--- sourceDocument: Australia ServiceNow AI Platform Administration sourceDocumentLink: https://www.servicenow.com/docs/r/platform-administration Release : - australia ft:locale : - en-US ft:publication_title : - Australia ServiceNow AI Platform Administration ft:clusterId : - platadm bundleId : - platadm workflow : - Platform --- # Internationalization support # Internationalization support for AI Search {#ariaid-title1} Release version: Australia Updated July 24, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 6 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete. ## Summary of Internationalization support for AI Search AI Search in ServiceNow supports indexing and searching content in multiple languages offered by the ServiceNow AI Platform®. Internationalization is automatically enabled, allowing users to search and retrieve relevant information in a variety of languages without additional configuration. This capability enhances global usability and ensures search accuracy across diverse linguistic contexts. Show full answer Show less ## Supported Languages and Tokenization AI Search supports a comprehensive list of languages including Arabic, Brazilian Portuguese, Czech, Danish, Dutch, English, Finnish, French (including Canadian French), German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian (Bokmål), Polish, Portuguese, Russian, Simplified and Traditional Chinese, Spanish, Swedish, and Turkish. Language-specific tokenization is employed to accurately separate text into terms, which differs by language. For example, tokenization for Chinese and Japanese uses contextual interpretation rather than simple space or punctuation separation. This ensures precise indexing and search matching. After activating a new language plugin, reindexing all relevant content is necessary to make it searchable in that language and to benefit from improved tokenization and feature support. ## Indexing Behavior * **Task table records:** AI Search detects the language automatically from the content and applies corresponding tokenization. Content in unsupported languages defaults to English tokenization. * **Non-Task tables:** Indexing uses the specified language or defaults to the instance's language if none is specified. * **External documents:** Language identification is performed to apply appropriate tokenization, with unsupported languages defaulting to English. * Embedded text in Japanese, Simplified Chinese, and Traditional Chinese within other language content is indexed using the correct tokenization for that embedded text. ## Search Query Processing AI Search processes queries using tokenization settings based on the user's session language, while still recognizing and correctly handling Japanese, Simplified Chinese, and Traditional Chinese terms regardless of the session language. Searches yield reliable matches when query and indexed content are in the same language; mismatched languages may produce unpredictable results. ## Language-Dependent Search Features * **Genius Results:** Evaluated only if the NLU model language matches the query language. * **Language Identification and Tokenization:** Supported for all listed languages, enabling precise text processing. * **Lemma and Unicode Normalization:** Language-specific normalization improves search term matching, with additional term decompounding for some languages. * **Result Improvement Rules, Stop Words, and Synonyms:** Applied only for languages activated in the instance and matching the query language. * **Typo Handling:** Supported for most languages except Japanese, Korean, and Chinese variants. ## Handling Translated Content and Multilingual Search * Users can configure Knowledge article search languages by country to improve multilingual search recall. * Globally searchable knowledge articles can be defined using encoded queries to ensure accessibility across languages. * Facets can be configured to display knowledge article reference field values either in the user's session language or the instance default language. ## Fallback and Language Filtering * When fallback languages are configured for a user session language, AI Search searches translated documents in both the session and fallback languages, using appropriate language-specific dictionaries. * A global fallback locale can also be enabled to match documents beyond the user's session and fallback languages. * Search results from external content connectors are filtered to show only content in the user's session language, fallback language, or global fallback locale language. ## Practical Considerations for ServiceNow Customers * Activate relevant language plugins to enable internationalized search for your user base. * Perform full reindexing of content after activating new languages or updating tokenization improvements to ensure optimal search performance. * Leverage language-dependent features and configure fallback languages to enhance search relevance for multilingual users. * Use configuration options for translated content and knowledge articles to improve search recall and user experience globally. AI Search supports indexing and search in all languages offered by the ServiceNow AI Platform®. Search linguistic features are supported in Arabic, Brazilian Portuguese, Czech, Danish, Dutch, English, Finnish, French, French - Canada, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian (Bokmål), Polish, Portuguese, Russian, Simplified Chinese, Spanish, Swedish, Traditional Chinese, and Turkish. Internationalization support is automatically enabled and isn't configurable. To view the full list of languages offered as ServiceNow AI Platform plugins and supported in AI Search, see [Activate a language](https://www.servicenow.com/docs/Y30JfDvzXwarUH9yXwYnZA "By default, the language supported by the platform is American English. You can activate plugins for other supported languages if you have the admin role."). Note: After you activate a new language plugin, you must reindex all indexed source content that you want to make searchable in the new language. For details on reindexing, see [Perform a full table index or reindex for a single AI Search indexed source](https://www.servicenow.com/docs/bwrBDfHjTH51BUWqtnLaOg "Make content from an internal indexed source searchable by performing a full table index. This procedure indexes existing records from the source table and any child tables configured for indexing. You can manually reindex content from an internal indexed source by repeating this procedure."). Language settings determine how AI Search separates the text of indexed content and search queries into individual terms. This process, called tokenization, is handled differently for each supported language, using language-specific settings. For example, most languages use spaces and punctuation to separate words and sentences, but when tokenizing Chinese or Japanese text, AI Search instead uses contextual interpretation to correctly identify word and sentence breaks. When tokenizing Japanese text, AI Search additionally recognizes the nakaguro (middle dot) as a word separator. Note: If you indexed content in any of the following languages before the specified date, reindex that content to benefit from improved tokenization and feature support added in the AI Search back end.{#international-language-support-ais__table_zyp_xyn_pgc__entry__2} | Date | Languages to reindex | |-|-| | August 2024 | Brazilian Portuguese, Dutch, Italian, Japanese, Korean, Portuguese, Swedish | | August 2025 | Finnish | | December 2025 | Polish | | June 2026 | Arabic, Czech, Danish, Hebrew, Hungarian, Norwegian (Bokmål), Russian, Turkish | [Table 1. Languages requiring reindexing] {#international-language-support-ais__table_zyp_xyn_pgc} ## Indexing behavior in supported languages {#international-language-support-ais__section_ln2_555_fnb} When indexing content and metadata from a ServiceNow AI Platform source record or an external document, AI Search uses tokenization settings for the language of the record or document, as shown in the following table. {#international-language-support-ais__table_kkt_zpc_pvb__entry__2} | Record or document | Tokenization settings | |-|-| | Source record from the Task \[task\] table or one of its child tables | AI Search performs language identification and uses tokenization settings for the detected language to index the record's content and metadata. Note: Language identification only identifies Arabic, Brazilian Portuguese, Czech, Danish, Dutch, English, Finnish, French, French - Canada, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian (Bokmål), Polish, Portuguese, Russian, Simplified Chinese, Spanish, Swedish, Traditional Chinese, and Turkish. Content in other languages is identified and treated as English. | | Source record from a non-Task table | AI Search uses tokenization settings for the record's language to index its content and metadata. If the record has no language specified, the ServiceNow AI Platform treats it as being in the instance's default language. In an English instance, for example, AI Search indexes records without specified languages using tokenization settings for English. | | External document | AI Search performs language identification and uses tokenization settings for the detected language to index the document's content and metadata. Note: Language identification only identifies Arabic, Brazilian Portuguese, Czech, Danish, Dutch, English, Finnish, French, French - Canada, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian (Bokmål), Polish, Portuguese, Russian, Simplified Chinese, Spanish, Swedish, Traditional Chinese, and Turkish. Content in other languages is identified and treated as English. | [Table 2. Indexing behavior by source] {#international-language-support-ais__table_kkt_zpc_pvb} Note: When indexing content and metadata, AI Search recognizes regions of Japanese, Simplified Chinese, and Traditional Chinese text embedded within text in other languages. These text regions are indexed with the appropriate language tokenization settings regardless of the surrounding text's language. As an example, suppose you index an English-language knowledge article that includes a paragraph of Simplified Chinese. AI Search indexes this paragraph's content as Simplified Chinese and the rest of the record's content as English. ## Search query behavior in supported languages {#international-language-support-ais__section_mlh_lsc_pvb} When processing search query text, AI Search uses tokenization settings for the language of the current user's ServiceNow AI Platform session. Note: AI Search recognizes Japanese, Simplified Chinese, and Traditional Chinese terms in search queries. These terms are processed with the appropriate language tokenization settings regardless of the user session's language. As an example, if a user in a French user session searches for remplacement ordinateur 笔记本电脑, AI Search applies Simplified Chinese settings for the 笔记本电脑 term and French settings for the other search terms. AI Search compares your search query terms with terms from indexed content and metadata, returning search results for indexed records or documents that contain matches. When your search terms are in the same language as the indexed terms, AI Search processes both sets of terms with the same tokenization settings, producing predictable matches and search results. If your search terms aren't in the same language as the indexed terms, AI Search processes the two sets of terms with different tokenization settings and matching may be unpredictable. ## Language dependence for search features {#international-language-support-ais__section_ekd_gz4_rnb} The following search features are language-dependent and supported only for the listed languages. {#international-language-support-ais__table_sp5_rt5_fnb__entry__2} | Feature | Language dependence and supported languages | |-|-| | [Genius Results](https://www.servicenow.com/docs/RKKGwiZmvlFBRZh43mRujg "Optionally display the best answers for a search query as actionable Genius Result cards included with search results.") | AI Search only evaluates Genius Result configurations with NLU triggers if the linked NLU model has the same language as the search query. Genius Result configurations that use an LLM or a heuristic model, such as Summary or Q\&A, are limited to languages supported by the model. Supported languages: Arabic, Brazilian Portuguese, Czech, Danish, Dutch, English, Finnish, French, French - Canada, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian (Bokmål), Polish, Portuguese, Russian, Simplified Chinese, Spanish, Swedish, Traditional Chinese, and Turkish. | | Language identification and tokenization | During indexing, AI Search identifies supported languages in Task table records and external documents. Text processing for the indexed content uses tokenization settings for the identified language. Supported languages: Arabic, Brazilian Portuguese, Czech, Danish, Dutch, English, Finnish, French, French - Canada, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian (Bokmål), Polish, Portuguese, Russian, Simplified Chinese, Spanish, Swedish, Traditional Chinese, and Turkish. | | [Lemma and Unicode normalization](https://www.servicenow.com/docs/6Fbn~REzz5F_YfroOW6zaw "AI Search normalizes inflected words and Unicode glyphs during indexing and at search query time. Normalization improves search recall and enables users to find content with variant forms of their search query terms.") | AI Search performs language-specific lemma normalization for terms in indexed content and search queries. Supported languages: Arabic, Brazilian Portuguese, Czech, Danish, Dutch, English, Finnish, French, French - Canada, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian (Bokmål), Polish, Portuguese, Russian, Simplified Chinese, Spanish, Swedish, Traditional Chinese, and Turkish. Note: For German, Danish, Hungarian, Korean, Norwegian (Bokmål), and Swedish, AI Search performs term decompounding in addition to lemma normalization. For Finnish, AI Search uses algorithmic stemming to identify lemmas. AI Search performs Unicode normalization for all terms in indexed content and search queries. For more information on normalization of lemmas and Unicode forms in indexed content and search queries, see [Lemma and Unicode normalization](https://www.servicenow.com/docs/6Fbn~REzz5F_YfroOW6zaw "AI Search normalizes inflected words and Unicode glyphs during indexing and at search query time. Normalization improves search recall and enables users to find content with variant forms of their search query terms."). | | [Result improvement rules](https://www.servicenow.com/docs/TaR44fGFW48~JSklNGO62w "Define rules with configurable trigger conditions to boost, block, or promote search results for specific searches. You can also boost search results for documents matching elements of the user context, such as a user's country, OS, or device type.") | AI Search only evaluates activation for result improvement rules that have the same language as the search query or that have All Languages specified. Supported languages: All languages activated in your instance. For the list of languages you can activate, see [Activate a language](https://www.servicenow.com/docs/Y30JfDvzXwarUH9yXwYnZA "By default, the language supported by the platform is American English. You can activate plugins for other supported languages if you have the admin role."). | | [Stop words](https://www.servicenow.com/docs/eiiQAp3yVs1voI~53xB_VA "Stop words remove search query terms that don't produce meaningful results. Improve search precision and relevancy by configuring stop word dictionaries and defining stop words.") | AI Search only considers stop words from dictionaries that have the same language as the search query. Supported languages: All languages activated in your instance. For the list of languages you can activate, see [Activate a language](https://www.servicenow.com/docs/Y30JfDvzXwarUH9yXwYnZA "By default, the language supported by the platform is American English. You can activate plugins for other supported languages if you have the admin role."). | | [Synonyms](https://www.servicenow.com/docs/BTOwKD3uhCQnDp5Nb8LfEg "Synonyms expand search queries to include additional terms with equivalent meaning or usage. Improve search recall by configuring synonym dictionaries and defining synonyms.") | AI Search only considers synonyms from dictionaries that have the same language as the search query. Supported languages: All languages activated in your instance. For the list of languages you can activate, see [Activate a language](https://www.servicenow.com/docs/Y30JfDvzXwarUH9yXwYnZA "By default, the language supported by the platform is American English. You can activate plugins for other supported languages if you have the admin role."). | | [Typo handling](https://www.servicenow.com/docs/g21GoEvGiHwb9MC3XfCgzg "AI Search replaces misspelled search query terms with auto-correction terms derived from indexed content. Configure typo handling dictionary settings to control derivation of auto-correction terms.") | AI Search derives a separate list of auto-correction terms for each supported language found in search source indexed content. Auto-correction only replaces search query terms with terms from the list that has the same language as the search query. Supported languages: Arabic, Brazilian Portuguese, Czech, Danish, Dutch, English, Finnish, French - Canada, French, German, Hebrew, Hungarian, Italian, Norwegian (Bokmål), Polish, Portuguese, Russian, Spanish, Swedish, and Turkish. Typo handling isn't supported for Japanese, Korean, Simplified Chinese, or Traditional Chinese. | [Table 3. Search feature language dependence] {#international-language-support-ais__table_sp5_rt5_fnb} * **[Searching translated content](https://www.servicenow.com/docs/OBBENolFTyTO377pjCvaxQ)** Understand how AI Search searches translated fields and documents. * **[Assign Knowledge article search languages by country](https://www.servicenow.com/docs/yLoelWSOIPCTa33r~NOPkQ)** Improve multilingual search recall by defining a set of Knowledge article search languages for each user country. User searches can match Knowledge articles in any of the search languages specified for their country as well as in the language associated with their ServiceNow AI Platform® session. * **[Configure globally searchable knowledge articles](https://www.servicenow.com/docs/88USFKaz2V~2SAnO5XyEXQ)** Define an encoded query for knowledge articles that you want to make searchable in any language. * **[Configure translation for knowledge article reference field values in facets](https://www.servicenow.com/docs/Znbp8YRFOmviQBLcZbMhfQ)** Specify whether facets should display knowledge article reference field values in the search user's session language. If you disable translation, facets display knowledge article reference field values in your instance's default language. * **[AI Search interaction with fallback languages](https://www.servicenow.com/docs/_WI660Bi1XhTQND5i948DA)** When a fallback language is configured for the user's session language, AI Search searches translated documents in both languages. Search uses the appropriate stop word, synonym, and typo handling dictionaries for the fallback language. * **[Enable a global fallback locale for translated content](https://www.servicenow.com/docs/HJKEwtQFxSfngmkX_yeb1w)** Configure AI Search to match translated documents in a global fallback locale's language as well as the user's session language. * **[Language filtering for external content](https://www.servicenow.com/docs/nZvNPqKnnx4deJZB7xwufw)** AI Search filters search results from external content connectors, showing only results in the user's session language, fallback language, and global fallback locale language.