[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/languages/en-x-emode/13-improvements/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [languages](https://md.mova.elamur.ai/free/en/docs/languages/) / [Early Modern English](https://md.mova.elamur.ai/free/en/docs/languages/en-x-emode/) / 13. Concrete improvements for Mova's parser and lexicon

# 13. Concrete improvements for Mova's parser and lexicon

**On this page**

1. [Status (2026-10-18)](#status-2026-10-18)
2. [Summary table](#summary-table)
3. [Details](#details)
4. [What not to do](#what-not-to-do)

Each item says what to change, where, how many sentences it touches (with the date and the set it was counted on), and its negative control: the case that must stay unchanged, so that the change can show red. Counts: **SLM now** = `en-agreed.bin` over 6 013 Torah sentences aligned with the db; **db** = 6 065 JPS sentences of `parsedb/current.conllu`; all 2026-10-17. Items are ordered by expected gain per line of code.

The items are written so that each can be a separate commit with its own measurement (two runs identical, the Torah and tales cycles as the check, the held-out sets untouched). The «Status» section says which are in the code.

## Status (2026-10-18)

Done: T1, T2, T3, T4, L1, L2, L3, L5, L6, F1, S1; F2 and F3 for the words the tables cover. The rest are proposals.

| # | Where | What the code does now |
| --- | --- | --- |
| L1–L3 | `en/src/morph.rs` (`archaic`, `ending_verb`, `known_form`) | spellings of the stem ranked (CVC stem → «e» spelling, else the most frequent verb in UD); AGID-only superlatives are not dictionary forms; «-est»/«-st» after a past form → that verb, VBD |
| T1, T2, T4 | `en/src/emode.rs` (`CLOSED`, `force`, `fix`) | 78 entries (pronouns, modals, have/do/be forms, saith, lest, unto, behold, lo, aught, nought, whosoever, yea, nay, 35 adverbs, LORD/GOD in capitals, a second reading of «thine» as PRP) with context conditions; the tag is forced in the tagger's beam (`PTagger::tag_forced`), lemma/UPOS/FEATS set after the parse, FEATS filtered by the UD registry |
| T3 | `en/src/emode.rs` (`ending`) | an unknown lower-case word in «-eth»/«-est»/«-st» over a known verb is forced VBZ/VBP/VBD; lemma the verb; FEATS person, number, tense, `Style=Arch` |
| S1 | `en::emode::postverbal_not`, called in `en::annotate` and `gparse annotate` | «not» after a lexical verb (or its postposed pronoun) → the verb's `advmod`; not after let/be/have/do, not before VBG/VBN/TO/JJ/«only» |
| L5 | `gparse/src/data.rs` (`Lex::fill`) | a retagged word unknown to `GP_LEX` is lemmatized for its new tag; a verb keeps an informative old lemma when the new one only repeats the form |
| F1 | `gparse/src/data.rs` (`Lex::table`), `gparse annotate` | every word the EModE table knows with its tags (retagged or not) takes lemma and FEATS from the table |
| L6 | `annot/src/repair.rs`; `annot db-repair <in> <out>`; `drafts_from` | rules `table`, `ending`, `verb-lemma`, `lower-lemma`, `not` over CoNLL-U lines; idempotent; the drafts get it before the gates |

Annotation path: `annot`'s Rust draft goes through `en::annotate::annotate` (one path with `en annotate`). Measurement tools: `en compare <ref> <pred>` (UD scores and agreement by class) and `annot gate-check <drafts>`.

Measured 2026-10-18, `en-agreed.bin`, graph parser `live-0707` with `GP_LEX` = school-agreed, against the 6 065 JPS sentences of `corpora/judaism/parsedb/current.conllu` (a copy taken 2026-10-17 23:47); every run twice, identical:

|  | main before (2026-10-17) | now |
| --- | --- | --- |
| SLM draft: UPOS / XPOS / UFeats | 94.25 / 92.20 / 92.36 | 97.00 / 95.37 / 95.54 |
| SLM draft: lemma / UAS / LAS / MLAS | 98.22 / 84.10 / 78.20 / 62.18 | 98.53 / 85.83 / 81.03 / 68.29 |
| SLM draft: closed EModE words UPOS / UFeats | 64.57 / 49.93 | 96.69 / 95.03 |
| SLM draft: -eth verbs UPOS; -est/-st verbs UPOS | 9.30; 5.48 | 100.00; 97.26 |
| SLM draft: sentences without a UPOS disagreement | 1 873 | 2 834 |
| SLM draft: refused by the gates (of 6 105) | 29 | 5 |
| graph parser: UFeats / MLAS | 95.88 / 83.55 | 96.90 / 85.41 |
| graph parser: verbs with lemma = form (-eth) | 14 626 (546) | 13 994 (3) |
| graph parser: archaic pronouns with Person=3 | 1 981 (old drafts) | 0 |
| graph parser vs the db repaired by L6: lemma / Feats | 98.51 / 94.24 | 99.53 / 97.06 |
| UD English EWT dev LAS (en-agreed.bin; en.bin) | 80.49; 80.29 | 80.50; 80.30 |
| UD English EWT test LAS (en-agreed.bin; en.bin) | 81.25; 81.04 | 81.28; 81.09 |

Lemma agreement with the db itself falls (SLM -eth 67.94 → 38.87, graph parser 99.18 → 98.78) because the db keeps D1, D3 and D6: `giveth` → giveth, `thee` → thee, `Lord` for LORD. `annot db-repair` on a copy of the judaism db (7 982 sentences) changes 3 665 words by `table`, 668 by `ending`, 51 by `not`, 19 by `lower-lemma`, 3 by `verb-lemma`; on its JPS sentences D1 375 → 0, D2 21 → 0, D3 243 → 2, D4 141 → 0, archaic forms without `Style=Arch` 2 817 → 27 tokens, D6 611 → 36, D9 72 → 7; the gates refuse nothing before or after. The shared db is not rewritten: that is the operator's step.

Not done, with the reason: a rule letting a dictionary adjective under a verb tag take the ending («thou lightest») turned *honest* (VB) into *hone*; `never` and modern `not` in S1 cost 0.01 LAS on EWT test; both left out.

## Summary table

| # | Change | Where | Sentences affected | Kind |
| --- | --- | --- | --- | --- |
| T1 | closed-class EModE table before the tagger: pronouns, auxiliaries, `lest`, `unto`, `behold`, `aught` … | `en` (tagger input or a forced-tag pass) | **1 637** (SLM now) | tag |
| T2 | the same for 27 pro-adverbs (`thereof`, `wherewith`, `whither` …) | same; and `archaic_adverbs` selection | **479** (SLM now) | tag |
| T3 | `-eth` / 2nd person `-est` guesser: unknown form = known verb stem + ending → verb tag | `en` tagger features or a pass after it | **573** (SLM now) | tag |
| — | T1–T3 together |  | **2 242** of 6 013 (37 %); 704 would have no UPOS error left |  |
| T4 | `LORD`, `GOD` in capitals → PROPN, lemma `LORD` | tagger pass | 705 (SLM now); 611 db lemmas | tag, lemma |
| T5 | capitalised divine pronouns (`Me`, `Thy`, `Thou`, `He` mid-sentence) → PRON | tagger pass | 110 (SLM now) | tag |
| L1 | `archaic()`: rank candidates by «is a verb lemma» then UD frequency | `en/src/morph.rs` | 55 tokens wrong today (`com`, `se`, `hat`, `li`, `di`, `putt`, `marri` …) | lemma |
| L2 | ignore AGID-only `JJS` analyses for verb tags; drop AGID superlatives of non-adjectives | `en/src/morph.rs` or `en/build.rs` | `goest` 27, `doest` 8, `seest` 7, `shouldest` 8, `liest` 3, … ≈ 60 tokens; plus the SLM's `JJS` tagging of 126 sentences | lemma, tag |
| L3 | 2nd person **past**: `-est`/`-st` after a past form → that form's lemma | `en/src/morph.rs` | `saidst` 7, `broughtest` 3, `stoodest` 2, `knewest`, `drankest`, `sentest`, `defiledst`, `stretchedst`, `badest`, `sawest`, `smotest` ≈ 20 tokens | lemma |
| L4 | strong/old forms table (≈ 50 entries) and old plurals | `en/data/archaic.tsv` via `build.rs` | db: 67 tokens / 62 sentences (D7) + `kine`/`brethren` 137 tokens | lemma |
| L5 | `gparse Lex::fill`: when the tag changes, re-lemmatize with `en::morph` instead of keeping the old lemma | `gparse/src/data.rs` | db: 400 tokens / 328 sentences (D1, D2) | lemma |
| L6 | `annot drafts_from`: extend the AUX lemma repair to VERB (any verb tag) and to `thee` → `thou` | `annot/src/main.rs` | 328 + 202 sentences | lemma |
| F1 | FEATS of the archaic pronouns from a table, never from the tag fallback | `gparse/src/data.rs` (`Lex::fill`) and the table of T1 | db: 98 sentences with `Person=3` on `thou`/`thy`/`thine` (D4) | feats |
| F2 | `Style=Arch` on every archaic form, by the table | T1 table, L4 table | db: 1 681 sentences lack it somewhere (D5) | feats |
| F3 | verb person/number from the ending (`-est` → 2 Sing, `-eth` → 3 Sing) | post-tag pass | db: 3 stray `Plur | Person=3`on`-est` verbs; future drafts |
| S1 | re-attach postverbal `not` to its verb | post-parse rule | db: 72 tokens, about 70 sentences | tree |
| S2 | «it came to pass»: one analysis (`it` expl, `pass` xcomp, event `csubj`/`conj`) | post-parse rule | db: 106 | tree |
| S3 | subjunctive: VB with a subject and a conditional `mark` → `Mood=Sub | Tense=Pres | VerbForm=Fin` | post-parse rule |
| S4 | `for ever`, `to-day`, `to-morrow`, `to-night`: one analysis each | post-parse rule | db: 67 + 14 + 9 + 1 | tree |
| S5 | NP + comma + resumptive pronoun → `dislocated` | post-parse rule | a few dozen («And Abel, he also…», «the LORD, He is God») | tree |
| S6 | `ye` + noun: `ye` head, noun `nmod:unmarked` (EWT) | post-parse rule | db: 4 | tree |
| S7 | lower-case lemma for non-PROPN (`Behold`, `Whosoever`, `Thy`, `Howbeit`, `Amen`, `Nay`) | lemma pass | db: 91 tokens / 87 sentences (D9) | lemma |
| P1 | negators: add `nought`, `naught`, `nay`; `lest` as negative purpose | `prag/src/feats.rs` | 66 `lest` + 8 `nought` + 9 `nay` sentences at most | pragmatics |
| P2 | modal feature from the lemma, or map `shalt`→shall, `wilt`→will, `mayest`→may, `canst`→can, `shouldest`→should … in `norm_word` | `prag/src/feats.rs` | 750 Torah sentences with an archaic modal | pragmatics |
| P3 | subject person: fall back to the pronoun's form (`thou`, `thee`, `ye` → 2) when FEATS disagree | `prag/src/feats.rs` | 98 (D4) | pragmatics |
| P4 | add `thyself` to the second-person list | `prag/src/feats.rs` | 32 `thyself` tokens | pragmatics |
| W1 | extend `archaic_adverbs` with the 19 missing pro-adverbs | [Who can do what to whom — level-1 selectional preferences (2026-10-02)](https://md.mova.elamur.ai/free/en/docs/global/seeds/shortcuts/selection/) | the reranker's lexical repair on 473 sentences (SLM now) | world |
| W2 | register senses for false friends (`even`, `corn`, `suffer`, `quick`, `sore`, `seed`, `stranger`, `know` …) | world dictionary, «formal»/archaic domain (`world/src/domains.rs`) | `at even` 11, `corn` 32, `seed` 93, `stranger` 53 … | world |
| W3 | biblical formulas into the expression base (`found grace in the eyes of`, `lifted up his eyes`, `be cut off from`, `surely die`, `knew his wife`) | [Expressions with their real meanings — the pragmatics lens](https://md.mova.elamur.ai/free/en/docs/docs/pragmatics-expressions/) base | 7 + 9 + 21 + 17 + 2 … | world |
| W4 | partitive `of` after *eat, take, drink, give, offer, bring* | frame reader | `eat of` 34, `take of` 26, … ≈ 80 | world |
| K1 | tokenizer: `'tis`, `'twas`, `'twould`, `may'st`, `could'st`, `ne'er`, `e'er`, `o'er`, `e'en`, `th'` | `en` tokenizer | tales: 112 lines with `'tis`-type, 13 with `-'st`, 44 with `ne'er`-type | token |
| K2 | `an`/`and` + nominative pronoun + finite verb = SCONJ *if* | post-tag rule | tales (`book:pg29672:104` …) | tag |
| R1 | retrain the SLM with the repaired Torah db | `en train` | all | model |
| R2 | add the repaired Torah db to `GP_LEX` (the graph parser's lexicon) | cycle config `CYCLE_LEX` | all retagged archaic tokens | lexicon |

## Details

### T1. A closed-class EModE table before the tagger

**What.** A table of forms whose analysis in the biblical register does not depend on context:

| Form | UPOS | XPOS | Lemma | FEATS |
| --- | --- | --- | --- | --- |
| thou | PRON | PRP | thou | `Case=Nom |
| thee | PRON | PRP | thou | `Case=Acc |
| thy | PRON | PRP$ | thy | `Case=Gen |
| thine | PRON | PRP$ | thy | same |
| thyself | PRON | PRP | thyself | `Case=Acc |
| ye | PRON | PRP | ye | `Case=Nom |
| shalt, wilt, canst, mayest, mayst, mightest, shouldest, shouldst, wouldest, wouldst, couldest, couldst | AUX | MD | shall, will, can, may, may, might, should, should, would, would, could, could | `Number=Sing |
| hast | AUX | VBP | have | `Mood=Ind |
| hath | AUX | VBZ | have | `Mood=Ind |
| hadst | AUX | VBD | have | `Mood=Ind |
| dost, doth, didst | AUX | VBP, VBZ, VBD | do | person, tense, `Style=Arch` |
| wast, wert | AUX | VBD | be | `… |
| saith, sayest | VERB | VBZ, VBP | say | person, `Style=Arch` |
| lest | SCONJ | IN | lest | — |
| unto | ADP | IN | unto | — |
| behold (sentence-initial or before a comma), lo | INTJ | UH | behold, lo | — |
| aught, nought, naught | PRON | NN | aught, nought, naught | `PronType=Ind` / `PronType=Neg` |
| whosoever, whoso | PRON | WP | whosoever, whoso | `PronType=Rel` |

The UPOS of `hath`, `hast`, `hadst` is AUX before a past participle and VERB otherwise; the parser decides (the table gives the lemma and FEATS and the XPOS; the UPOS between AUX and VERB comes from the context, as for modern *have*). `art` needs one context condition: AUX when `thou` is within one word before or after it, otherwise left to the tagger (it is mostly the noun in the tales).

**Where.** A forced-tag pass: the table is `CLOSED` in `en/src/emode.rs` (a Rust constant; each entry carries its «why»), `force` gives the tags to `PTagger::tag_forced` before the tagger decides the rest, `fix` sets lemma, UPOS and FEATS after the parse. The modals carry `Style=Arch|VerbForm=Fin` (EWT gives a modal `VerbForm=Fin` only, no person); `thine` has the lemma *thy*; `art`, `wilt` need `thou` up to two words before or one after; `behold`, `lo` are UH first in the clause, after a punctuation mark or *and*, or before a punctuation mark. `hath`, `hast`, `hadst`, `dost`, `doth`, `didst` take AUX or VERB from the parse; a copula among them becomes `aux`.

**Count.** SLM now: 1 637 sentences have a UPOS error on a T1 form. The table does not need a model.

**Negative control.** «the art of the perfumer» (db `art|NOUN`), «Ye Olde» (not in our texts; the table must not fire on a capitalised `Ye` before a capitalised noun in a modern text), *wilt* the verb (to droop) in a modern text: `wilt` is AUX only before a verb or after `thou`.

### T2. Pro-adverbs

Add to the same table, as ADV with `advmod`: thereof, therein, thereon, thereby, thereto, therewith, whereof, wherein, whereon, wherewith, whereby, whither, whence, thither, hither, thence, hence, wherefore, peradventure, howbeit, yonder, nigh, betimes, hitherto, henceforth, thenceforth, yesternight. SLM now: **479** sentences. `whither`, `whereof`, `wherein`, `wherewith`, `whereon`, `whereby` get `PronType=Rel` when they open a relative clause. Negative control: `hence` and `thence` in modern prose («hence the name») are also ADV — no conflict; `nigh` as an adjective («the time is nigh») → let the parser choose ADJ when it is a predicate after `be`.

**Now.** In `CLOSED`: the 24 *there-*/*thither*/… words as RB/ADV with no FEATS, the 11 *where-* words as WRB/ADV with `PronType` from the annotation, `nigh` only when not after a form of *be*; `yesternight` is left out (the db has it as NOUN). Also `yea`, `nay` as UH/INTJ.

### T3. The `-eth` / `-est` guesser

A form not in the dictionary (or in it only as an AGID superlative, L2) that ends in `-eth`/`-th` or `-est`/`-st` and whose stem (with the spelling rules of chapter 4.3) is a known **verb** lemma is a verb: VBZ with `Number=Sing|Person=3|Style=Arch` for `-eth`; VBP (or VBD after a past stem) with `Number=Sing|Person=2|Style=Arch` for `-est`. SLM now: 454 sentences with an `-eth` error and 126 with an `-est` error, 573 together.

Negative control (all from the Torah): *priest*, *against*, *beast*, *feast*, *harvest*, *interest*, *youngest*, *greatest*, *earth*, *death*, *teeth*, *Beth*, *Heth*, *Japheth*, *twentieth* — every one of these is in the dictionary as a noun, adjective or proper noun, or has a stem that is not a verb.

**Now.** `en::emode::ending` with `en::morph::ending_verb`; the word must be all letters and not capitalised inside the sentence (after a punctuation mark it may be). A lexical verb the parser made AUX is VERB unless its lemma is a registry auxiliary. The negative controls above, with *first*, *must*, *best*, *lest*, *honest*, *forest*, are tests.

### L1–L3. Fixes inside `archaic()`

```
candidates(form):
  for ending in [eth, est, th, st, edst, dst]:
    stem = form - ending
    try: stem, stem+e, undoubled(stem), stem[-i]+y          # spelling rules
    keep candidates c with dict::lemma(c) having a verb paradigm (VB/VBZ/VBD forms)
    and, for -est/-st/-edst/-dst, also stems that are a VBD form → that form's lemma
  pick the kept candidate with the highest UD frequency
```

Unit tests to add (each from the Torah, with the right answer): `cometh`→come, `seeth`→see, `hateth`→hate, `lieth`→lie, `dieth`→die, `putteth`→put, `marrieth`→marry, `biteth`→bite, `rideth`→ride, `writeth`→write, `goest`→go, `doest`→do, `seest`→see, `shouldest`→should, `liest`→lie, `saidst`→say, `broughtest`→bring, `stoodest`→stand, `knewest`→know, `sentest`→send, `badest`→bid. Negative controls: `digest`, `interest`, `harvest`, `greatest`, `rest` with their usual tags (already in `archaic_verbs`), plus `hat`, `com`, `putt` as nouns.

**Now.** All the forms above are tests in `en/src/morph.rs` (`archaic_endings`) and pass. The ranking differs from the sketch: a stem ending consonant–vowel–consonant takes its «e» spelling first (*biteth* → bite, not *bit*), the others go by the verb's UD frequency, then the lemma's. A form is «known» unless AGID alone lists it, as a superlative or comparative (`known_form`). For the past, the VBD reading must be at least as frequent in UD as the form's own present reading (*sawest* → see; *layest* → lay). *badest* is in the verb-only list (AGID has no *bade*).

### L4. The old-forms table

Proposed entries (verb tag required unless marked *):

| Form | Lemma | Form | Lemma | Form | Lemma |
| --- | --- | --- | --- | --- | --- |
| spake* | speak | brake | break | bare | bear |
| sware* | swear | clave* | cleave | gat | get |
| begat* | beget | drave* | drive | sate | sit |
| bade | bid | trode* | tread | clomb* | climb |
| holp*, holpen* | help | durst* | dare | wist* | wit |
| wot* | wit | wrought | work | smote | smite |
| abode | abide | builded* | build | digged* | dig |
| sod | seethe | sodden | seethe | waxen | wax |
| hewn | hew | molten | melt | graven | grave |
| shapen | shape | stricken | strike | laden | lade |
| gotten | get | shew*, shewed*, shewn* | show | quoth* | quoth |
| kine (NNS)* | cow | brethren (NNS)* | brother |  |  |

`wrought` must stay ADJ with lemma *wrought* in «wrought iron»; `sod`, `bare`, `abode`, `laden`, `bade` keep their noun/adjective readings without a verb tag.

### L5. Re-lemmatize after a re-tag

In `gparse/src/data.rs`, `Lex::fill` returns «the most frequent FEATS of the tag, with the old lemma» when the corpus does not know the (form, UPOS, XPOS) triple. Replace the old lemma by `en::morph::Morph.lemmatize(form, Tag::parse(xpos))` (and the FEATS by those of T1/T3 when the form is in the tables). This is the step that turns `giveth` NOUN into `giveth` VERB today. db: **400 tokens in 328 sentences** carry the result (D1 + D2). The same change keeps future rounds clean.

Negative control: a form whose tag does not change keeps its lemma (the current behaviour, `annotate` in `gparse/src/main.rs` already guards this).

**Now.** Done in `Lex::fill`: the EModE table first (F1), then the corpus, then the lemma for the new tag. A verb whose new lemma would only repeat its form keeps an old lemma that does not (*smote* VBD → VBP stays *smite*).

### L6. A deterministic repair pass over the db

The current db can be repaired without a teacher: re-lemmatize every VERB/AUX whose lemma equals an archaic form (L1–L5), set `thee` → `thou`, `thine` → `thy`, `mine` → `my`, lower-case non-PROPN lemmas (S7), and apply F1/F2. Write the result as a new db version (the db keeps `history.conllu` and `log.tsv`), and report the changed token counts per rule. Then re-run the world and the course on it; Torah ★ (252 on 2026-10-17) is the check.

**Now.** `annot db-repair <in.conllu> <out.conllu>` writes the repaired copy and prints the counts per rule (see the status section); `drafts_from` applies the same rules to every draft before the gates. `mine` → *my* is not done (not in the table). Writing it into the shared db, and the world and course re-run, are left to the operator.

### F1–F3. Features

- F1: archaic pronoun FEATS only from the T1 table (db: 98 sentences with `Person=3`).
- F2: `Style=Arch` everywhere the tables fire (db: 1 681 sentences lack it on at least one archaic form). UD English EWT uses it on its single `thou`, `thy`, `ye` and `art` tokens; the registry allows it.
- F3: verb person and number from the ending; remove `Number=Plur|Person=3` from `-est` verbs (3 in the db).

**Now.** F1 in `en::emode::fix` (the SLM draft), `Lex::table` (the graph parser, every word of the table) and `annot db-repair`. F2 for every word of the tables, filtered by the registry (no `Style=Arch` on SCONJ or INTJ). F3 for the words T3 covers.

### S1. Postverbal `not`

Rule: `not` (or `never`) directly after a lexical VERB tagged VB/VBD/VBP/VBZ, or after that verb's postposed pronoun subject, and attached to a word to its right → re-attach to the verb as `advmod`. db: **72** tokens attached elsewhere today. Negative controls: «not the sinew but the bone» (no verb before `not`); «I will not eat» (AUX before `not`); «let not the Lord be angry» (keep: `not` belongs to the lower clause — exception for *let*).

**Now.** `en::emode::postverbal_not`, after the parse in `en::annotate`, `gparse annotate` and `annot db-repair`. Only `not`: `never` and modern `not` («recommend not using», «know not to eat», «has not a Tom») moved EWT words, so the rule skips *be*, *have*, *do* and a `not` before VBG, VBN, TO, JJ or *only*. Torah SLM draft: 114 moved, their head agreeing with the db 33 → 73; the rest are the db's own D10 errors.

### S2. «it came to pass»

Rewrite to: `came` root, `it` `expl`, `to` `mark` of `pass`, `pass` `xcomp`, the `that`-clause `csubj` of `came`, a temporal `as`/`when`-clause `advcl`. db: 106 occurrences, five analyses today. Negative control: «came to the place» (no `pass`), «come to pass» inside a quoted prophecy («it shall come to pass») — same rule, future tense.

### S3. Subjunctive

A VB with a subject, under a `mark` in {if, though, lest, until, till, ere, whether, except, unless}, or a VB root with a third-person subject before it and no auxiliary («God give thee», «cursed be») → `Mood=Sub|Tense=Pres| VerbForm=Fin` plus the subject's person and number (EWT's convention). db: 53 VB tokens with `VerbForm=Inf` in this position, plus 35 `be` tokens (the two overlap). Negative controls: «that thou mayest know» (modal + infinitive); «if ye will do this» (indicative AUX); imperatives (no subject).

### P1–P4. The pragmatic layer

All in `prag/src/feats.rs`:

- `negw`: add *nought*, *naught*, *nay*; treat `lest` as `neg = "purpose"` (or as a separate feature) so that «lest ye die» is not a statement that you die.
- `norm_word`: add `"shalt" => "shall"`, `"wilt" => "will"`, `"canst" => "can"`, `"mayest" | "mayst" => "may"`, `"mightest" => "might"`, `"shouldest" | "shouldst" => "should"`, `"wouldest" | "wouldst" => "would"`, `"couldest" | "couldst" => "could"` — as it already maps `"sha" => "shall"`. 750 Torah sentences.
- subject person: when `w.form` is *thou*, *thee*, *ye*, use 2 whatever FEATS say (D4: 98 sentences).
- the second-person list: add *thyself*.

### W1–W4. The world layer

- W1: `archaic_adverbs` in [Who can do what to whom — level-1 selectional preferences (2026-10-02)](https://md.mova.elamur.ai/free/en/docs/global/seeds/shortcuts/selection/): add thereof, therein, thereon, thereby, thereto, therewith, whereof, wherein, whereon, wherewith, whereby, peradventure, howbeit, nigh, betimes, hitherto, henceforth, thenceforth, yesternight.
- W2: false friends as register senses (chapter 10.3).
- W3: biblical formulas as expressions (chapter 11.4).
- W4: partitive `of` as an object role in frames (chapter 8.3).

### K1–K2. Tokenizer and the conditional `an`

- K1: split `'tis` → `'t` + `is`, `'twas`, `'twere`, `'twill`, `'twould` alike; keep `may'st`, `could'st`, `would'st`, `should'st`, `ne'er`, `e'er`, `o'er`, `e'en`, `th'` as one token each and give them lemmas (*may, could, would, should, never, ever, over, even, the*). Tales: 112 lines with `'tis`-type forms, 13 with `-'st`, 44 with `ne'er`-type forms (pool, 2026-10-17); round 121 refused drafts on the fragments `St`, `st`, `e`, `er`, `lt`, `k`.
- K2: `an`/`and` + nominative pronoun + finite verb → SCONJ, lemma *an*, gloss *if*.

### R1–R2. Training data

- R1: once L6 has repaired the db, add the Torah db to the SLM's training set (JPS 1917 is public domain; the annotation is ours). One word in 32 of the Torah is an archaic pronoun; EWT train has 6 such tokens in all. Follow «examples are not truth»: retrain on the repaired db, measure on the tales and on EWT dev, and keep the Torah test fold out of the training.
- R2: `CYCLE_LEX` (the graph parser's and `treeagree`'s lexicon) is `corpus/school/school-agreed.conllu`, which has no biblical forms; adding the repaired Torah db makes `Lex::fill` find (form, UPOS, XPOS) for every archaic form and stops the `it`-features fallback at the source.

## What not to do

- **Do not normalise the text** (respell `thou` → `you`, `hath` → `has`) before parsing. It would destroy the person and number information (`thou` is singular, `you` is not), break the alignment with the KJV and the Hebrew, and make the db disagree with the text it claims to annotate. Normalisation is for spelling (chapter 2), not for grammar.
- **Do not extend the registry's auxiliary list** with `shalt`, `hath`, `art`: the registry is right, the lemma is wrong.
- **Do not ask the teacher to fix lemmas the tables can fix**: it costs money, it is not deterministic, and the db shows it does not do it reliably (D1–D3).
- [← previous 12. How Mova reads this English today: pipeline, fixes, failures](https://md.mova.elamur.ai/free/en/docs/languages/en-x-emode/12-mova-pipeline/)
- [next → 14. Sample texts, read word by word](https://md.mova.elamur.ai/free/en/docs/languages/en-x-emode/14-sample-texts/)
- [↑ back to Early Modern English](https://md.mova.elamur.ai/free/en/docs/languages/en-x-emode/)