23
Error Analysis of Rule-based Machine Translation Output A Case Study on English – Persian MT Systems ترجمه؟تنی بر خروجی دستگاه از حکومت مبیل خطا تجزیه و تحلسی انگلی مطالعه موردی در زبان- ستم های سیارسی فMT Zahra Pourniksefat Islamic Azad University – Science & Research Branch

Error Analysis of Rule-based Machine Translation Outputs

Embed Size (px)

Citation preview

Page 1: Error Analysis of Rule-based Machine Translation Outputs

Error Analysis of Rule-based Machine Translation Output

A Case Study on English – Persian MT Systems

تجزیه و تحلیل خطا از حکومت مبتنی بر خروجی دستگاه ترجمه؟MTف ارسی سیستم های -مطالعه موردی در زبان انگلیسی

Zahra Pourniksefat

Islamic Azad University – Science & Research Branch

Page 2: Error Analysis of Rule-based Machine Translation Outputs
Page 3: Error Analysis of Rule-based Machine Translation Outputs

Agenda

Introduction

Machine Translation Overview

Evaluation of MT systems

Methods & Materials

Error Categories & Description

Results & Discussion

Page 4: Error Analysis of Rule-based Machine Translation Outputs

Machine Translation Overview

Definition: The term Machine Translation (MT) is used for translating text or

speech from one natural language to another by using computers and software.

• Systran: MT is much faster than human translators because it is much cheaper

and has a better memory than human translators.

• Shahba 2002 believed that “It’s better to spend our time on the actual act of

translation rather than typing the English text or scanning it for the MT to

translate. Efforts in MT are by themselves valuable as they at least satisfy one of

the needs of human beings: need for innovation and discovery”

• MT is more economic on time and money, but it is less accurate than human

translators (Frederking, 2004).

Page 5: Error Analysis of Rule-based Machine Translation Outputs

Why MT matters?

According to Hatim and Munday it’s an important topic - socially, politically, commercially,

scientifically, and intellectually or philosophically (2004)

• The social or political importance of MT arises from the socio- political importance of translation in

communities where more than one language is generally spoken. So translation is necessary for

communication- for ordinary human interaction, and for gathering the information one needs to play

a full part in society.

• The commercial importance of MT is a result of related factors. First, translation itself is

commercially important. Second, translation is expensive.

• Scientifically, MT is interesting, because it is an obvious application and testing ground for many

ideas in Computer Science, Artificial Intelligence, and Linguistics.

• Philosophically , MT is interesting, because it represents an attempt to automate an activity that can

require the full range of human knowledge.

Page 6: Error Analysis of Rule-based Machine Translation Outputs

Some Misconceptions about MT

MT is a waste of time because you will never make a machine that can translate

Shakespeare. This criticism that MT systems cannot translate Shakespeare is a bit like

the criticism of industrial robots for not being able to dance.(Hatim and Munday, 2004)

• First, translating literature requires special literary skills – it is not the kind of

thing that the average professional translators normally attempt

• Second, literary translation is a small proportion of the translation that has to be

done.

• Finally, one may wonder who would ever want to translate Shakespeare by

machine – it’s a job that human translators find challenging and rewarding, and

it’s not a job that MT systems have been designed for.

Page 7: Error Analysis of Rule-based Machine Translation Outputs

Approaches to MT

• Direct Machine Translation Approach

The first developed MT systems where a word–for–word translation from the source language to the target

language is performed.

• Transfer Machine Translation Approach

1. The analysis stage that is the direct strategy which takes benefits of a dictionary in source language to

demonstrate the source language from linguistic point of view.

2. The transfer stage varies the outputs of the analysis stage to produce structural and linguistic equivalents

between the two languages.

3. The generation stage is the third stage in which a target language dictionary is applied to result the target

language document on the basis of linguistic information. (Steiner, 1988)

• Interlingua Machine Translation Approach

First the source text meaning is decoded

Second the resulted meaning is re-encoded in the target language

Page 8: Error Analysis of Rule-based Machine Translation Outputs

Approaches to MT cont’d.

• Rule-based Machine Translation Approach

It operates on the linguistic data on source and target languages fundamentally

taken from bilingual dictionaries and the basic semantic, morphological, and

syntactic grammar of the individual language (Gelbukh, 2011).

Minimally, to get a Persian translation of English sentence one needs:

1. A dictionary that will map each English word to an appropriate Persian

word.

2. Rules representing regular English sentence structure

3. Rules representing regular Persian sentence structure

4. And finally, we need rules according to which one can relate these two

structures together.

Page 9: Error Analysis of Rule-based Machine Translation Outputs

Approaches to MT cont’d.

• Statistical Machine Translation Approach

This system uses a corpus or database as a translated example for analyzing and decoding

source language. In comparison with the machine translation of about three decades ago,

Google Translate as an example of more contemporary automated engine for the task of

translation has taken a giant leap. However, it is still too imperfect. (Nierenberg, 1998)

• Hybrid Machine Translation Approach

1. Rules post-processed by statistics in which translation are practiced on the pivot of

rule-based engine. Next statistics are applied to correct the output.

2. Statistics guided by rules in which rules have an important role to pre-process date

to quite the statistical representation to normalize. This approach is powerful,

flexible and under more control when it’s translating.

Page 10: Error Analysis of Rule-based Machine Translation Outputs

Evaluation of MT Systems

• Human translation assessment (Secară 2005; Williams 2001) has been

moving from microtextual, word- or sentence-level error analysis methods

toward more macrotextual methods focused on the function, purpose and

effect of the text. At the same time, machine translation assessment has

mainly been microtextual and focused on the aspects of accuracy and

fluency.

• Hovy (2002) discussed the complexity of MT evaluation, and stressed the

importance of adjusting evaluation to the purpose and context of the

translation.

Page 11: Error Analysis of Rule-based Machine Translation Outputs

Evaluation of MT Systems cont’d.

Mary A. Flangan Believed that Machine translation quality can be difficult to

quantify for a number of reasons:

1) A text can have several different translations, all of which are correct.

2) Defining the boundaries of errors in MT output is often difficult. Errors sometimes

involve only single words, but more often involve phrases, discontinuous

expressions, word order or relationships across sentence boundaries. Therefore,

simply counting the number of wrong words in the translation is not meaningful.

3) One error can lead to another. For example, if the part of speech of a word is

identified incorrectly by the MT software, the entire analysis of the sentence may be

affected, creating a chain of errors.

4) The cause of errors in MT output is not always apparent. The evaluator usually does

not have access to a trace of the software's tests and actions. Thus it can be difficult

to identify what went wrong in the translation of a sentence.

Page 12: Error Analysis of Rule-based Machine Translation Outputs

Evaluation of MT Systems cont’d.

Types of Evaluation

Automatic Evaluation

the Word Error Rate (WER), the Position independent word Error Rate (PER), the

BLEU (Papineni et al., 2002) and the NIST (Doddington, 2002) where the MT

output is compared to one or more human reference translations.

Human Evaluation

Due to the complexity of natural language, manual evaluation seems more reliable

1. Three passages were selected and translated by Rule-based MT Systems

and compared with one Statistical MT System and Human translator

2. Error categories were derived after the analysis of each text

Page 13: Error Analysis of Rule-based Machine Translation Outputs

Methods & Materials • Three passages were translated by two different MT systems and also a human

translator.

• From each text type a passage of approximately 400 words was taken from story,

user guide and magazine.

• The rule-based MT – Arya TM– system was designed based on thousands of lexical

and grammatical rules.

• The statistical system, Google Translate by Google Inc., is based on the use of large

monolingual and parallel corpora for translation.

• The unit of analysis was set to a sentence level because it’s the largest unit which

can be easily recognized in MT systems and ST sentence can be clearly

corresponded to its TT pairs.

Table of Source Text Passages for Analysis

Number of Words Number of Sentences

Short Story

The Lottery 398 13

User Guide

Microsoft Access 2012 390 16

Magazine

Academic article 415 15

Page 14: Error Analysis of Rule-based Machine Translation Outputs

Errors Category

Syntactic

Word Order

Missing

Words

Punctuation

Parts of

Speech Conjugation

Unknown Words

Semantic

Incorrect Words

Polysemy

Idiomatic Expressions

• For English-to-Persian Rule- based MT systems the following categories were

derived

Error Categories & Descriptions

Page 15: Error Analysis of Rule-based Machine Translation Outputs

Error Categories & Descriptions cont’d.

Description of Error Categories:

• Syntactic Errors: Those errors that are related to the grammar of the language such as parts

of speech or conjugation

Word order that means sentence elements ordered incorrectly

Example: Commands generally take the form of buttons and lists. (User Guide)

Missing words: incorrect elision of some words

Example: This requires better data collection and analysis tools for studying outcomes and

consistent use of these tools across individual studies. (Magazine)

Arya Translation System .دستور ها بطور کلی فرم شاگرد می گیرد و فهرست ها

Google Translate .دستورات به طور کلی به شکل دکمه ها و لیست

Arya Translation System این مجموعه اطالعات بهتر نیاز های و ابزار ها تحلیل برای مطالعه می

.کن حاصل ها و سازگار استفاده می کند

Google Translate این امر مستلزم جمع آوری داده ها بهتر و با استفاده از ابزار تجزیه و

مطالعات تحلیل برای بررسی نتایج و استفاده مداوم از این ابزار در سراسر

.فردی

Page 16: Error Analysis of Rule-based Machine Translation Outputs

Error Categories & Descriptions cont’d.

Unknown words: word not in a dictionary

Example: The women, wearing faded house dresses and sweaters, came shortly after their

menfolk.( Story)

Punctuation: incorrect punctuation

Example: The children assembled first, of course. (Story)

Arya Translation System خسته کننده لباس ها خانه و ژاکت ها محو کردند ، به زودی پس, زن ها

آمدندشان menfolkاز

Google Translate زنان، پوشیدن لباس و ژاکت پژمرده خانه، در آمد مدت کوتاهی پس از

menfolk خود را.

Arya Translations .البته جمع کردند , بچه ها اول

Google Translations .کودکان مونتاژ اول، البته

Page 17: Error Analysis of Rule-based Machine Translation Outputs

Error Categories & Descriptions cont’d.

Parts of speech: errors in identifying pars of speech such as noun or verb

Example: If you decrease the width of the ribbon, small button labels disappear. (User Guide)

Conjugation: incorrectly formed verb or wrong tense

Example: Soon the women, standing by their husbands, began to call to their children, and the

children came reluctantly, having to be called four or five times.

Arya Translation System اگر شما پهنا نوار کاهشبیابید ، دکمه کوچک ناپدید برچسب می زند

Google Translate د اگر عرض نوار شما را کاهش دهد، برچسب ها دکمه کوچک ناپدید می شون

Arya Translations به شروع کردن صدا به بچه ها , حمایت می کن شوهر های شان , بزودی زن ها

.و بچه ها با اکراه آمدند ، می دارد که اشد صدا زده چهار یا پنج دوره , شان

Google Translations ه به زودی زنان، شوهران خود ایستاده، شروع به تماس به فرزندان خود، و بچه ها ب

.اکراه، به نام چهار یا پنج بار

Page 18: Error Analysis of Rule-based Machine Translation Outputs

Error Categories & Descriptions cont’d.

• Semantic Errors: Those errors that are related to the meaning such as incorrect meaning

of words or expressions which caused the incorrect meaning of the whole sentence.

Incorrect word: completely incorrect meaning

Polysemy: incorrect selection of the meaning of the words with more than one meaning

Example: The people of the village began to gather in the square, between the post office and the bank,

around ten o'clock.

Style and idiomatic expression : incorrect translation of multi-word expression

Example: They greeted one another and exchanged bits of gossip as they went to join their husbands.

Arya Translations صل آنها سالم همدیگر و ذره غیبت معاوضه کردند آنها رفتند که و

.کنند شوهر های شان

Google Translations را به آنها استقبال یکدیگر و رد و بدل بیت از شایعات بی اساس

.عنوان آنها را برای پیوستن به شوهر خود رفت

Arya Translations در , مردم روستا شروع کردند که جمع شوند در مربع

میان پستخانه و بانک ، حدود دَه ساعت

Google Translations مردم روستا در میدان شروع به جمع آوری، بین اداره

.پست و بانک، ساعت حدود ده

Page 19: Error Analysis of Rule-based Machine Translation Outputs

Results & Discussions

RBMT

SMT

Human

Word Order Missing Words Unknown

Words

Punctuation Parts of Speech Conjugation

Story 12 6 3 12 8 9

User Guide 17 5 1 10 5 13

Magazine 14 4 10 7 15

Story 11 7 3 12 7 8

User Guide 17 5 1 9 7 11

Magazine 15 2 5 9 6 14

Story 1 2 0 3 1 3

User Guide 0 0 2 1 0 1

Magazine 2 1 1 1 2 2

Syntactic Category

Word OrderMissing Words

Unknown Words

PunctuationParts of Speech

Conjugation

Tab

le o

f S

yn

tact

ic E

rrors

Page 20: Error Analysis of Rule-based Machine Translation Outputs

RBMT

SMT

Human

Incorrect Lexicon Polysemy Idiomatic Expression

Story 10 7 12

User Guide 7 9 5

Magazine 7 11 9

Story 8 8 9

User Guide 3 7 3

Magazine 5 13 8

Story 0 0 2

User Guide 1 0 0

Magazine 0 1 1

Semantic Category

Incorrect Lexicon Polysemy Idiomatic Expression

Tab

le o

f S

eman

tic

Err

ors

Results & Discussions contd.

Page 21: Error Analysis of Rule-based Machine Translation Outputs

Results & Discussions cont’d.

• Both systems made the least errors with the simpler sentences and the most ones with the

compound- complex sentences, as well as lexically or structurally ambiguous texts. This is

because ambiguous source texts with different contents can correspond with more than one

representation.

• For the rule-based system, the most typical errors are in conjugation, word order and also in

rendering polysemous words and idiomatic expressions. For the statistical system the most

common error is in conjugating and determining the tense. However, it has also some

problems in translating words with multiple meaning and idiomatic expression.

• To see whether machine translation accuracy is affected by text-type three different genres

were analyzed thoroughly. And for the different text types, the rule- based system had

similar amounts of syntactic and semantic errors in each text.

Page 22: Error Analysis of Rule-based Machine Translation Outputs

Future!

• Evaluating MT quality is necessarily a subjective process because it involves

human judgments.

• Determining the best category for an error in MT output is not easy because we

have to place them on how they are realized rather than the cause of errors and

many machine translated sentences contained multiple, linked errors.

• Future work will therefore be focused on the cause of errors and ranking error

categories. The error categories presented here is flexible, allowing for the

deletion or addition of more categories.

Page 23: Error Analysis of Rule-based Machine Translation Outputs