MACHINE TRANSLATION – POSITIVE SIDE
Context:
To process any translation, human or automated, the meaning of a text in the original (source) language
must be fully restored in the target language, i.e. the translation. While on the surface this seems
straightforward, it is far more complex. Translation is not a mere word-for-word substitution. A translator
must interpret and analyze all of the elements in the text and know how each word may influence another.
This requires extensive expertise in grammar, syntax (sentence structure), semantics (meanings), etc., in
the source and target languages, as well as familiarity with each local region.
Human and machine translation each have their share of challenges. For example, no two individual
translators can produce identical translations of the same text in the same language pair, and it
may take several rounds of revisions to meet customer satisfaction. But the greater challenge lies in
how machine translation can produce publishable quality translations.
Concept: also called Computer Aided Translation
Machine translation (MT) is automated translation. It is the process by which computer software is used to
translate a text from one natural language (such as English) to another (such as Spanish). – SYSTRAN
“beyond language”
Pros arguments:
Timeline
The rate of machine translation is exponentially faster than that of human translation. The average
human translator can translate around 2,000 words a day. Multiple translators can be assigned to
a given project to increase that output, but it pales in comparison to machine translation. Machine
translation can generate thousands of words each minute. One should note that the output of
machine translation is not in its final useable form right away, but in certain scenarios it can be quite
useful. Even when adding a post-editing step, machine translation takes a fraction of the
time that human translation takes.
Adaptation
Machine translation can memorize key terms and phrases that are used within a given
industry. This leads to translations that are very consistent across the entire file, something that is
more difficult to achieve when using multiple human translators.
Universality
Usually a professional translator becomes specialized in a definite field, but machine translation
system can translate any a text about any area. For the translation of special terminology you
have to just switch on a corresponding setting.
Real time
Sometimes having a human translator simply isn’t cost-effective. For example, having a
human translator standing by to translate every live online customer service chat
would be very costly and difficult to achieve for every language used. Machine
translation gives a good enough result instantly and at a much lower cost.
Web Content & Web Page Translation
Because of machine translation, web content and web page translation have become extremely
easy. This allows people searching the web to easily translate web content and pages
into their native language when navigating on content or pages that are written in a
different language. There are also opportunities for businesses to apply this type of software
on their own websites, which can give their audience the ability to change the language as they
are browsing through their website.
Repetitive text
Machine translation excels when it comes to repetitive text. Think of all those car manuals
translated into a wide range of languages across the world.
Interesting data:
Google Pixel’s ability to instantly translate speech for people having a conversation, and we use
Microsoft’s Bing Translator.
Neural Networks or Neural Machine Translation.
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine
Translation
Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation,
with the potential to overcome many of the weaknesses of conventional phrase-based
translation systems. These issues have hindered NMT's use in practical deployments and
services, where both accuracy and speed are essential. In this work, we present GNMT,
Google's Neural Machine Translation system, which attempts to address many of these
issues. Our model consists of a deep LSTM network with 8 encoder and 8 decoder layers
using attention and residual connections. To improve parallelism and therefore
decrease training time, our attention mechanism connects the bottom layer of the
decoder to the top layer of the encoder. To accelerate the final translation speed, we
employ low-precision arithmetic during inference computations. To improve handling
of rare words, we divide words into a limited set of common sub-word units
("wordpieces") for both input and output. This method provides a good balance between
the flexibility of "character"-delimited models and the efficiency of "word"-delimited models,
naturally handles translation of rare words, and ultimately improves the overall accuracy of the
system. Our beam search technique employs a length-normalization procedure and uses a
coverage penalty, which encourages generation of an output sentence that is most likely to
cover all the words in the source sentence. On the WMT'14 English-to-French and English-to-
German benchmarks, GNMT achieves competitive results to state-of-the-art. Using a human
side-by-side evaluation on a set of isolated simple sentences, it reduces translation errors by an
average of 60% compared to Google's phrase-based production system.
Conclusion:
It’s not all or nothing
It’s not machine translation or human translators – using both together achieves high quality,
lower cost translations.
Other:
Systran offers a wealth of translation software that supports a total of 15 different languages. These can be
mixed and matched with your choice of a base language to make 52 language pairs. Each language pair is
available for purchase. The company also offers software in ten multilingual packs, such as the Systran
Business Translator English World Pack that we review here. This specific language bundle translates from or
to English and German, Chinese, Korean, Spanish, French, Italian, Japanese, Dutch, Polish, Portuguese,
Russian and Swedish.
Translate More for Less
Machine translation eliminates the main constraints of human translation: cost and capacity.
A translator usually translates 2,000 words per day for 20 cents per word.
As the volume of information grows, it surpasses the capacity of human translators and enterprise budgets.
Corporations want to translate more for less and they need to do it fast.
Machine translation is the only viable solution to translate content that would not be translated otherwise because it
is quick and the cost is independent of the volume translated.
Rule-Based Machine Translation Technology
Rule-based machine translation relies on countless built-in linguistic rules and millions of bilingual dictionaries for
each language pair.
The software parses text and creates a transitional representation from which the text in the target language is
generated. This process requires extensive lexicons with morphological, syntactic, and semantic information, and
large sets of rules. The software uses these complex rule sets and then transfers the grammatical structure of the
source language into the target language.
Translations are built on gigantic dictionaries and sophisticated linguistic rules. Users can improve the out-of-the-
box translation quality by adding their terminology into the translation process. They create user-defined dictionaries
which override the system’s default settings.
In most cases, there are two steps: an initial investment that significantly increases the quality at a limited cost, and
an ongoing investment to increase quality incrementally. While rule-based MT brings companies to the quality
threshold and beyond, the quality improvement process may be long and expensive.
Statistical Machine Translation Technology
Statistical machine translation utilizes statistical translation models whose parameters stem from the analysis of
monolingual and bilingual corpora. Building statistical translation models is a quick process, but the technology
relies heavily on existing multilingual corpora. A minimum of 2 million words for a specific domain and even more
for general language are required. Theoretically it is possible to reach the quality threshold but most companies do
not have such large amounts of existing multilingual corpora to build the necessary translation models. Additionally,
statistical machine translation is CPU intensive and requires an extensive hardware configuration to run translation
models for average performance levels.
Rule-Based MT vs. Statistical MT
Rule-based MT provides good out-of-domain quality and is by nature predictable. Dictionary-based customization
guarantees improved quality and compliance with corporate terminology. But translation results may lack the
fluency readers expect. In terms of investment, the customization cycle needed to reach the quality threshold can be
long and costly. The performance is high even on standard hardware.
Statistical MT provides good quality when large and qualified corpora are available. The translation is fluent,
meaning it reads well and therefore meets user expectations. However, the translation is neither predictable nor
consistent. Training from good corpora is automated and cheaper. But training on general language corpora, meaning
text other than the specified domain, is poor. Furthermore, statistical MT requires significant hardware to build and
manage large translation models.
Rule-Based MT Statistical MT
+ Consistent and predictable quality – Unpredictable translation quality
+ Out-of-domain translation quality – Poor out-of-domain quality
+ Knows grammatical rules – Does not know grammar
+ High performance and robustness – High CPU and disk space requirements
+ Consistency between versions – Inconsistency between versions
– Lack of fluency + Good fluency
– Hard to handle exceptions to rules + Good for catching exceptions to rules
– High development and + Rapid and cost-effective development costs provided the
customization costs required corpus exists
Given the overall requirements, there is a clear need for a third approach through which users would reach better
translation quality and high performance (similar to rule-based MT), with less investment (similar to statistical MT).
