pengKiina / KeypartX
KeypartX is a graph-based approach to represent perception (text in general) by key parts of speech.
β0Updated last year
Alternatives and similar repositories for KeypartX:
Users that are interested in KeypartX are comparing it to the libraries listed below
- Versatile framework designed to streamline the integration of your models, as well as those sourced from Hugging Face, into complex progrβ¦β30Updated 3 weeks ago
- π« SpaCy wrapper for ConceptNet π«β92Updated last year
- Explainable Zero-Shot Topic Extractionβ62Updated 8 months ago
- A Python library aimed at dissecting and augmenting NER training data.β58Updated last year
- β43Updated 2 years ago
- An LLM training library for instruction-tuning.β25Updated last year
- Robust and fast topic models with sentence-transformers.β48Updated last week
- Library for creating causal chains using language models.β78Updated 2 years ago
- A BERT-based application for reusable text classification at scaleβ38Updated last year
- HDBSCAN Tuning for BERTopic Modelsβ45Updated last year
- Generalist and Lightweight Model for Text Classificationβ123Updated this week
- Python package for deduplication/entity resolution using active learningβ79Updated 8 months ago
- This repository contains an easy and intuitive approach to use SetFit in combination with spaCy.β79Updated last year
- SpaCyEx allows the creation of spaCy Matcher patterns with RegEx like syntax.β59Updated last year
- spaCy match and replace, maintaining conjugationβ35Updated 2 years ago
- A public repo that contains integrations for Argilla and LlamaIndex.β15Updated 6 months ago
- π₯ Use Hugging Face text and token classification pipelines directly in spaCyβ63Updated last year
- Pre-train Static Word Embeddingsβ58Updated 3 weeks ago
- Alternate Implementation for Zero Shot Text Classification: Instead of reframing NLI/XNLI, this reframes the text backbone of CLIP modelsβ¦β36Updated 3 years ago
- Vespa application making an index of the CORD-19 dataset.β39Updated 3 months ago
- A monolingual and cross-lingual meta-embedding generation and evaluation frameworkβ80Updated 3 years ago
- β54Updated last year
- Creating time-indexed datasets with clusters of texts as inputs and timeseries as targets.β19Updated 3 weeks ago
- RaKUn 2.0 - A fast keyword detection algorithmβ67Updated 2 weeks ago
- Fact checking baseline combining dense retrieval and textual entailmentβ28Updated 3 months ago
- Few-shot Named Entity Recognitionβ123Updated 3 years ago
- Using short models to classify long textsβ21Updated 2 years ago
- [EMNLP 2023 Demo] fabricator - annotating and generating datasets with large language models.β108Updated 11 months ago
- A spaCy custom component that extracts and normalizes temporal expressionsβ54Updated 2 years ago
- An easy way to chunk spaCy docs.β20Updated 8 months ago