dependency_parse
Parse text into per-word heads, dependency relations, POS tags, and morphological features to support syntax-aware extraction such as subject/object probing and definitional clause detection.
Instructions
Neural/statistical dependency parse: head, relation label, POS and morphological features per word (universal-dependencies for stanza).
English: spaCy (en_core_web) by default, stanza also available. Chinese: stanza only - spaCy zh labels are coarse; jieba cannot parse. This is the entry point for syntax-aware extraction: definitional clauses, subject/object probing, syntactic patterns - far above keyword statistics.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"text": "<text>"
},
"name": "dependency_parse"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | auto | |
| text | Yes | ||
| engine | No | auto | |
| max_sents | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||