pdasigi/onto-lstm
Keras implementation of ontology aware token embeddings
This tool helps natural language processing practitioners improve how computers understand the meaning of words in text. It takes text where each word has been tagged with its part of speech (like noun or verb) and processes it through a specialized neural network layer. The output is a richer, context-aware representation of each word, which can then be used to make other NLP tasks more accurate, especially when dealing with ambiguities.
No commits in the last 6 months.
Use this if you need to build or enhance a system that requires a deeper, more nuanced understanding of word meanings in different contexts, particularly for tasks where word sense disambiguation is critical.
Not ideal if your primary goal is simple keyword matching or if you are working with very small datasets where the overhead of complex embeddings might not yield significant benefits.
Stars
49
Forks
15
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 09, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/pdasigi/onto-lstm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MinishLab/model2vec
Fast State-of-the-Art Static Embeddings
AnswerDotAI/ModernBERT
Bringing BERT into modernity via both architecture changes and scaling
tensorflow/hub
A library for transfer learning by reusing parts of TensorFlow models.
Embedding/Chinese-Word-Vectors
100+ Chinese Word Vectors 上百种预训练中文词向量
twang2218/vocab-coverage
语言模型中文认知能力分析