Skip to content

[LLM] Add curated syntactic progression lessons seed dataset and processor #12

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
menny wants to merge 1 commit into
base: false-cognates-seed
Choose a base branch
from
+550 −25
Open

[LLM] Add curated syntactic progression lessons seed dataset and processor #12

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions data/seeds/BUILD.bazel
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,13 +2,15 @@ package(default_visibility = ["//visibility:public"])

exports_files([
"cognate_rules_seed.json",
"curated_lessons_seed.json",
"false_cognates_seed.json",
])

filegroup(
name = "seed_files",
srcs = [
"cognate_rules_seed.json",
"curated_lessons_seed.json",
"false_cognates_seed.json",
],
)
336 changes: 336 additions & 0 deletions data/seeds/curated_lessons_seed.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,336 @@
[
{
"lesson_id": "lvl0_00_cognate_unlock",
"level": 0,
"sequence_order": 0,
"title": "The Cognate Unlock & Vowel Soundboard",
"target_concept": "Recognize shared Latin roots and steady five-vowel Spanish pronunciation in your very first sentences.",
"content": {
"sentences": [
{
"sentence_es": "El hotel moderno es excelente.",
"translation_en": "The modern hotel is excellent.",
"interlinear_gloss": [
{ "es": "El", "en": "the" },
{ "es": "hotel", "en": "hotel" },
{ "es": "moderno", "en": "modern" },
{ "es": "es", "en": "is" },
{ "es": "excelente", "en": "excellent" }
],
"grammar_callout": "Four of these five words are transparent cognates. Only 'el' (the) and 'es' (is) are structural glue."
},
{
"sentence_es": "La música clásica es fantástica.",
"translation_en": "Classical music is fantastic.",
"interlinear_gloss": [
{ "es": "La", "en": "the" },
{ "es": "música", "en": "music" },
{ "es": "clásica", "en": "classical" },
{ "es": "es", "en": "is" },
{ "es": "fantástica", "en": "fantastic" }
],
"grammar_callout": "Spanish uses 'la' before general feminine nouns like 'la música' even when English omits 'the'."
}
]
}
},
{
"lesson_id": "lvl0_01_svo_cognates",
"level": 0,
"sequence_order": 1,
"title": "Basic Subject-Verb-Object with Cognates",
"target_concept": "Decode standard Subject-Verb-Object clauses where suffix bridges (-ción, -dad) unlock the nouns.",
"content": {
"sentences": [
{
"sentence_es": "El profesor explica la situación.",
"translation_en": "The professor explains the situation.",
"interlinear_gloss": [
{ "es": "El", "en": "the" },
{ "es": "profesor", "en": "professor" },
{ "es": "explica", "en": "explains" },
{ "es": "la", "en": "the" },
{ "es": "situación", "en": "situation" }
],
"grammar_callout": "The suffix -ción always maps to English -tion and is always feminine (la situación)."
},
{
"sentence_es": "La universidad organiza una conferencia internacional.",
"translation_en": "The university organizes an international conference.",
"interlinear_gloss": [
{ "es": "La", "en": "the" },
{ "es": "universidad", "en": "university" },
{ "es": "organiza", "en": "organizes" },
{ "es": "una", "en": "an" },
{ "es": "conferencia", "en": "conference" },
{ "es": "internacional", "en": "international" }
],
"grammar_callout": "English -ty maps to -dad (universidad) and -nce maps to -ncia (conferencia)."
}
]
}
},
{
"lesson_id": "lvl0_02_adjectives_after_nouns",
"level": 0,
"sequence_order": 2,
"title": "Adjectives After Nouns",
"target_concept": "Spanish names the thing first and describes it second: Noun + Adjective.",
"content": {
"sentences": [
{
"sentence_es": "El director presenta un proyecto importante.",
"translation_en": "The director presents an important project.",
"interlinear_gloss": [
{ "es": "El", "en": "the" },
{ "es": "director", "en": "director" },
{ "es": "presenta", "en": "presents" },
{ "es": "un", "en": "a" },
{ "es": "proyecto", "en": "project" },
{ "es": "importante", "en": "important" }
],
"grammar_callout": "Read 'un proyecto importante' as a single unit: first see the noun (project), then apply the modifier (important)."
},
{
"sentence_es": "Las soluciones posibles requieren paciencia.",
"translation_en": "The possible solutions require patience.",
"interlinear_gloss": [
{ "es": "Las", "en": "the (pl.)" },
{ "es": "soluciones", "en": "solutions" },
{ "es": "posibles", "en": "possible (pl.)" },
{ "es": "requieren", "en": "require" },
{ "es": "paciencia", "en": "patience" }
],
"grammar_callout": "Adjectives also echo plural endings: 'soluciones' (plural) pulls 'posibles' into the plural."
}
]
}
},
{
"lesson_id": "lvl0_03_negation_and_questions",
"level": 0,
"sequence_order": 3,
"title": "Negation & Question Markers",
"target_concept": "Place 'no' directly before the verb to negate, and use inverted '¿' as an early heads-up for questions.",
"content": {
"sentences": [
{
"sentence_es": "El sistema no funciona correctamente.",
"translation_en": "The system does not work properly.",
"interlinear_gloss": [
{ "es": "El", "en": "the" },
{ "es": "sistema", "en": "system" },
{ "es": "no", "en": "not" },
{ "es": "funciona", "en": "functions / works" },
{ "es": "correctamente", "en": "correctly" }
],
"grammar_callout": "Spanish has no dummy auxiliary like 'does'. Simply put 'no' immediately before the action verb."
},
{
"sentence_es": "¿Necesita el equipo más información?",
"translation_en": "Does the team need more information?",
"interlinear_gloss": [
{ "es": "¿Necesita", "en": "needs?" },
{ "es": "el", "en": "the" },
{ "es": "equipo", "en": "team" },
{ "es": "más", "en": "more" },
{ "es": "información?", "en": "information?" }
],
"grammar_callout": "The opening '¿' tells your internal reading voice to adopt question intonation before you even reach the first word."
}
]
}
},
{
"lesson_id": "lvl0_04_omitted_subjects",
"level": 0,
"sequence_order": 4,
"title": "Omitted Subjects (Verb Endings as Pronouns)",
"target_concept": "Spanish drops subject pronouns ('I', 'we', 'they') because the verb ending already reveals who is acting.",
"content": {
"sentences": [
{
"sentence_es": "Buscamos una oportunidad diferente.",
"translation_en": "We are looking for a different opportunity.",
"interlinear_gloss": [
{ "es": "Buscamos", "en": "we look for" },
{ "es": "una", "en": "a" },
{ "es": "oportunidad", "en": "opportunity" },
{ "es": "diferente", "en": "different" }
],
"grammar_callout": "The ending '-mos' always means 'we' (nosotros). Also note that 'buscar' includes the 'for' inside the verb itself."
},
{
"sentence_es": "Prefieren estudiar en la biblioteca central.",
"translation_en": "They prefer to study in the central library.",
"interlinear_gloss": [
{ "es": "Prefieren", "en": "they prefer" },
{ "es": "estudiar", "en": "to study" },
{ "es": "en", "en": "in" },
{ "es": "la", "en": "the" },
{ "es": "biblioteca", "en": "library" },
{ "es": "central", "en": "central" }
],
"grammar_callout": "A verb ending in '-n' (-an / -en) signals a plural 'they' (or plural 'you')."
}
]
}
},
{
"lesson_id": "lvl0_05_clitic_object_pronouns",
"level": 0,
"sequence_order": 5,
"title": "Clitic Object Pronouns",
"target_concept": "Short object pronouns (lo, la, le, se, me) appear right before conjugated verbs or fuse onto the end of infinitives and gerunds.",
"content": {
"sentences": [
{
"sentence_es": "El médico lo recomienda totalmente.",
"translation_en": "The doctor totally recommends it.",
"interlinear_gloss": [
{ "es": "El", "en": "the" },
{ "es": "médico", "en": "doctor" },
{ "es": "lo", "en": "it" },
{ "es": "recomienda", "en": "recommends" },
{ "es": "totalmente", "en": "totally" }
],
"grammar_callout": "With conjugated verbs, 'lo' (it/him) jumps ahead of the verb: literally 'The doctor it recommends'."
},
{
"sentence_es": "Queremos explicárselo con calma.",
"translation_en": "We want to explain it to him calmly.",
"interlinear_gloss": [
{ "es": "Queremos", "en": "we want" },
{ "es": "explicárselo", "en": "to explain + to him/her + it" },
{ "es": "con", "en": "with" },
{ "es": "calma", "en": "calm" }
],
"grammar_callout": "Pronoun Surgery: 'explicárselo' unpacks into 'explicar' (to explain) + 'se' (to him/her/them) + 'lo' (it)."
}
]
}
},
{
"lesson_id": "lvl1_01_el_problema_en_la_oficina",
"level": 1,
"sequence_order": 1,
"title": "El Problema en la Oficina",
"target_concept": "Read a connected present-tense micro-story combining false cognates (soportar, carpeta) and clitic pronouns.",
"content": {
"sentences": [
{
"sentence_es": "Actualmente Marco trabaja en una oficina muy activa.",
"translation_en": "Currently Marco works in a very busy office.",
"interlinear_gloss": [
{ "es": "Actualmente", "en": "currently" },
{ "es": "Marco", "en": "Marco" },
{ "es": "trabaja", "en": "works" },
{ "es": "en", "en": "in" },
{ "es": "una", "en": "an" },
{ "es": "oficina", "en": "office" },
{ "es": "muy", "en": "very" },
{ "es": "activa", "en": "active / busy" }
],
"grammar_callout": "Trap alert: 'Actualmente' means 'currently', not 'actually'."
},
{
"sentence_es": "Guarda todos los contratos importantes en una carpeta azul.",
"translation_en": "He keeps all the important contracts in a blue folder.",
"interlinear_gloss": [
{ "es": "Guarda", "en": "he keeps" },
{ "es": "todos", "en": "all" },
{ "es": "los", "en": "the" },
{ "es": "contratos", "en": "contracts" },
{ "es": "importantes", "en": "important" },
{ "es": "en", "en": "in" },
{ "es": "una", "en": "a" },
{ "es": "carpeta", "en": "folder" },
{ "es": "azul", "en": "blue" }
],
"grammar_callout": "Trap alert: 'carpeta' is a desk folder or binder, never a floor carpet."
},
{
"sentence_es": "Elena no soporta el ruido y decide explicárselo al director.",
"translation_en": "Elena cannot stand the noise and decides to explain it to the director.",
"interlinear_gloss": [
{ "es": "Elena", "en": "Elena" },
{ "es": "no", "en": "not" },
{ "es": "soporta", "en": "tolerates / stands" },
{ "es": "el", "en": "the" },
{ "es": "ruido", "en": "noise" },
{ "es": "y", "en": "and" },
{ "es": "decide", "en": "decides" },
{ "es": "explicárselo", "en": "to explain + to him + it" },
{ "es": "al", "en": "to the" },
{ "es": "director", "en": "director" }
],
"grammar_callout": "Combines the false friend 'soporta' (tolerates) with the compound clitic verb 'explicárselo' (explicar + se + lo)."
}
]
}
},
{
"lesson_id": "lvl2_01_el_misterio_de_la_libreria",
"level": 2,
"sequence_order": 1,
"title": "El Misterio de la Librería",
"target_concept": "Navigate past-tense narrative contrasts (ongoing imperfecto vs. completed pretérito) in a short story.",
"content": {
"sentences": [
{
"sentence_es": "Llovía intensamente cuando Clara entró en la pequeña librería del barrio.",
"translation_en": "It was raining heavily when Clara walked into the small neighborhood bookstore.",
"interlinear_gloss": [
{ "es": "Llovía", "en": "it was raining" },
{ "es": "intensamente", "en": "intensely / heavily" },
{ "es": "cuando", "en": "when" },
{ "es": "Clara", "en": "Clara" },
{ "es": "entró", "en": "entered" },
{ "es": "en", "en": "in / into" },
{ "es": "la", "en": "the" },
{ "es": "pequeña", "en": "small" },
{ "es": "librería", "en": "bookstore" },
{ "es": "del", "en": "of the" },
{ "es": "barrio", "en": "neighborhood" }
],
"grammar_callout": "'Llovía' (-ía imperfecto) paints the ongoing background weather, while 'entró' (-ó pretérito) marks the single completed action."
},
{
"sentence_es": "Buscaba una novela histórica pero encontró una carta antigua entre las páginas.",
"translation_en": "She was looking for a historical novel, but she found an old letter between the pages.",
"interlinear_gloss": [
{ "es": "Buscaba", "en": "she was looking for" },
{ "es": "una", "en": "a" },
{ "es": "novela", "en": "novel" },
{ "es": "histórica", "en": "historical" },
{ "es": "pero", "en": "but" },
{ "es": "encontró", "en": "she found" },
{ "es": "una", "en": "an" },
{ "es": "carta", "en": "letter" },
{ "es": "antigua", "en": "old / ancient" },
{ "es": "entre", "en": "between" },
{ "es": "las", "en": "the" },
{ "es": "páginas", "en": "pages" }
],
"grammar_callout": "Again, '-aba' (buscaba = was looking for) sets the ongoing intention interrupted by '-ó' (encontró = found)."
},
{
"sentence_es": "La lectura del documento reveló un secreto familiar extraordinario.",
"translation_en": "Reading the document revealed an extraordinary family secret.",
"interlinear_gloss": [
{ "es": "La", "en": "the" },
{ "es": "lectura", "en": "reading" },
{ "es": "del", "en": "of the" },
{ "es": "documento", "en": "document" },
{ "es": "reveló", "en": "revealed" },
{ "es": "un", "en": "an" },
{ "es": "secreto", "en": "secret" },
{ "es": "familiar", "en": "family" },
{ "es": "extraordinario", "en": "extraordinary" }
],
"grammar_callout": "Trap alert: 'lectura' means 'reading' (not lecture), and 'familiar' as an adjective means 'related to family' (not just well-known)."
}
]
}
}
]
1 change: 1 addition & 0 deletions tools/preprocessor/BUILD.bazel
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ kt_jvm_test(
srcs = glob(["src/test/kotlin/**/*.kt"]),
data = [
"//data/seeds:cognate_rules_seed.json",
"//data/seeds:curated_lessons_seed.json",
"//data/seeds:false_cognates_seed.json",
],
test_class = "com.anysoftkeyboard.calque.preprocessor.PreprocessorTest",
Expand Down
Loading
Loading