Multi-Language HS Classification: How Do You Classify Non-English Product Descriptions?

Why does language matter less than methodology for HS classification?

The Harmonized System is the same internationally. A "cotton knit short-sleeve T-shirt" classifies under HS 6109.10 whether the description is in English, Mandarin, or Spanish. The classification engine needs to understand what the product is (a cotton knit shirt), not which language the description is in. Text-matching APIs that translate the description to English first and then text-match against HTS heading text inherit translation error on top of text-match error. A GRI-logic engine that understands product facts directly applies the same legal reasoning across languages.

---

Review what GingerControl's 99.86% classification accuracy measures before comparing that first-party result with another vendor's benchmark.

---

Why Text-Matching Classification APIs Fail on Non-English Descriptions

Most automated HS classification APIs treat classification as a text-matching problem. They embed the product description, embed the HTS heading text, and find the closest match. This approach has two structural failure modes on non-English descriptions.

Translation error compounds classification error. A text-matching API that translates "棉针织短袖T恤" (Mandarin for cotton knit short-sleeve T-shirt) to English first introduces translation noise. The translation might be "cotton woven T-shirt" or "cotton knitted short sleeve shirt" depending on the translation model. Text matching on the translation then introduces further error. The end result is lower accuracy on non-English descriptions than on English descriptions, because the translation layer is a lossy step before the matching layer.

Some languages do not have direct HTS heading equivalents. HTS headings are written in legal English with specific terms of art ("articles of bedding," "complete or finished article," "in measured doses or for retail sale"). Other languages use different conceptual structures. A direct text-to-text match between, say, a Japanese product description and the English HTS heading may miss the conceptual alignment that determines the correct heading.

The bigger problem is that these failure modes are silent. The API returns a code, the importer files an entry, and the misclassification surfaces only on audit. No vendor publishes accuracy by language, so how much lower the error rate runs on non-English descriptions has not been measured publicly.

Why GRI-Logic Classification Works Across Languages

The General Rules of Interpretation are language-agnostic legal logic. GRI 1 says classification is determined by the terms of the headings and the Section/Chapter Notes. The terms of the headings are facts about what the product is, not strings in English. When the classification engine understands the product as facts (this is a cotton garment, knit construction, short-sleeve, for upper body wear), GRI 1 routes to heading 6109 (T-shirts, singlets, tank tops, and similar garments, knitted or crocheted). The language of the original description does not change the underlying facts.

GingerControl's API operates on product facts. The engine:

1. Extracts product facts from the description: material composition, construction, function, intended use, dimensions, packaging
2. Applies GRI 1-6 to those facts: determines the heading based on the legal rules
3. Applies Section and Chapter Notes as exclusions and inclusions
4. Returns the HTS code with the U.S. duty layers in force on the day of the call

The API response is in English (because HTS is in English), and the API accepts English descriptions and does not accept Chinese; GingerOS, the system GingerControl builds for a company, takes English and Chinese descriptions today. The API manual documents no reasoning trace; the full GRI reasoning report, citing the rule and the legal references behind a code, comes from the Classification Researcher in the GingerLite app.

Common Multi-Language Classification Scenarios

Scenario: Mandarin product descriptions from Chinese suppliers A 3PL receives product data from Chinese suppliers in Mandarin. Manual translation by analyst is the typical approach today. GingerOS takes Chinese descriptions today, so they can go to classification without an analyst translating them first. Your broker reviews each code before U.S. import filing.

For Chinese-language catalogs, HS classification from Mandarin product descriptions separates the supported document workflow from an English-only API input.

Scenario: German technical specifications An importer of German industrial equipment receives technical specifications in German. The specifications include precise material composition and engineering tolerances. German is not one of GingerOS's input languages today (English and Chinese); it is customized for a customer who needs it, so the German technical terms (Stahl, Aluminium, Edelstahl, Gusseisen) can be read as product facts.

Scenario: Spanish-language marketplace seller catalog A marketplace operates in Spain and Latin America with seller catalogs in Spanish. Sellers upload products with Spanish descriptions; the marketplace needs HS classification for cross-border duty calculation. Spanish is customized for a customer who needs it; GingerOS's standard input languages today are English and Chinese.

Scenario: Japanese consumer electronics A consumer electronics distributor sources from Japanese manufacturers with product specifications in Japanese. Product descriptions use Japanese-language technical terms for components, materials, and functions. Japanese is customized for a customer who needs it; with English or Chinese descriptions, the Chapter 85/90 boundary analysis runs as it does for any other product.

Supported Languages

GingerOS, the system GingerControl builds for a company, takes product descriptions in English and Chinese today; the API accepts English descriptions and does not accept Chinese. Other languages are customized for a customer who needs them; if your catalog is in another language, raise it on the first call so it can be scoped and tested on your own products.

How the API Handles Language in the Request and Response

Request body: the description field; the API accepts English descriptions and does not accept Chinese and documents no language parameter.

{
  "description": "棉针织短袖T恤",
  "country_of_origin": "CN"
}

Response: the HTS code and tariff stack are returned in English (because HTS is in English).

{
  "hts_code": "6109.10.0012",
  "tariffs": {
    "general_rate": "16.5%",
    "special_rate": "Free",
    "Section 301": [...]
  }
}

For platforms that need to present results in the source language to end users, the platform's re-rendering layer can translate the English results back to the source language. The structured JSON output makes this re-rendering straightforward.

Why Multi-Language Classification Matters More in 2026

Three trends are increasing the importance of multi-language HS classification:

Cross-border ecommerce growth. Marketplaces serving multiple regions accept seller catalogs in the seller's native language. The marketplace then needs HS classification for cross-border duty calculation. Manual translation is unscalable.

For a storefront catalog, the HS code API for ecommerce catalogs guide covers the product facts and integration points classification needs.

Global 3PL operations. 3PLs onboarding clients in non-English-speaking markets receive product data in the client's language. Translation-then-classification doubles the per-SKU cost and introduces translation error.

Supplier-provided product data in source language. Importers receive product specifications from suppliers in the supplier's language. The classification workflow that requires English translation first adds steps and error.

For each of these trends, a classification API that handles non-English descriptions directly removes a workflow bottleneck and eliminates translation-introduced error.

Multi-Language HS Classification Performance

GingerControl publishes no latency or throughput figures for the API. The batch endpoint takes 120 items per call by default, and each customer's key is sized to its own throughput after a call. GingerControl has not published accuracy by language; its 99.86% figure, at the 10-digit level, is for the quick classification line on its own internal test of 1,000+ products.

Frequently Asked Questions

Does the API translate the description to English before classification?

The public API accepts English descriptions only, not Chinese. Classification Researcher in GingerLite and GingerOS accept English and Chinese. GingerOS can be customized for other languages; confirm specialized terminology using your own products.

What happens if my description uses a mix of languages?

The public API accepts English descriptions only, not Chinese. Classification Researcher in GingerLite and GingerOS accept English and Chinese. GingerOS can be customized for other languages; confirm specialized terminology using your own products.

Does the API support classification for non-US destinations from non-English descriptions?

No. GingerControl's public API accepts English descriptions and returns U.S. import classification and U.S. duty layers only. Its first six HS digits can be a starting point for another country, but confirm that country's national classification. Canadian classification and EU CN8 in beta are available through the Researcher, not the API.

How accurate is multi-language classification compared to English-only classification?

GingerControl has not published accuracy by language. The quick classification line its API uses scored 99.86% at the 10-digit level on GingerControl's own internal test of 1,000+ products, a first-party test, not an independent benchmark. No vendor publishes accuracy by language, so the size of any drop on non-English descriptions has not been measured publicly; translation error compounding with text-match error is the reason to expect one in text-matching APIs.

Can my customers submit descriptions in their native language and receive results in their native language?

The API returns results in English because the HTS schedule itself is in English. For platforms that need to present results in the customer's native language, the platform's re-rendering layer can translate the English results back to the customer's language. The structured JSON output (HTS code and tariff stack) is straightforward to re-render in any language.

Does the API handle product descriptions with special characters and unicode?

The public API accepts English descriptions only, not Chinese. Classification Researcher in GingerLite and GingerOS accept English and Chinese. GingerOS can be customized for other languages; confirm specialized terminology using your own products.

How does the API handle technical terms in non-English languages?

The public API accepts English descriptions only, not Chinese. Classification Researcher in GingerLite and GingerOS accept English and Chinese. GingerOS can be customized for other languages; confirm specialized terminology using your own products.

---

Start Classifying Multi-Language Catalogs

If you operate a global 3PL, an international marketplace, or an importer with non-English supplier data, the classification workflow that requires English translation first is adding cost and introducing error you do not need. The right architecture handles non-English descriptions directly.

See the GingerControl API at gingercontrol.com/products/openapi. It is for enterprise systems, starts with a call and has no published price.

For a company-wide system rather than an API, GingerControl builds GingerOS, the AI trade compliance platform that runs on your process and the data you have, ERP or not. Book a call about embedding multi-language HS classification into your production workflow.

---

References

1. World Customs Organization, Harmonized System Multilingual Edition
   Data cited: HS is internationally standardized with multilingual official versions
   Source: WCO Harmonized System
2. USITC Harmonized Tariff Schedule
   Data cited: U.S. HTS in legal English with internationally harmonized 6-digit framework
   Source: USITC HTS
3. U.S. Customs and Border Protection, Trade Statistics
   Data cited: $216.7 billion in duties, taxes, and fees collected in FY 2025
   Source: CBP Trade Statistics
   Published: 2025
4. CBP Informed Compliance Publication, Reasonable Care
   Data cited: Reasonable care standard, documentation requirements
   Source: CBP Reasonable Care Publication
   Published: September 2017
5. ATLAS: Benchmarking and Adapting LLMs for Global Trade via HTS Classification, arXiv (September 22, 2025; historical 200-example test)
   Context: historical study, not a current ceiling or a comparison with GingerControl's internal test.
   Data cited: Generic LLM accuracy benchmarks for comparison
   Source: arXiv 2509.18400
   Published: 2025

Related Articles

• Automated Global HS Classification: How Do You Classify Across 100+ Countries?