What's New in the LILT Platform
6 December 2024
Instant Video Dubbing
LILT is excited to announce Instant Video dubbing, where you can pair your existing custom models with text-to-speech and voice selection capabilities to receive a dubbed video in a new language within seconds. This offering allows you to consolidate your workflows into one easy-to-use product, expand your audience reach, and maintain brand accuracy by leveraging your fine-tuned models. Interested in learning more? Check out our announcement at our Winter AI Day: https://resources.lilt.com/ai-day-winter24-ty
Data Labeling
LILT announced the release of our Data Labeling feature at our Winter AI Day. This feature is an AI-optimized and human reinforced solution to build high-quality, reliable, and multilingual training data sets used to train foundational Large Language Models. We designed this feature for the world’s leading Generative AI companies, and we are working with those companies to train their foundational LLMs. LILT Label can help:
Expand your data pool - Training LLMs on non-English languages helps avoid biases and apply cultural nuances in a secure environment.
Ensure data quality, because our responses are sourced from native-speaking, domain experts to ensure accuracy and quality.
Accelerate the labeling process, with dedicated interfaces to intuitively build and annotate data.
To learn more, check out our announcement at our Winter AI Day: https://resources.lilt.com/ai-day-winter24-ty
22 November 2024
LILT Translate
Improved Tag Projection
LILT is excited to announce updates to our tag projection functionality, which improves the overall quality of tag projection and allows linguists to spend less time on adjustment.
Previously, tags were projected by computing a word alignment on the tag-stripped source/target using a variant of our V1 models, then used a rule-based approach to transfer tags based on word alignments. With this new update, tags are projected using a single, multilingual projection model that directly generates the target sentence with tags, without the detour through word alignment.
For more information on our Research Team's work on tag projection, see this article.
Linguist Stats Data Refresh
Linguists now have visibility into when the data in Linguist stats was last refreshed, to provide visibility into how recent the data is.
8 November 2024
Security and Stability Improvements
We fixed 90+ issues related to security and stability so that our customers would have a more delightful experience.
Translation Consistency & Performance Enhancements
We've improved the handling of batch updates and resolved translation inconsistencies, ensuring greater accuracy in translation quality.
Addressed timeout and performance issues in AutoMQM and Instant Translate features.
User Experience & Interface Enhancements
Enhanced the UI across multiple areas, ensuring consistency with our design system. Notable fixes include copy/paste functionality, action button alignment, and improved handling of notifications and tooltips.
Updated the Create page and other components for a cleaner, more intuitive interface.
Connector & Integration Updates
Added Box to our Connector Builder for seamless integration.
Fixed encoding issues in XTM custom MT integration
Improved Contentful workflow, including publishing and translation warnings.
Domains & Permissions
Improved user access and permission handling in Domains, with fixes for non-Admin behavior and verification processes.
Job & Document Management Improvements
Enhanced document handling, ensuring large batch jobs and project details load efficiently and correctly.
Technical & Performance Fixes
Addressed load performance issues, specifically for Figma projects and the Linguist Homepage.
Removed outdated dependencies to improve system reliability and responsiveness.
We continue to prioritize your feedback and are committed to delivering a better experience with every update. Thank you for your continued support and insights!
1 November 2024
LILT Manage
LILT’s new Domains feature enhances workflow segmentation, allowing organizations to create distinct operational areas within LILT. By assigning resources such as users, models, and preferences to specific domains, administrators can customize experiences to improve productivity, focus, and data privacy for each user group.
What’s New?
Customizable Domains
Domains allow administrators to segment LILT by operational areas, facilitating tailored experiences across teams or departments.
Enhanced User Personalization
Users can switch between assigned domains, with interfaces updating to reflect models, file loaders, and translation jobs associated with the active domain.
Advanced Administrative Control
Administrators can set up, manage, and delete domains, assigning specific resources such as users, models, and preferences.
Default languages, workflows, and file loaders can be specified per domain.
Domain-Specific Analytics and Job Filtering
Analytics and job management views are filtered based on the active domain, making it easier for users and admins to manage tasks and track progress relevant to their domain.
4 October 2024
LILT Translate
Assign Domains as Secondary Reviewers
LILT is excited to announce updated assignment functionality where project opportunities can be presented to multiple Secondary Reviewers. With this update, Secondary Reviewers identify which languages they support in their LILT profile, and are then assigned to domains. LILT can then assign a domain as a Secondary Reviewer, which would share the opportunity with all those qualified and Secondary Reviewers can accept projects based on their availability. For more information, please visit https://support.lilt.com/kb/customer-review#SecondaryReview-SecondaryReviewerassignmentsthroughdomains.
Please note: This feature is in beta and will be available for all orgs in early November. If you would like to use this feature before then, please reach out to your LILT Account Team to learn more.
Additional data in Concordance search and Data Source download
Concordance searches now display additional data: Creation date, Updated date, Created by (name/email), Updated by (name/email), and the file name from which it was created. This allows users to understand who accepted and confirmed segments into their data sources. Only those with the User Visibility permission set are allowed to see the names and emails of those who created or updated the entry. This data is now also available for managers and admins in the Data Source download.
LILT Connect
LILT is now on the Box App Center!
We're excited to announce that Lilt is now available on the Box App Center, making it easier than ever to integrate your translation workflow directly with Box. With this integration, you can seamlessly manage and translate content stored in Box, streamlining localization processes for global teams. Try it today and experience efficient, high-quality translations right from your Box environment.
LILT Manage
Edit Model Names
You can now edit the names of your model based on your preferred naming conversations for your teams.
20 September 2024
LILT Translate
Recently used language options
LILT is excited to introduce a feature improvement to our language dropdown menu that shows customers their most recently used languages when submitting projects for translation. Previously, customers needed to search for languages every time they went to submit new projects. With this update, their recently used languages are more accessible.
Project-level setting for Copy/Paste
LILT Translate now has a project-level setting to define the usage of Copy/Paste. All new projects inherit the organization setting by default, but can be adjusted at the project level. To learn more about the Copy/Paste setting, please visit the the Organization Settings page.
LILT Manage
New LLM Support
We’ve grown the number of models we support in LILT!
New LLM Services for LILT Create
OpenAI
GPT-4o
GPT-4o-mini
Anthropic
Claude 3.5 Sonnet
Claude 3 Haiku
Claude 3 Sonnet
Claude 3 Opus
AI21 Labs
Jamba-Instruct
Jurassic-2 Ultra
Jurassic-2 Mid
Gemini 1.0 Ultra
Gemini 1.5 Pro
Gemini 1.0 Pro
Gemini 1.0 Nano
Gemini 1.5 Flash
PaLM 2
New LLM Services for LILT Translate
GPT-4
GPT-4o
GPT-4o-mini
LILT Connect
Contentful x LILT Connector Updates:
Support for Rich Text Embedding
We are introducing a new feature for the Contentful x Lilt connector to better support embedded entries within Rich Text fields. With this update, the connector will automatically recognize and include embedded entries in the translation process, just like linked entries. This enhancement will eliminate the need for manual intervention, ensuring a smoother and more efficient localization workflow for content that includes embedded assets.
Default Locale
We are working on an update to address issues with the Contentful x Lilt connector for customers using a default locale other than en-US. Currently, when a customer’s default locale is set to a different variant, such as en, the connector does not operate as expected. While a force extract is possible, it does not allow for content to be sent organically using this source language, and the workflow statuses in Contentful are not updated properly.
This update will ensure the connector can seamlessly handle non-en-US default locales, allowing for efficient content management and status updates, even at scale with multiple stakeholders involved.
Auto-publish upon Delivery
We are introducing a new feature in the Contentful x Lilt connector that allows content to be automatically published upon delivery from Lilt to Contentful. With this option, once translations are completed and delivered back into Contentful, the content can be immediately published without requiring manual intervention. This streamlines the content publishing process, saving time and ensuring quicker go-to-market for localized content.
31 August 2024
LILT Translate
V3 Model Release for PT > EN
LILT is excited to introduce an improved and larger Translation and Adaptation V3 model for Portuguese (PT) > English (EN). We will be releasing additional V3 models. Please visit our Supported Languages page for more information on our available languages and models.
New Keyboard Shortcut
LILT released a new keyboard shortcut that will insert the top TM entry from the CAT sidebar into the segment editor. Use Ctrl + Shift + S to insert.
Setting to Automatically Run Batch QA
We released a new sub-setting for Mandatory Batch QA that would automatically run Batch QA. When this is enabled, Batch QA will run immediately after the selected workflow step is completed. For more information, please visit the Mandatory Batch QA KB page.
24 August 2024
LILT Connect
LILT x Shopify Connector Updates:
Shopify - Feature to Select Only Active Products
Added an option to filter and select only active products within the Shopify connector. This improvement enhances the user experience by allowing more granular control over product selection during the translation process.
LILT Shopify App Not Showing Metaobjects
Fixed a bug where metaobjects were not being displayed in the True Classic LILT Shopify App. This correction ensures that all relevant data is visible to users, improving the user experience.
Adjust All Products Filtering
Enhanced the product filtering capabilities to provide more comprehensive options within the Shopify connector. The improvements include:
Product Count: Added a count of available products within each section for better visibility and management.
Filter Updates: Changed the filter label from "All Active Products" to "All Products" to reflect the inclusion of all product statuses.
Selection Options: Introduced new filtering options, allowing users to select between "All Active," "All Archived," and "All Draft" products, offering more granular control over product data management.
Shopify Connector Import Issues
Addressed urgent issues related to product import functionality within the Shopify Connector. This critical fix resolves import errors that were affecting data synchronization.
Shopify Connector - Export Products by Tag
Added a new feature to export products based on tags in the Shopify Connector. This functionality enables more targeted data exports, enhancing the ability to manage and utilize product data.
LILT x S3 Connector Updates
Duplicate Projects Created During Connector Job
Fixed an issue where duplicate projects were being created during connector jobs. This correction ensures that only a single project is generated per job, preventing redundancy and reducing confusion in project management.
Expand S3 to Select Source Based on a Directory Path
Enhanced the S3 storage-based connector to allow users to select the source based on a specific directory path. This update provides greater flexibility in defining the source data, making it easier to manage large datasets within S3.
Add Ability to Create/Set a File-Level Metadata Field When Returning Target Files
Introduced the ability to create or set metadata fields at the file level when returning target files. This enhancement allows users to attach custom metadata to files, enabling better organization and retrieval of data within S3.
Allow the S3 connector to Use a Different Bucket for Outputs
Updated the rclone-based S3 connector to support using a different bucket for output files. This feature provides more control over where processed data is stored, improving flexibility in managing output destinations.
LILT Translate
Updated default roles - Customer, and Customer + LILT Create
To better reflect the needs of our platform customers, we’ve updated LILT’s default roles so there are two customer roles - Customer, and Customer + LILT Create. This differentiates which users have LILT Create permissions. Both of these roles also had the “User visibility” permission revoked so as to not reveal sensitive information. For more details, please reference https://support.lilt.com/kb/default-roles.
16 August 2024
LILT Translate
Customer Review is now Secondary Review
We’ve updated our product verbiage to better reflect our customers' workflows, and we’ve renamed the Customer Review stage to Secondary Review.
Overwrite confirmed segments for Secondary Review
Forward and backward overwrite confirmed segments is now available in the Secondary Review stage. These are enabled by default, as they are for existing workflow stages.
Keyboard shortcut to insert top TM entry
Linguists and customers now have a keyboard shortcut to insert (copy & paste) the top TM entry from the CAT sidebar into the CAT editor - “Ctrl + Shift + S”.
Reordered segment context panel
The segment context panel has been reorganized to reflect the importance of information during translation. The blocks now display TM results, Termbase results, and MT results.
Word count in linguist assignment emails
LILT has added data to linguist assignment emails to provide further details. Translation assignment emails now include the number of Exact Match words across the project. Review assignment emails now include the number of Repetitions & Exact Match words across the project.
LILT Financial File Download
We are excited to introduce a new feature that allows you to download your monthly financial report directly from the LILT platform. This report will help you easily track your localization spending and stay on top of your financials.
Format: The report is available in Excel format.
Availability: You can download the report every month. And this is available on a per-customer basis - please contact LILT sales with any questions regarding access.
This enhancement is designed to provide you with greater transparency and control over your localization budget.
19 July 2024
LILT Translate
Additional V2 language model
LILT is happy to announce the release of our updated V2 language model for ja > en. Our models expand LILT’s capability to delivery high quality low cost translations. Learn more about LILT’s supported languages.
Block copy and paste functionality
LILT Translate now supports blocking any usage of copy and paste. This will prevent all copy and pasting within source and target text, and can be applied through the org settings page. For more information, please visit the Organization Settings page.
12 July 2024
Show target tags
LILT Translate now has an additional visibility setting to allow linguists to hide tags from target segments, specifically in cases where they act as a nuisance and make it hard to understand the target content. By default, tags are still shown in target segments and QA still checks for tag errors.
For more information, please refer to the Display settings section of the Tags & Formatting page.
28 June 2024
Analytics V2
LILT Analytics offers a detailed view of translation accuracy, quality, and efficiency. By monitoring these metrics, users can identify areas for improvement, track progress over time, and ensure high-quality translations across various language pairs and connectors.
Style guide
LILT is excited to announce our new in-app style guide, which helps provide a consistent brand voice across LILT Translate and LILT Create. This functionality enables you to document style-related details that will display to linguists in LILT Translate and will be used as the style guide for LILT Create. For more information, please review the Organization settings page.
Updated workflow setting to unlock locked segments
LILT has a new workflow setting to allow unlocking locked segments. This is intended as a safety valve specifically for Reviewers and Secondary Reviewers if errors are spotted during their review so they can quickly and easily correct any errors present. For more information, please review the feature information in the Organization settings page.
14 June 2024
Microsoft authorization
LILT is excited to announce our integration with with Microsoft for authentication with Active Directory and Azure. This will enable customers to securely login to LILT using their Microsoft authentication protocols. For more information see our Single Sign-On page.
7 June 2024
OCR improvements
Much of the world’s text is locked in images which cannot be easily translated. With LILT’s new end-to-end image translation workflows and processing capabilities, you can use the tool of your choice to extract text from images and begin translation. Additionally, we improved the user experience of uploading multiple images and created more robust segmentation rules so that you can consistently see and edit source text as a sentence or paragraph. Learn more on our Image and Scanned PDF File Translation page.
24 May 2024
Instant > Review > Secondary Review workflow
We have released a new workflow, available for all organizations. This workflow leverage’s LILT’s machine translation to offer suggestions and our CAT editor for linguist and secondary review. This is a capability that leverages both human and machine intelligence for translation.
Domains
LILT is excited to offer a new model management tool called Domains which will simplify both job creation and model management. With this new tool, administrators can group models into specific domains, and assign these domains to certain users. You can then have a personalized self-service application which shows a custom list of models tailored to their translation needs.
10 May 2024
LILT Connect
File Loaders (Custom File Processing)
We're excited to introduce File Loaders, a powerful new feature for managers and administrators. Now, you can upload, apply, and manage organization-specific file loaders directly within the LILT platform, streamlining your translation workflow. With this update, you can easily create new configurations, set default loaders per file type, override automated suggestions, and delete unnecessary loaders. If no custom loader is selected, LILT will continue to use the Okapi default loader as before. Enjoy a more tailored translation experience with this latest enhancement!
WorkDocs Connector
We're thrilled to announce the new LILT Connector for Amazon WorkDocs, offering seamless integration between LILT’s translation services and Amazon's secure, fully managed file storage platform. With this connector, users can now efficiently manage translation workflows directly within their Amazon WorkDocs cloud storage environment. Documents stored in Amazon WorkDocs can be automatically sent to LILT for translation and securely received back for streamlined productivity and collaboration across global teams.
26 April 2024
New workflow setting to unlock exact matches
LILT has a new workflow setting to allow unlocking exact matches. This is intended as a safety valve specifically for Secondary Reviewers if errors are spotted during their review so they can quickly and easily correct any errors present. For more information, please review the feature information in the Organization settings page.
12 April 2024
Knowledge base update
We’ve updated several pages in our knowledge base. The updated knowledge base is now available, making it easier to find help with the LILT platform.
05 April 2024
LILT Translate
Advanced jobs page filters and sorts
Users can now filter the homepage by delivery dates, creation dates, and job statuses. In addition, users can sort the page based on due date, creation date, and job name. These new page management tools will enable teams to easily find the needed job.
14 March 2024
Linguist Stats Update
Linguist Stats will now include updates to payments for offline work in addition to online work!
Read more here: https://support.LILT.com/kb/linguist-stats
08 March 2024
LILT Platform
LILT Palantir FedStart Integration
We are excited to announce an integration with Palantir FedStart. This integration will allow linguists, analysts, language managers, and project managers working on GovCloud IL4/IL5 environments to utilize LILT software to efficiently translate material! Please reach out to your account executive for more details!
LILT Connect
LILT Connect Workflows
Introducing LILT Connect Workflows: a dynamic solution that empowers you to configure and tailor workflows to meet your specific enterprise requirements. Seamlessly integrate with the connectors you already use at LILT for enhanced efficiency and customization. We have expanded the number of connectors in Workflows by 10x, covering the vast majority of day to day connector needs. Effectively overseeing multiple localization projects within your organization and guaranteeing timely delivery can be a time-consuming endeavor. This powerful tool empowers you with unmatched speed and comprehensive control throughout the entirety of the localization process by enabling you to configure your own workflows to meet specific enterprise requirements. Now, you will be able to access that functionality in top CMS’ and TMS’ such as Contentful, Lokalise, Crowdin, Smartling, Google Drive, Github, and Braze.
16 February 2024
LILT Translate
Today, we are introducing exciting updates to the LILT Platform as a follow-up to our initial release on AI Day 4.
LLM Evaluations in AI Hub
Firstly, we are introducing LLM evaluations in AI Hub, aimed at helping customers understand which model providers they should be choosing for their respective translation workflows, depending on parameters such as privacy requirements, content type, fine-tuning capabilities, and more.
New OCR, ASR, and GenAI providers
We are also adding transcription and translation services for video content, so that customers can upload video files similarly to our existing image, PDF, and audio workflow support. Additionally, we now offer interoperability with several new providers for generative content, OCR, and ASR.
9 February 2024
LILT Translate
Plurals V2
LILT is excited to announce our second release of ICU and plurals support. With this release we will support all ICU formats including plurals, select, select-ordinals, date, time, and number. In addition we will support Android plurals and iOS plurals. These formats will automatically be processed by our backend system and displayed to linguists in an easy to use modal. With these improvements we should see increases in our quality and delivery timelines!
Linguist Homepage
The Linguist homepage is a completely redesigned homepage for linguists. The designs were optimized for simple navigation and project prioritization. On the Linguist Homepage, linguists can see due date, customer name, project stage, total segments, and completion percentage for each individual document. These documents can be organized into completion states, quickly filtered, and easily ordered. All these improvements enable linguists to quickly sort through their documents, find the most important job, and start translating!
19 January 2024
LILT Translate
We launched a new project-level setting to Include Exact Matches in the Secondary Review sample. Previously, we only had an Organization Setting, where this can now be customized and set on a per-project basis in Project settings. The project-level setting will match the org setting by default, but can be modified. Changing the default setting for review sampling in the Organization Settings does not update the settings of existing projects. Read more about Review Sampling here.
12 January 2024
LILT Translate
We have added a feature to disable MT suggestions from CAT suggestions and the CAT sidebar. This can be controlled in the organization settings under “Translate settings”. Disabling MT is most commonly used for creating training data sets, where the goal is to have no bias from other machine translation tools.
22 December 2023
LILT Translate
New Language Models
LILT is happy to announce the following new language models:
Kurdish to English
Vietnamese to English
Nepalese to English
These models expand LILT’s capability to delivery high quality low cost translations!
Instant > Review Workflow
This workflow leverage’s LILT’s machine translation to offer suggestions and our CAT editor for linguist review. This is a capability that leverages both human and machine intelligence for translation.
New QA Checks
LILT has released three new automated checks in Batch QA and Full QA:
Unpaired symbols - This QA check will check for unpaired symbols in the target text, for example, an opening bracket
(
without a closing bracket)
.Case matching - This QA check will check that the case in the source text matches the case in the target text and will point out any errors, i.e. a sentence starting with a lowercase letter or a word written in all caps.
Alphanumeric mismatches - This QA check will check that 'enclosed' alphanumeric characters (such as ③ ⑵ ⒋ ⒝ Ⓔ ⓭ ⓹) match in the source text and the translation. The enclosed characters are in the Unicode range of 0x2460 to 0x24FF.
LILT Connect
LILT is excited to announce a partnership between KalciumQT and LILT! KalciumQT is a terminology management software. With LILT’s new integration, linguists using LILT will have the opportunity to sync terminology between Kalcium and LILT. Allowing them to utilize the most up-to-date terminology across their systems.
15 December 2023
Overview
The LILT Platform release at AI Day 4 marks a transformative milestone, delivering an array of features and use cases designed to redefine your enterprise translation and multilingual content creation experience - focused on giving you, the user, more access than ever before. This release introduces groundbreaking capabilities focused on enterprise AI deployment and control features, including LLM orchestration, multimodal translation capabilities, and content generation prompt templates for teams and use cases.
LILT Homepage
Begin your multilingual journey with our brand new homepage, where we make it as easy as possible to get started using LILT’s various offerings. The redesign is centered around one question, “what do you want to do?”. Whether that’s translating an existing piece of content, creating something new, connecting systems to your workflows, or managing a series of functionalities, we now enable all of these use cases in a single, cohesive platform.
LILT Translate
The translate functionality is what most of LILT’s users are already familiar with, and we’re excited to introduce some brand new capabilities, primarily multi-modality and self-serve 3rd party MT integrations.
Expanded Translation Capabilities: Seamlessly translate all file types, including image, audio, PDF, and video, within the LILT platform. Address a wide range of media so whether you need to translate a PDF report, a picture of a text chart, an audio recording from a conference, or a video recording from a talk, you can now do it all in one place in LILT.
Choose your Translation Workflow: Instant and Verified Translation workflows supported for all file types.
Model Interoperability: Translate with LILT or your 3rd party translation model of choice.
Models include
Google Cloud
DeepL
Amazon AWS
LILT Create
LILT Create is our multilingual content generation product that allows users to quickly create on-brand, locally relevant content in any language. Starting today, get started with your multilingual content generation quicker than ever before with Create Prompt Templates.
Content Generation Prompt Templates
With Prompt Templates, you can create multilingual content on pre-trained guided prompt templates for your specific use case.
Predefined Content Creation: Leverage prompt templates for instant content generation in 100+ languages.
Use Cases Across Teams: Address specific use cases across Marketing, Sales, Legal, HR, and Support. Three templates are available today, with many more coming in Q1 '24.
Create Content with Your LLMs of Choice: Integrations with the following LLM providers
Amazon Titan-G1
OpenAI GPT3, GPT3.5, and GPT4
LILT Connect
Now that we’ve gone through some applications in the LILT platform, we’ll transition to where we give you access to your own control room, where you can manage your workflows, data, security, and models.
The first is LILT Connect which enables you to set up and manage your own automated connector workflows with your content systems. We’ve always supported a plethora of connectors, but what’s really exciting today is that you can configure and manage these connectors all on your own, with virtually no technical support.
Connect Workflows
LILT Connect integrates with over 40 Content Systems including CMS’ like Contentful, TMS’ like Crowdin and Smartling, Storage files like S3 and Google Drive, Repos like Github and Gitlab, and many more. Today, you can get started on creating your own connector workflow by just selecting one of these cards and deciding what system you want to integrate with.
After you’ve selected your connector, you can select your desired workflow from the following options: AI + Review, Verified Translate, Verified Translate + Review, Verified Translate + Review + Secondary Review.
Finally, not only can you choose your own workflow, you can fully customize individual steps within your end-to-end connector configuration.
LILT Manage
LILT Manage is your Control Room, where you can manage your data and model inputs. Set up, own, and manage your data. Privacy is a critical part of LILT’s offering here, supporting government and on-prem customers, and this is something that’s critical to LILT’s platform offering as well.
Manage Data Sources & LILT Models
Additionally, you can manage your fine-tuned models as well. What this means is that you may have a foundation model like AWS supporting your translation needs, and combine that with your LILT memories, and finally add LILT’s contextual AI for your English-French translations. All of that will be managed in your Model Hub. Thus, you can maintain brand preferences, guidelines, memories, and more for consistent quality with LILT and 3rd party providers.
Large Language Models & Interoperability
Enable and configure third-party Language Model Managers (LLMs) integrations within LILT for diverse business use cases.
8 December 2023
LILT Connect
Lokalise
We’ve made some exciting updates to the LILT <> Lokalise connector! These changes primarily focus on the ability to provide additional context for linguists:
Ability to extract “Key names” from Lokalise
Ability to add Key name to metadata for respective segment in LILT
Ability to add Character Limit to metadata for respective segment
All of these changes are focused on improving quality! To learn more about our Lokalise connector click here.
Smartling
We're excited to introduce significant enhancements to the LILT <> Smartling connector, optimizing translation management for a more seamless experience. Effortlessly synchronize both term bases and segments from Smartling to LILT. This update includes:
Termbase Sync Enhancements
Prevent duplicate termbase entries, ensuring a streamlined workflow.
Update targets without creating new entries when the source remains constant.
Data Source Sync Enhancements
Ensure a cleaner process by preventing duplicates during segment synchronization.
Avoid duplicate records when both source and target match an existing LILT segment entry, enhancing overall data integrity.
In addition to Termbase and Data source enhancements, we’re excited to share that LILT is now an official MT partner and provider on the Smartling TMS, joining other providers such as Microsoft, Google, and Amazon.
When utilizing LILT via Smartling, please note that:
If using LILT for your verification step, the models will continue to be adapted through the customer’s human verification workflow.
If using LILT for your instant translation workflow, translations will not be saved to data sources, so no need to push data back for LILT model adaption.
Learn more about our connectors here.
LILT Translate
Expanded ICU Support
LILT now supports fully automated filters for ICU select formats. This expanded automation will help us support product strings or support documentation content types. To learn more about LILT’s ICU support click here.
1 December 2023
LILT Create
Homepage and new content type
We’re excited to share LILT Create’s new homepage, where regional teams can generate enterprise-grade multilingual content for Marketing and Training Course content types (with additional content types coming soon!). Combining style guides and existing LILT data sources with real-time user prompts, LILT Create can generate brand-aligned content in a matter of seconds for users to refine and finalize. Learn more about how to use LILT Create here.
LILT Translate
Exact matches in review sampling
The org and project settings for exact matches in review sampling are both now “Include exact matches: When running review sampling, include exact matches from the sample.” Existing project settings were updated so they have the same settings as before we made the update. Learn more about review sampling here.
Linguist stats
The linguist stats page is now turned on for all linguists, providing information on payment data and hours worked, broken down by project and document. Learn more about Linguist stats here.
New Error Categories, Sub-Categories, and Severities
LILT has launched updates to our error logging to reflect Multidimensional Quality Metrics (MQM) standards. When logging an error, linguists will now apply a category, sub-category, severity, and comment. There is no change to permissions or visibility - existing permissions for translators, reviewers, and secondary reviewers remain. Learn more about error flagging in Review mode here.
Connectors
LILT Create in Contentful
LILT Create is now integrated into the Contentful app ecosystem, which allows creation of on-brand, AI-generated multilingual content directly within Contentful's content models, saving time and streamlining workflows. Because LILT specializes in brand-specific translation, users can generate content across any number of languages with the same prompt - making content ready to publish globally in partnership with regional marketing teams significantly faster than possible through traditional translation workflows. Learn more about LILT Create in Contentful here.
Shopify
The LILT <> Shopify Connector can help expand your store accessibility to international markets by bridging language barriers with LILT’s translation services. With this connector, you can:
Translate all of your site’s content, including product descriptions, checkout pages, and customer service messages.
Choose from 60+ languages to cater to your target audience’s needs.
Preview translations for accuracy and brand suitability before publishing.
Learn more about our LILT <> Shopify Connector and our packaged-based pricing model here.
GitHub
We’ve made a number of improvements to our LILT <> GitHub Connector:
LILT’s GitHub Connector labels PRs for clear tracking of file status in your translation workflow.
We now automatically excludes unchanged files, with an optional manual inclusion.
Learn more about our LILT <> GitHub Connector here.
19 October 2023
LILT Translate
New QA Check
LILT has released a Terminology Verification QA check in Batch QA and full QA, which validates if terms in the source text have been translated correctly in the target text according to customers' glossaries/termbases.
Concordance Search Improvements
Public data has been removed from Concordance Search and the CAT editor sidebar. It now only displays TM and partial matches.
Tag UX Improvements
We’ve implemented a visual distinction between the opening tag of a pair and a solo self-closing tag. Solo tags are rectangular.
Connectors
New LILT Connectors
Magento - The LILT <> Magento Connector can help you expand your store accessibility to international markets by bridging language barriers with LILT’s translation services, and is now available in the Adobe Commerce Store. Learn more about the LILT <> Magento Connector here.
Braze - The LILT <> Braze Connector is now available upon request. Please contact your Account Executive for more information.
Sitecore - The LILT <> Sitecore Connector is now available upon request. Please contact your Account Executive for more information.
Connector Improvements
Contentful
We’ve made a number of improvements to our LILT <> Contentful connector:
We’ve made it easier to work with nested (or “child”) entries, where you can see all the selected projects prior to sending for localization and add any missing nested projects by selecting them from their content page.
We’ve now made it so you can edit the content type for each project prior to “Sending for localization”.
Shopify
The LILT <> Shopify Connector is now available on the Shopify Marketplace! Learn more about our pricing and packages here.
19 September 2023
At LILT’s third AI Day, we announced our latest innovations, including third-party large language model integration in the Contextual AI Engine, self-serve model building and training, and advanced program analytics. As leading enterprises rush to implement a global AI and LLM strategy, LILT’s Contextual AI Platform offers a quick and scalable path to achieving extraordinary ROI from AI.
Enterprise Portal with Advanced Analytics
We're excited to present LILT’s Enterprise Portal - a home base for localization teams to quickly understand program-level insights of your work with LILT, view status updates for projects, and build your AI translation strategy.
When you log into LILT’s platform, you will see the Program Insights dashboard that provides in-depth insights into your operations. This user-friendly tool offers customizable visualizations of vital metrics and strategic insights, empowering you to make key decisions and optimize your Localization/AI strategy, quality, and impact.
You’ll also have access to a self-service job intake portal to submit content for Verified or Instant Translation, and a detailed view of all active and delivered jobs that have run through LILT’s Contextual AI platform.
3rd party support for the Contextual AI Engine
LILT’s newest foundation model integration enables customers to harness Amazon Translate, DeepL, and Google Translate models right within the LILT Platform. This third-party LLM support pairs enterprise LLM preferences with LILT’s proven production processes, linguists, and Translate tool - providing the highest quality Instant Translation for your use case.
Use the LILT platform to configure your existing LLM to access it via LILT, including supported capabilities for fine-tuning and terminology support connected to LILT’s Data Sources.
Model Builder
Once configured, 3rd party LLMs will be available through LILT Model Builder, a new management feature within the platform’s orchestration layer. Model Builder enables fine-tuning of third-party LLMs to be used in the LILT Contextual AI Engine. The LILT Platform has historically enabled model fine-tuning for LILT’s proprietary LLMs, with a continuous training cycle that feeds training data to models in real time as human translators and verifiers perform work in the platform. With Model Builder, LILT customers can now apply that same quality-verified training data to fine-tuning of third-party LLMs. You can fine-tune your models in just a click with LILT’s model building and training interface, optimizing model quality on the cadence of days or weeks instead of months or years.
31 August 2023
LILT Translate
New QA Checks
LILT has released 6 new types of automated checks in the Batch QA feature:
1. Untranslated segments
2. Target text identical to source
3. Repeated words in the target
4. Target x% longer than source
5. Target x% shorter than source
6. Tag order mismatch between source and target
Batch QA is also now available in the Secondary Review stage in addition to Translation and Review stages of the workflow.
Tag UX Improvements
LILT’s CAT editor now supports visually expanding all tags in the active document to display tag content. Linguists use this tool for easier tag placement and, ultimately, better translation quality.
Visual indicators for Termbase mismatches
To support high-quality, on-brand translation, LILT’s CAT editor now goes a step further to highlight segment words with green and red visual indicators for termbase matches and mismatches, respectively.
Connectors
Figma Connector Improvements
The LILT <> Figma Connector has some fresh updates! We’ve visually redesigned the UI of the connector, and included a number of functional improvements.
We’ve made it easier to multi-select pages for translation, and also support selection of multiple target languages for the same selection/order. Target pages will be automatically created for all new languages selected, making the translation process for design files faster than ever before.
Learn more about the LILT <> Figma Connector here.
Phrase TMS Connector Improvements
We’ve made a number of improvements to our LILT <> Phrase Connector.
1. Updating all the relevant intermediary workflow steps’ statuses in Phrase with their respective progress
2. Mapping distinct domain Data Sources based on the Content Type indicated in the Project Name
3. Transferring segment statuses set in Phrase TMS to LILT’s CAT Editor for linguists to reference
Github Connector Improvements
LILT’s GitHub Connector now controls for which files are excluded from translation jobs. It will only select files changed from the specified PR unless there is a specific parameter to manually include it. Additionally, the connector now adds a label to the PR when it exports the source files to LILT to ensure there’s clarity of where files stand in the translation workflow.
Other Updates
Navigation changes
You can now find the “Jobs” page as “Verified” under the “Contextual AI” tab in the navigation.
Q2 2023
The LILT team has been developing new and exciting features over the past quarter. We’re eager to announce…
LILT Create
In June 2023, LILT announced the launch of LILT Create, a multilingual writing tool. LILT Create enables regional teams to quickly and directly create brand-aligned, enterprise grade content in any language.
Combining historical preferences with real-time user prompts, LILT Create generates formatted content in a matter of seconds for users to refine and finalize. With Create, regional teams can produce content that’s tailored not only to company but also to locale.
Read our press release and blog post about the LILT Create launch! And learn more about how to use the LILT Create product here.
Plurals
Plurals are a mechanism of language that allows a speaker or writer to differentiate types of nouns or phrases. In English we have two plural forms singular and plural. However, English forms are just the beginning, in Arabic there are six different forms. In Q2 2023, LILT released features for automated support for the ICU plurals syntax. Users can upload files with the ICU syntax, easily translate, and export with correct formatting. This can be used for website pages that personalize the language based on dynamic values (e.g. 1 computer vs 2 computers). LILT’s Verified Translation workflow enables linguists to quickly view and update all translations needed to support this type of use case.
Learn more about LILT’s support of Plurals here.
Connectors
Trados Enterprise
LILT has released a new connector integration for Trados Enterprise TMS, enabling users to work where their content lives, and send Instant and Verified Translation jobs to LILT. In addition to triggering translation work, the integration includes robust sync features for translation memory and termbase data to transfer to and from LILT Data Sources and align to specified domains.
Learn more about the LILT <> Trados Enterprise Connector here.
Bitbucket
Your team can now streamline localization by sending content for translation and receiving localized content from inside Bitbucket. Avoid manual steps and the inconvenience of transferring content back and forth between platforms by translating directly in your preferred code hosting platform.
Learn more about the LILT <> Bitbucket Connector here.
Crowdin → Data Source Sync
Our Crowdin connector now supports a Data Source sync process that ensure that all of the latest translation memory entries in your TMS are sent to LILT to optimize leverage, translation quality and consistency.
Learn more about the LILT <> Crowdin Connector here.
Contentful → Nested Entry Support
LILT now supports the automatic inclusion of nested entries within the selection in the Contentful connector. This means fewer clicks to order the translation jobs needed!
Learn more about the LILT <> Contentful Connector here.
Instant Translation Available in Connectors
LILT customers have loved the versatility of our Dual Method Connectors, which allow content creators to send content for Verified or Instant Translation, depending on the project needs.
All LILT Connectors are now capable of supporting both Instant and Verified Translation. Whether you need translated content in minutes or quality-guaranteed content in hours, LILT Connectors can support your varied translation needs.
Q1 2023
We're excited to announce the newest features and improvements to the LILT Platform in this quarter!
Visual Redesign
We've overhauled the interface to be sleek, modern, and optimized for accessing key areas of the platform. Here’s what you can find under each tab.
Jobs: A nested list of jobs, projects, and documents. Context-specific actions and sub-tabs are on the main pane of the screen with secondary navigation along the top, and action buttons in the top right.
Data: Memories and Termbases.
Contextual AI: Your system’s Contextual AI models that power your LILT translation behind the scenes, per language-pair, with links to the associated translation memory. If you have account permissions to view Instant Translate, it is also listed. We’ve also released a feature to train new models. Reach out to your LILT account team to learn more!
Observability: Reports depending on your role permissions. Linguists can find the Linguist Stats report here; others can find program-level insights.
Organization: Admins and users with the necessary role permissions can manage settings, users, and role permissions under this tab.
Connect: Available LILT connectors, and your organization's API key for use in integrations.
Other Navigation: Found at the bottom of the page. Click your avatar to change profile settings and logout. Access LILT’s Knowledge Base through the icon, and see inbox notifications.
New and Improved Connectors
Phrase TMS (formerly Memsource): LILT’s new Phrase TMS (formerly Memsource) connector enables transfer of content directly from the Phrase interface to LILT for translation. The connector integrates status updates for tracking directly within Phrase, so requesters can maintain their entire workflow in their TMS of choice.
Salesforce Email Templates: Within Salesforce Service Cloud, customer support agents can use email templates to provide ‘canned responses’ to common questions. LILT has a new connector that connects Salesforce and the LILT platform to support sending and receiving this content for translation in LILT.
Termweb: LILT’s new Termweb connector enables a centralized termbase (in Termweb) to be transferred to LILT at a regular cadence. This helps LILT leverage the latest terms through its Contextual AI models.
Azure Blob: We’ve released a new connector to automatically push and pull content between Azure Blob and LILT. This creates efficiencies by providing seamless localization without transferring content out of your file-storage solution of choice.
Jira integration enhancements: We’ve made improvements to our Jira integration to support project-level status tracking as well as additional transfer of metadata, such as inclusion of language-locale codes, requester names, and due dates.
Improvements to Existing Features
We've also made several improvements to existing features in the LILT Platform based on user feedback. Here are some of the highlights:
Translation memory (TM) deduplication, which automatically identifies and removes duplicate records during import and export of .TMX files. This helps you keep assets clean and accurate, and saves you time by eliminating the need for manual deduplication.
Full document rejection during review without the need complete error annotations across all segments. To learn more, reach out to your LILT account team.
Robust CAT editor capabilities for the Secondary Review step of workflows, including Undo, Find & Replace, and Accept All Actions.
The option to disable whitespace penalties during TM leverage using BatchMT. This helps increase leverage and ensure high-quality translation with LILT’s Contextual AI.
We always appreciate your feedback and suggestions for continued improvement of the product. Thank you for working with the LILT team and our platform!