See language model in All languages combined, or Wiktionary
Download JSON data for language model meaning in English (2.4kB)
{
"forms": [
{
"form": "language models",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "language model (plural language models)",
"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": "topical",
"langcode": "en",
"name": "Artificial intelligence",
"orig": "en:Artificial intelligence",
"parents": [
"Computer science",
"Cybernetics",
"Computing",
"Sciences",
"Applied mathematics",
"Systems theory",
"Technology",
"All topics",
"Mathematics",
"Systems",
"Fundamental",
"Formal sciences",
"Interdisciplinary fields",
"Society"
],
"source": "w"
}
],
"derived": [
{
"word": "large language model"
}
],
"examples": [
{
"ref": "2022 [2009], Chengxiang Zhai, Statistical Language Models for Information Retrieval, Springer Nature, page 9",
"text": "Although unigram language models are simple, they clearly make unrealistic assumptions about word occurrences in text.",
"type": "quotation"
}
],
"glosses": [
"A machine learning model that assigns probabilities to sequences of characters or words, and/or is capable of generating plausible subsequent text from a given prompt."
],
"id": "en-language_model-en-noun-MbXSy3a-",
"links": [
[
"machine learning",
"machine learning"
],
[
"model",
"model"
],
[
"probabilities",
"probability"
],
[
"sequences",
"sequences"
],
[
"character",
"character"
],
[
"word",
"word"
],
[
"generating",
"generate"
],
[
"plausible",
"plausible"
],
[
"text",
"text"
],
[
"prompt",
"prompt"
]
],
"qualifier": "machine learning",
"raw_glosses": [
"(machine learning) A machine learning model that assigns probabilities to sequences of characters or words, and/or is capable of generating plausible subsequent text from a given prompt."
],
"related": [
{
"english": "large language model",
"word": "LLM"
}
],
"synonyms": [
{
"word": "LM"
}
],
"translations": [
{
"code": "nl",
"lang": "Dutch",
"sense": "ML model",
"tags": [
"neuter"
],
"word": "taalmodel"
},
{
"code": "fi",
"lang": "Finnish",
"sense": "ML model",
"word": "kielimalli"
},
{
"code": "de",
"lang": "German",
"sense": "ML model",
"tags": [
"neuter"
],
"word": "Sprachmodell"
},
{
"code": "ro",
"lang": "Romanian",
"sense": "ML model",
"tags": [
"neuter"
],
"word": "model de limbă"
},
{
"code": "sv",
"lang": "Swedish",
"sense": "ML model",
"tags": [
"common-gender"
],
"word": "språkmodell"
}
]
}
],
"word": "language model"
}
{
"derived": [
{
"word": "large language model"
}
],
"forms": [
{
"form": "language models",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "language model (plural language models)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"related": [
{
"english": "large language model",
"word": "LLM"
}
],
"senses": [
{
"categories": [
"English countable nouns",
"English entries with incorrect language header",
"English lemmas",
"English multiword terms",
"English nouns",
"English terms with quotations",
"en:Artificial intelligence"
],
"examples": [
{
"ref": "2022 [2009], Chengxiang Zhai, Statistical Language Models for Information Retrieval, Springer Nature, page 9",
"text": "Although unigram language models are simple, they clearly make unrealistic assumptions about word occurrences in text.",
"type": "quotation"
}
],
"glosses": [
"A machine learning model that assigns probabilities to sequences of characters or words, and/or is capable of generating plausible subsequent text from a given prompt."
],
"links": [
[
"machine learning",
"machine learning"
],
[
"model",
"model"
],
[
"probabilities",
"probability"
],
[
"sequences",
"sequences"
],
[
"character",
"character"
],
[
"word",
"word"
],
[
"generating",
"generate"
],
[
"plausible",
"plausible"
],
[
"text",
"text"
],
[
"prompt",
"prompt"
]
],
"qualifier": "machine learning",
"raw_glosses": [
"(machine learning) A machine learning model that assigns probabilities to sequences of characters or words, and/or is capable of generating plausible subsequent text from a given prompt."
],
"synonyms": [
{
"word": "LM"
}
]
}
],
"translations": [
{
"code": "nl",
"lang": "Dutch",
"sense": "ML model",
"tags": [
"neuter"
],
"word": "taalmodel"
},
{
"code": "fi",
"lang": "Finnish",
"sense": "ML model",
"word": "kielimalli"
},
{
"code": "de",
"lang": "German",
"sense": "ML model",
"tags": [
"neuter"
],
"word": "Sprachmodell"
},
{
"code": "ro",
"lang": "Romanian",
"sense": "ML model",
"tags": [
"neuter"
],
"word": "model de limbă"
},
{
"code": "sv",
"lang": "Swedish",
"sense": "ML model",
"tags": [
"common-gender"
],
"word": "språkmodell"
}
],
"word": "language model"
}
This page is a part of the kaikki.org machine-readable English dictionary. This dictionary is based on structured data extracted on 2024-05-05 from the enwiktionary dump dated 2024-05-02 using wiktextract (f4fd8c9 and c9440ce). 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.