See tokenize on Wiktionary
{
"derived": [
{
"_dis1": "0 0 0",
"word": "tokenizable"
},
{
"_dis1": "0 0 0",
"word": "tokenizer"
}
],
"etymology_templates": [
{
"args": {
"1": "en",
"2": "token",
"3": "ize"
},
"expansion": "token + -ize",
"name": "suffix"
}
],
"etymology_text": "From token + -ize.",
"forms": [
{
"form": "tokenizes",
"tags": [
"present",
"singular",
"third-person"
]
},
{
"form": "tokenizing",
"tags": [
"participle",
"present"
]
},
{
"form": "tokenized",
"tags": [
"participle",
"past"
]
},
{
"form": "tokenized",
"tags": [
"past"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "tokenize (third-person singular simple present tokenizes, present participle tokenizing, simple past and past participle tokenized)",
"name": "en-verb"
}
],
"lang": "English",
"lang_code": "en",
"pos": "verb",
"related": [
{
"_dis1": "0 0 0",
"word": "tokenization"
}
],
"senses": [
{
"categories": [
{
"kind": "topical",
"langcode": "en",
"name": "Computing",
"orig": "en:Computing",
"parents": [
"Technology",
"All topics",
"Fundamental"
],
"source": "w"
},
{
"_dis": "61 33 6",
"kind": "other",
"name": "English entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "52 28 20",
"kind": "other",
"name": "English terms suffixed with -ize",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "61 32 7",
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "65 31 5",
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"To reduce to a token or set of tokens by lexical analysis."
],
"id": "en-tokenize-en-verb-jT9kOSc9",
"links": [
[
"computing",
"computing#Noun"
],
[
"token",
"token"
],
[
"lexical analysis",
"lexical analysis"
]
],
"raw_glosses": [
"(transitive, computing) To reduce to a token or set of tokens by lexical analysis."
],
"tags": [
"transitive"
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
},
{
"categories": [
{
"kind": "topical",
"langcode": "en",
"name": "Computing",
"orig": "en:Computing",
"parents": [
"Technology",
"All topics",
"Fundamental"
],
"source": "w"
}
],
"glosses": [
"To substitute sensitive data with meaningless placeholders."
],
"id": "en-tokenize-en-verb--Kj3NOCS",
"links": [
[
"computing",
"computing#Noun"
]
],
"raw_glosses": [
"(transitive, computing) To substitute sensitive data with meaningless placeholders."
],
"tags": [
"transitive"
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
},
{
"categories": [],
"glosses": [
"To treat as a token minority."
],
"id": "en-tokenize-en-verb-bFvBu9Vi",
"links": [
[
"token",
"token"
],
[
"minority",
"minority"
]
],
"raw_glosses": [
"(transitive) To treat as a token minority."
],
"tags": [
"transitive"
]
}
],
"sounds": [
{
"ipa": "/ˈtoʊ.kən.aɪz/",
"tags": [
"General-American"
]
}
],
"wikipedia": [
"Tokenization"
],
"word": "tokenize"
}
{
"categories": [
"English 3-syllable words",
"English entries with incorrect language header",
"English lemmas",
"English terms suffixed with -ize",
"English verbs",
"Pages with 1 entry",
"Pages with entries"
],
"derived": [
{
"word": "tokenizable"
},
{
"word": "tokenizer"
}
],
"etymology_templates": [
{
"args": {
"1": "en",
"2": "token",
"3": "ize"
},
"expansion": "token + -ize",
"name": "suffix"
}
],
"etymology_text": "From token + -ize.",
"forms": [
{
"form": "tokenizes",
"tags": [
"present",
"singular",
"third-person"
]
},
{
"form": "tokenizing",
"tags": [
"participle",
"present"
]
},
{
"form": "tokenized",
"tags": [
"participle",
"past"
]
},
{
"form": "tokenized",
"tags": [
"past"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "tokenize (third-person singular simple present tokenizes, present participle tokenizing, simple past and past participle tokenized)",
"name": "en-verb"
}
],
"lang": "English",
"lang_code": "en",
"pos": "verb",
"related": [
{
"word": "tokenization"
}
],
"senses": [
{
"categories": [
"English transitive verbs",
"en:Computing"
],
"glosses": [
"To reduce to a token or set of tokens by lexical analysis."
],
"links": [
[
"computing",
"computing#Noun"
],
[
"token",
"token"
],
[
"lexical analysis",
"lexical analysis"
]
],
"raw_glosses": [
"(transitive, computing) To reduce to a token or set of tokens by lexical analysis."
],
"tags": [
"transitive"
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
},
{
"categories": [
"English transitive verbs",
"en:Computing"
],
"glosses": [
"To substitute sensitive data with meaningless placeholders."
],
"links": [
[
"computing",
"computing#Noun"
]
],
"raw_glosses": [
"(transitive, computing) To substitute sensitive data with meaningless placeholders."
],
"tags": [
"transitive"
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
},
{
"categories": [
"English transitive verbs"
],
"glosses": [
"To treat as a token minority."
],
"links": [
[
"token",
"token"
],
[
"minority",
"minority"
]
],
"raw_glosses": [
"(transitive) To treat as a token minority."
],
"tags": [
"transitive"
]
}
],
"sounds": [
{
"ipa": "/ˈtoʊ.kən.aɪz/",
"tags": [
"General-American"
]
}
],
"wikipedia": [
"Tokenization"
],
"word": "tokenize"
}
Download raw JSONL data for tokenize meaning in All languages combined (2.2kB)
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2024-12-21 from the enwiktionary dump dated 2024-12-04 using wiktextract (d8cb2f3 and 4e554ae). The data shown on this site has been post-processed and various details (e.g., extra categories) removed, some information disambiguated, and additional data merged from other sources. See the raw data download page for the unprocessed wiktextract data.
If you use this data in academic research, please cite Tatu Ylonen: Wiktextract: Wiktionary as Machine-Readable Structured Data, Proceedings of the 13th Conference on Language Resources and Evaluation (LREC), pp. 1317-1325, Marseille, 20-25 June 2022. Linking to the relevant page(s) under https://kaikki.org would also be greatly appreciated.