TEXTOIR
TEXTOIR is the first opensource toolkit for text open intent recognition. (ACL 2021) (by thuiar)
sapbert
[NAACL'21 & ACL'21] SapBERT: Self-alignment pretraining for BERT & XL-BEL: Cross-Lingual Biomedical Entity Linking. (by cambridgeltl)
TEXTOIR | sapbert | |
---|---|---|
1 | 1 | |
179 | 156 | |
4.5% | 1.3% | |
7.7 | 0.0 | |
3 months ago | about 1 year ago | |
Python | Python | |
MIT License | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
TEXTOIR
Posts with mentions or reviews of TEXTOIR.
We have used some of these posts to build our list of alternatives
and similar projects.
-
[D] Extracting next action from conversation
- Intent extraction models such as https://github.com/thuiar/textoir. My problem with this approach is that they are multi-label classifiers and usually focused on single-sentence classification "Can you get me a table?" would be assigned to the "Reservation" label. I feel that I would lose information such as "Meet at 10PM in this address."
sapbert
Posts with mentions or reviews of sapbert.
We have used some of these posts to build our list of alternatives
and similar projects.
-
Weighting embedding similarity by frequency/saliency
For example, when using concept embeddings, I'd like to be able to score "Exam" <-> "Exam" as less important than "Diabetes" <-> "High blood sugar". But obviously, the former has a similarity of 1.
What are some alternatives?
When comparing TEXTOIR and sapbert you can also consider the following projects:
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
DeBERTa - The implementation of DeBERTa
clip-as-service - 🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
pytorch-metric-learning - The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.