Item listing categorization system

A system comprising:

• a machine having a memory and at least one processor;
• a listing module configured to access listing titles of one or more item listings on a marketplace website, the item listings being associated with a particular product category in a product category structure of the marketplace website;
• and
• a tokenization module, executable by the machine, configured to:
• convert words in each of the listing titles to semantic tokens in a token symbol space, based on a tokenization process;
• perform n-gram modeling on the tokens corresponding to each of the listing titles of the item listings in the particular product category;
• and
• identify one or more dominant n-gram models associated with the listing titles of the item listings in the particular product category, each dominant n-gram model identifying a sequence of one or more semantic tokens that appear in a statistically significant portion of the listing titles of the item listings in the particular product category.

A non-transitory machine-readable storage medium having embodied thereon instructions executable by one or more machines to perform operations comprising:

• accessing listing titles of one or more item listings on a marketplace website, the item listings being associated with a particular product category in a product category structure of the marketplace website;
• converting words in each of the listing titles to semantic tokens in a token symbol space, based on a tokenization process;
• performing n-gram modeling on the tokens corresponding to each of the listing titles of the item listings in the particular product category;
• and
• identifying one or more dominant n-gram models associated with the listing titles of the item listings in the particular product category, each dominant n-gram model identifying a sequence of one or more semantic tokens that appear in a statistically significant portion of the listing titles of the item listings in the particular product category.