nikulchev (Eds.), Psychology and Education  ICPE 2017, vol 33. European Proceedings of Social and Behavioural Sciences (pp. 290298). Future Academy. https://doi.org/10.15405/epsbs.2017.12.29