collocation_morphology_preprocessor
Preprocess English text with WordNet-style collocation matching, tokenization, and inflectional normalization.
- License 许可
- Apache-2.0
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- collocation_morphology_preprocessor
- description
- Preprocess English text with WordNet-style collocation matching, tokenization, and inflectional normalization.
02 资源文件 2
03 SKILL.md 正文
Collocation and Morphology Preprocessor
Use this skill when a recovery or application needs the preprocessing behavior described in the WordNet report: one sentence per line, WordNet collocation search, tokenization, part-of-speech hints, and morphology-aware lookup forms.
Inputs
- Raw English text.
- A list of known collocations, using spaces or underscores.
Outputs
- Sentence records with original text, token records, normalized lemmas, POS hints, and collocation spans.
Workflow
- Split bounded text into sentence records.
- Lowercase and remove punctuation for matching while preserving original sentence text.
- Greedily match known collocations before single-token normalization.
- Normalize regular plurals and common
-ingor-edinflections. - Emit unknown tokens rather than dropping them, because the ConText-style tagger must record unresolved reasons.
Validation
Run python tests/test_preprocessor.py or the Distiller skill-tree validator with tests enabled.
Limitations
The POS hints are deterministic and lightweight. They are sufficient for reduced recovery but not a replacement for a full part-of-speech tagger.
04 同仓库更多 Skills
passnet-triton-opt
Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.
passnet-solve
END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.
passnet-skill
PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.
passnet-pattern-fusion
Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.
passnet-orchestrate
Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.
passnet-feedback
Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).