See bag of words on Wiktionary
{
"forms": [
{
"form": "bags of words",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {
"1": "bags of words",
"head": "bag of words"
},
"expansion": "bag of words (plural bags of words)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "English entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w"
},
{
"kind": "other",
"name": "Entries with translation boxes",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Terms with Portuguese translations",
"parents": [],
"source": "w"
},
{
"kind": "topical",
"langcode": "en",
"name": "Computational linguistics",
"orig": "en:Computational linguistics",
"parents": [
"Computer science",
"Linguistics",
"Computing",
"Sciences",
"Language",
"Social sciences",
"Technology",
"All topics",
"Communication",
"Society",
"Fundamental"
],
"source": "w"
}
],
"derived": [
{
"word": "continuous bag of words"
}
],
"examples": [
{
"ref": "2023, John Paul Mueller, Luca Massaron, Python for Data Science For Dummies, John Wiley & Sons, →ISBN, page 132:",
"text": "You can then use the bag of words to train classifiers, a special kind of algorithm used to break words down into categories.",
"type": "quote"
}
],
"glosses": [
"The collection of words from an unprocessed text without regard to grammar; a collection of word unigrams."
],
"id": "en-bag_of_words-en-noun-1tXne3JR",
"links": [
[
"computational linguistics",
"computational linguistics"
],
[
"collection",
"collection"
],
[
"word",
"word"
],
[
"unprocessed",
"unprocessed"
],
[
"text",
"text"
],
[
"grammar",
"grammar"
],
[
"unigram",
"unigram"
]
],
"raw_glosses": [
"(computational linguistics) The collection of words from an unprocessed text without regard to grammar; a collection of word unigrams."
],
"synonyms": [
{
"word": "BOW"
}
],
"topics": [
"computational",
"computing",
"engineering",
"human-sciences",
"linguistics",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
],
"translations": [
{
"code": "pt",
"lang": "Portuguese",
"sense": "collection of words",
"word": "conjunto de palavras"
}
],
"wikipedia": [
"bag-of-words model"
]
}
],
"word": "bag of words"
}
{
"derived": [
{
"word": "continuous bag of words"
}
],
"forms": [
{
"form": "bags of words",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {
"1": "bags of words",
"head": "bag of words"
},
"expansion": "bag of words (plural bags of words)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"senses": [
{
"categories": [
"English countable nouns",
"English entries with incorrect language header",
"English lemmas",
"English multiword terms",
"English nouns",
"English terms with quotations",
"Entries with translation boxes",
"Pages with 1 entry",
"Pages with entries",
"Terms with Portuguese translations",
"en:Computational linguistics"
],
"examples": [
{
"ref": "2023, John Paul Mueller, Luca Massaron, Python for Data Science For Dummies, John Wiley & Sons, →ISBN, page 132:",
"text": "You can then use the bag of words to train classifiers, a special kind of algorithm used to break words down into categories.",
"type": "quote"
}
],
"glosses": [
"The collection of words from an unprocessed text without regard to grammar; a collection of word unigrams."
],
"links": [
[
"computational linguistics",
"computational linguistics"
],
[
"collection",
"collection"
],
[
"word",
"word"
],
[
"unprocessed",
"unprocessed"
],
[
"text",
"text"
],
[
"grammar",
"grammar"
],
[
"unigram",
"unigram"
]
],
"raw_glosses": [
"(computational linguistics) The collection of words from an unprocessed text without regard to grammar; a collection of word unigrams."
],
"synonyms": [
{
"word": "BOW"
}
],
"topics": [
"computational",
"computing",
"engineering",
"human-sciences",
"linguistics",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
],
"wikipedia": [
"bag-of-words model"
]
}
],
"translations": [
{
"code": "pt",
"lang": "Portuguese",
"sense": "collection of words",
"word": "conjunto de palavras"
}
],
"word": "bag of words"
}
Download raw JSONL data for bag of words meaning in All languages combined (1.8kB)
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2024-11-06 from the enwiktionary dump dated 2024-10-02 using wiktextract (fbeafe8 and 7f03c9b). 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.