October '20 Lilt Updates

by Allison Yarborough
4 Minute Read
 

Welcome to the October 2020 Newsletter. Thank you so much to all of you who came out and joined us at the end of October for Lilt Ascend 2020.

Ascend 2020 brought together leaders from across the localization industry for discussion surrounding leading successful localization orgs, the role of AI in the future of work, and exciting developments around machine translation. We heard from a number of our customer partners, MT and AI thought leaders, and last but not least from our very own Lilt colleagues.

For those who weren’t able to join us, never fear! Recordings of all conference sessions are available here. While we’re sad it’s over, Lilt has much more in the works. Read on to learn more.

• • •

Single Sign-on (SSO)

Forget your black book of passwords - single sign on is here! Convenience and ease is the name of the game with our new and improved sign-on.

SSO allows users to securely authenticate and log in to multiple applications and websites using a single username and password, saving the hassle of having to remember multiple different passwords and creating an easier customer experience.

For more information, please check out Single Sign-on in our knowledge base.

Whitespace Handling


The Lilt CAT editor now better supports the representation of whitespace characters with new hotkeys:

Non-breaking space: For non-breaking space, users can now enter it using Control + Shift + Space:

Whitespace hotkey-1

Tab: Users can now Tab indent using the → key to Tab to the right.

As a result of these hotkeys, the Tab key will now be used to enter the Tab whitespace character. MT suggestions in the editor will only autocomplete using the Enter/Return key.

Platform Quality Improvement

Every platform requires maintenance! In addition to developing new features, the Lilt Product and Engineering teams spent substantial time in October monitoring and auditing system performance, and resolving system bugs to improve platform quality and ensure optimal performance. With our continuous improvement model, Lilt strives to provide a better and better customer experience every day.

Import TMs Into the Concordance Only

While TMs have traditionally been used to train Lilt’s MT, quality and consistency of TMs can vary widely, making some less suitable as MT training sets. However, all TMs can still serve a purpose! With this feature, TMs in Lilt can be used only for search and reference without being used to train the MT. That way, TMs that may have bad entries won’t negatively affect MT performance.

 

• • •

Eager for more? Sign up for our monthly newsletter here to stay up to date on Lilt news. Thank you for reading, and thank you for translating with Lilt.

Cheers,

The Lilt Team

 

 

November '20 Lilt Updates

4 Minute Read

Read More
null

Interactive and Adaptive Computer Aided Translation

5 Minute Read

Originally published on Kirti Vashee’s blog eMpTy Pages. Lilt is an interactive and adaptive computer-aided translation tool that integrates machine translation, translation memories, and termbases into one interface that learns from translators. Using Lilt is an entirely different experience from post-editing machine translations — an experience that our users love, and one that yields substantial productivity gains without compromising quality. The first step toward using this new kind of tool is to understand how interactive and adaptive machine assistance is different from conventional MT, and how these technologies relate to exciting new developments in neural MT and deep learning. Interactive MT doesn’t just translate each segment once and leave the translator to clean up the mess. Instead, each word that the translator types into the Lilt environment is integrated into a new automatic translation suggestion in real time. While text messaging apps autocomplete words, interactive MT autocompletes whole sentences. Interactive MT actually improves translation quality. In conventional MT post-editing, the computer knows what segment will be translated, but doesn’t know anything about the phrasing decisions that a translator will make. Interactive translations are more accurate because they can observe what the translator has typed so far and update their suggestions based on all available information.

Read More