Metadata-Version: 2.1
Name: spondee
Version: 0.1.2
Summary: Sentence algorithms for Stanza
License: MIT
Author: tbonza
Author-email: tylers.pile@gmail.com
Requires-Python: >=3.10,<3.13
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Dist: networkx (>=3.3,<4.0)
Requires-Dist: numpy (<2.0.0)
Requires-Dist: pydantic (>=2.7.3,<3.0.0)
Requires-Dist: stanza (>=1.8.2,<2.0.0)
Requires-Dist: torch (>=2.2,<2.3)
Description-Content-Type: text/markdown

# Dactyl

[Sentence Algorithms](https://nlp.stanford.edu/nlp/javadoc/javanlp/edu/stanford/nlp/simple/SentenceAlgorithms.html) for [stanza](https://github.com/stanfordnlp/stanza).

## Related Works

Slot filling tasks such as those referenced by the [KILT Benchmark](https://ai.meta.com/tools/kilt/) may 
better accomplish this goal but are generally more compute intensive and less
explainable:

* [Zero-Shot Relation Extraction via Reading Comprehension](https://nlp.cs.washington.edu/zeroshot/)
* [T-Rex : A Large Scale Alignment of Natural Language with Knowledge Base Triples](https://hadyelsahar.github.io/t-rex/)

Also see [NLP-Progress: Intent Detection and Slot-Filling](https://nlpprogress.com/english/intent_detection_slot_filling.html).

This package extends grammar parsing from [Paradigms of Artificial 
Intelligence Programming: Case Studies in Common Lisp, Norvig (1992)](https://norvig.github.io/paip-lisp/#/).

