Machine Translation: The Importance of Document-Level Evaluation

Research suggests that when it comes to evaluating entire documents, human translations are rated as more adequate and more fluent than machine translations. Human raters assessing adequacy and fluency show a stronger preference for human over machine translation when evaluating documents as compared to isolated sentences. This suggests that the way machine translation is evaluated needs to evolve away from a system where machines consider each sentence in isolation.

en flag
fr flag
de flag
pt flag
es flag

Editor’s Note: Given the increased pulse rate of discussions about the use of machine translation in support of data and legal discovery tasks, the following information pieces may be beneficial for considering, contrasting, and comparing human translations and machine translations at both the sentence level and the document level.

Human Translators Are Still On Top – For Now

An extract from an article posted on MIT Technology Review

You may have missed the popping of champagne corks and the shower of ticker tape, but in recent months computational linguists have begun to claim that neural machine translation now matches the performance of human translators.

The technique of using a neural network to translate text from one language into another has improved by leaps and bounds in recent years, thanks to the ongoing breakthroughs in machine learning and artificial intelligence. So it is not really a surprise that machines have approached the performance of humans. Indeed, computational linguists have good evidence to back up this claim.

But today, Samuel Laubli at the University of Zurich and a couple of colleagues say the champagne should go back on ice. They do not dispute their colleagues’ results but say the testing protocol fails to take account of the way humans read entire documents. When this is assessed, machines lag significantly behind humans, they say.

Read the complete article at Human Translators Are Still On Top – For Now

Has Machine Translation Achieved Human Parity? A Case for Document-Level Evaluation

An abstract from a research study by Samuel Laubli, Rico Sennrich, and Martin Volk

Recent research suggests that neural machine translation achieves parity with professional human translation on the WMT Chinese–English news translation task. We empirically test this claim with alternative evaluation protocols, contrasting the evaluation of single sentences and entire documents. In a pairwise ranking experiment, human raters assessing adequacy and fluency show a stronger preference for human over machine translation when evaluating documents as compared to isolated sentences. Our findings emphasize the need to shift towards document-level evaluation as machine translation improves to the degree that errors which are hard or impossible to spot at the sentence-level become decisive in discriminating quality of different translation outputs.

Read the complete study at Has Machine Translation Achieved Human Parity? A Case for Document-Level Evaluation

In Human vs. Machine Translation, Compare Documents, Not Sentences

An extract from an article by Gino Dino

In their paper’s conclusion, Läubli, Sennrich, and Volk explain that NMT [Neural Machine Translation] is currently at a level of fluency where BLEU (bilingual evaluation understudy) scores based on a single model translation and even evaluations of non-professional human translators of sentence-level output are no longer enough.

“As machine translation quality improves, translations will become harder to discriminate in terms of quality, and it may be time to shift towards document-level evaluation, which gives raters more context to understand the original text and its translation,” the paper’s conclusion read. It further explained that document-level evaluation shows translation errors otherwise “invisible” in a sentence-level evaluation.

Read the complete article at In Human vs. Machine Translation, Compare Documents, Not Sentences

Additional Reading

Source: ComplexDiscovery

Have a Request?

If you have information or offering requests that you would like to ask us about, please let us know and we will make our response to you a priority.

ComplexDiscovery is an online publication that highlights data and legal discovery insight and intelligence ranging from original research to aggregated news for use by business, information technology, and legal professionals. The highly targeted publication seeks to increase the collective understanding of readers regarding data and legal discovery information and issues and to provide an objective resource for considering trends, technologies, and services related to electronically stored information.

ComplexDiscovery OÜ is a technology marketing firm providing strategic planning and tactical execution expertise in support of data and legal discovery organizations. Registered as a private limited company in the European Union country of Estonia, one of the most digitally advanced countries in the world, ComplexDiscovery OÜ operates virtually worldwide to deliver marketing consulting and services.

Business as Unusual? Eighteen Observations on eDiscovery Business Confidence in the Summer of 2020

The results of the recent Summer 2020 eDiscovery Business Confidence Survey present the unfortunate and continuing impact of COVID-19 on the business of eDiscovery. However, for these pandemic-driven results to be fully understood, they should be viewed through the contextual lens of the results of all nineteen surveys that have been administered to eDiscovery professionals since the inception of the eDiscovery Business Confidence Survey in early 2016.



Check Out the Observations Now!

Interested in Contributing?

ComplexDiscovery combines original industry research with curated expert articles to create an informational resource that helps legal, business, and information technology professionals better understand the business and practice of data discovery and legal discovery.

All contributions are invested to support the development and distribution of ComplexDiscovery content. Contributors can make as many article contributions as they like, but will not be asked to register and pay until their contribution reaches $5.

Five Great Reads on eDiscovery for September 2020

From cloud forensics and cyber defense to social media and surveys,...

Time for a Change? FTC Proposes Changes to HSR Act Premerger Notification Rules

The Federal Trade Commission, with the support of the Department of...

An eDiscovery Holiday Season Down Under? Macquarie Prepares Nuix for IPO

According to John Beveridge, writing for Small Caps, Macquarie holds a...

Collaborative Cyber Defense: The U.S. Army and Estonia Sign Historic Agreement

“Estonia is a cyber country of excellence with a robust cyber...

A Running List: Top 100+ eDiscovery Providers

Based on a compilation of research from analyst firms and industry...

The eDisclosure Systems Buyers Guide – 2020 Edition (Andrew Haslam)

Authored by industry expert Andrew Haslam, the eDisclosure Buyers Guide continues...

The Race to the Starting Line? Recent Secure Remote Review Announcements

Not all secure remote review offerings are equal as the apparent...

Enabling Remote eDiscovery? A Snapshot of DaaS

Desktop as a Service (DaaS) providers are becoming important contributors to...

Home or Away? New eDiscovery Collection Market Sizing and Pricing Considerations

One of the key home (onsite) or away (remote) decisions that...

Revisions and Decisions? New Considerations for eDiscovery Secure Remote Reviews

One of the key revision and decision areas that business, legal,...

A Macro Look at Past and Projected eDiscovery Market Size from 2012 to 2024

From a macro look at past estimations of eDiscovery market size...

An eDiscovery Market Size Mashup: 2019-2024 Worldwide Software and Services Overview

While the Compound Annual Growth Rate (CAGR) for worldwide eDiscovery software...

Festive or Restive? The Fall 2020 eDiscovery Business Confidence Survey

Since January 2016, 2,189 individual responses to nineteen quarterly eDiscovery Business...

Casting a Wider Net? Predictive Coding Technologies and Protocols Survey – Fall 2020 Results

The Predictive Coding Technologies and Protocols Survey is a non-scientific semi-annual...

Business as Unusual? Eighteen Observations on eDiscovery Business Confidence in the Summer of 2020

Based on the aggregate results of nineteen past eDiscovery Business Confidence...

A Growing Concern? Budgetary Constraints and the Business of eDiscovery

In the summer of 2020, 56% of respondents viewed budgetary constraints...

An eDiscovery Holiday Season Down Under? Macquarie Prepares Nuix for IPO

According to John Beveridge, writing for Small Caps, Macquarie holds a...

ayfie to Acquire Haive

According to Johannes Stiehler, CEO of ayfie Group AS, “This acquisition...

Innovative Discovery and Integro Merge

“Integro and Innovative Discovery’s services and solutions are highly complementary. Our...

Software Growth Partners Makes Majority Investment in Venio Systems

According to the press announcement, industry analysts have enthusiastically supported this...

Five Great Reads on eDiscovery for September 2020

From cloud forensics and cyber defense to social media and surveys,...

Five Great Reads on eDiscovery for August 2020

From predictive coding and artificial intelligence to antitrust investigations and malware,...

Five Great Reads on eDiscovery for July 2020

From business confidence and operational metrics to data protection and privacy...

Five Great Reads on eDiscovery for June 2020

From collection market size updates to cloud outsourcing guidelines, the June...